Papers by Liang Liang

OOP: Object-Oriented Programming Evaluation Benchmark for Large Language Models (2024.findings-acl)

Challenge:	Existing unlearning paradigms are mired in vague forgetting boundaries, erasing knowledge indiscriminately.
Approach:	They propose a benchmark to evaluate if unlearning erases essential knowledge . they propose 'knowUnDo' which uses copyrighted content and privacy domains .
Outcome:	The proposed method is superior to existing methods in both precise knowledge unlearning and general knowledge retaining of LLMs.

Copied to clipboard

Shuai Wang, Liang Ding, Li Shen, Yong Luo, Bo Du, Dacheng Tao

RiOT: Efficient Prompt Refinement with Residual Optimization Tree (2025.acl-long)

Challenge:	None Large language models (LLMs) are emerging as a key tool for automated programming.
Approach:	They compare performance of None Large language models with language understanding models on functional programming and object-oriented programming benchmarks.
Outcome:	The models perform relatively well on functional programming (FP) and object-oriented programming (OOP) benchmarks, while exhibiting poor performance on OOP benchmarks.

Copied to clipboard

Chenyi Zhou, Zhengyan Shi, Yuan Yao, Lei Liang, Huajun Chen, Qiang Zhang

Plan-then-Seam: Towards Efficient Table-to-Text Generation (2023.findings-eacl)

Challenge:	Existing methods for automatic prompt optimization face two challenges: lack of diversity and semantic drift.
Approach:	They propose a framework for automatic prompt optimization that iteratively refines prompts through text gradients and selects the best prompt using perplexity.
Outcome:	The proposed framework outperforms existing prompt optimization methods and manual prompting on commonsense, mathematical, logical, temporal, and semantic reasoning benchmarks.

Copied to clipboard

Liang Li, Ruiying Geng, Chengyang Fang, Bing Li, Can Ma, Binhua Li, Yongbin Li

Improving Model Generalization: A Chinese Named Entity Recognition Case Study (2021.acl-short)

Challenge:	Recent work explicitly decomposes the generation process into content planning and surface generation stages, employing two autoregressive networks for them respectively.
Approach:	They propose a non-parallelelizable table-to-text model that produces outputs in parallel with one network.
Outcome:	The proposed model achieves 3.0 5.6 times speedup for inference time, reducing 50% parameters, while maintaining as least comparable performance against strong two-stage table-to-text competitors.

Copied to clipboard

Guanqing Liang, Cane Wing-Ki Leung

AFT-Tab: Adversarial Fine-Tuning for Tabular Data Synthesis with Long Text Columns (2026.acl-long)

Challenge:	Named Entity Recognition (NER) is a fundamental building block for various downstream natural language processing tasks due to the ambiguous word boundaries and complex composition.
Approach:	They propose to resample entities within the same category to encourage a model to leverage both name and context knowledge in the training process.
Outcome:	The proposed method significantly improves a model’s ability to detect unseen entities, especially for company, organization and position categories.

Copied to clipboard

Yuhao Zhang, Liang Yan, Shaoming Duan, Xinyu Zha, Jinhang Su, Peiyi Han, Chuanyi Liu

Temporal Knowledge Graph Reasoning with Dynamic Hypergraph Embedding (2024.lrec-main)

Challenge:	Existing tabular data synthesis methods fail to account for cross-modal heterogeneity of real-world tables, where structured continuous and discrete attributes coexist with unstructured long-text columns.
Approach:	They propose a framework that synergistically trains an LLM-based text generator and a deep-learning-based non-textual generator to quantify cross-modal semantic alignment.
Outcome:	The proposed framework outperforms state-of-the-art frameworks in fidelity, diversity, and task utility.

Copied to clipboard

Xinyue Liu, Jianan Zhang, Chi Ma, Wenxin Liang, Bo Xu, Linlin Zong

Enhancing Reinforcement Learning for Radiology Report Generation with Evidence-aware Rewards and Self-correcting Preference Learning (2026.acl-long)

Challenge:	Existing models that model temporal dynamics with knowledge graphs and graph convolution networks lack high-order interactions between objects in TKG, which is an important factor to predict future facts.
Approach:	They propose to embed temporal knowledge graph reasoning by constructing hypergraphs based on temporal information graphs at different timestamps and then adapt dynamic meta-embedding to fit TKG.
Outcome:	The proposed method outperforms baseline models on public TKG datasets and provides good interpretation for the predicted results.

Copied to clipboard

Qin Zhou, Guoyan Liang, Qianyi Yang, Jingyuan Chen, Sai Wu, Chang Yao, Zhe Wang

RoleCDE: Benchmarking and Mitigating Role–Alignment Trade-offs in Role-Playing Agents (2026.findings-acl)

Challenge:	Recent reinforcement learning approaches have advanced radiology report generation (RRG) however, there are two limitations: report-level rewards offer limited evidence-grounded guidance for clinical faithfulness .
Approach:	They propose a method that uses group-wise evidence-aware alignment rewards and self-correcting preference learning to build a reliable, disease-agnostic preference dataset without human supervision.
Outcome:	ESC-RL promotes clinically faithful, disease-aligned reward and supports continual self-improvement during training.

Copied to clipboard

Huayi Lai, Shichao Song, Simin Niu, Hanyu Wang, Jiawei Yang, Zhouxing Wang, Zhiqiang Yin, Xun Liang

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders (2025.findings-emnlp)

Challenge:	Existing benchmarks for role-playing agents only evaluate surface-level fidelity and provide limited insight into decision making under role–alignment value conflicts.
Approach:	They propose a benchmark to evaluate RPAs under role–alignment value conflicts . they use 8k diverse role profiles and 240k dilemma instances to evaluate role-aware decision making .
Outcome:	The proposed benchmark covers 8k diverse role profiles and scenarios and nearly 240k dilemma instances across three difficulty levels and eight role categories.

Copied to clipboard

Yuqi Zhang, Yuchun Miao, Zuchao Li, Liang Ding

Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective (2024.acl-long)

Challenge:	AMIA is a lightweight, inference-only defense for Large Vision–Language Models . it automatically masks text-irrelevant image patches and conducts joint Intention Analysis .
Approach:	AMIA is a lightweight, inference-only defense for large vision–language models . it automatically masks a small set of text-irrelevant image patches to disrupt adversarial perturbations .
Outcome:	AMIA improves defense success rates across diverse LVLMs and jailbreak benchmarks . it preserves general utility with only 2% accuracy drop, incurs only modest inference overhead .

Copied to clipboard

Zihao Yue, Liang Zhang, Qin Jin

CACL: Community-Aware Heterogeneous Graph Contrastive Learning for Social Media Bot Detection (2024.findings-acl)

Challenge:	Extensive research has shed light on the origins of multimodal hallucinations, including the inability of vision encoders to represent finegrained visual details and model reliance on inherent parametric knowledge such as language priors and statistical biases.
Approach:	They propose to use EOS to terminate generation of large multimodal models by comparing the generated text with the image to mitigate multimodal hallucinations.
Outcome:	The proposed method significantly improves the hallucination performance of Large Multimodal Models without additional data or knowledge.

Copied to clipboard

Sirry Chen, Shuo Feng, Liang Songsong, Chen-Chen Zong, Jing Li, Piji Li

HutCRS: Hierarchical User-Interest Tracking for Conversational Recommender System (2023.emnlp-main)

Challenge:	Existing methods for social media bot detection neglect community structure and poor model generalization due to the relatively small scale of the dataset.
Approach:	They propose a framework that constructs social networks as heterogeneous graphs and uses community-aware modules to mine hard positive and hard negative samples for supervised graph contrastive learning.
Outcome:	The proposed framework outperforms baselines on three social media bot benchmarks.

Copied to clipboard

Mingjie Qian, Yongsen Zheng, Jinghui Qin, Liang Lin

Multiview Clickbait Detection via Jointly Modeling Subjective and Objective Preference (2023.findings-emnlp)

Challenge:	Existing CRSs assume that users like all attributes of the target item and dislike those unrelated to it, which can introduce bias in attribute-level feedback and impede the system’s ability to accurately identify the target items.
Approach:	They propose a framework that allows users to explicitly acquire user preferences through natural language conversations by providing explicit answers (yes/no) for each attribute they require.
Outcome:	The proposed framework portrays the conversation as a hierarchical interest tree that consists of two stages.

Copied to clipboard

Chongyang Shi, Yijun Yin, Qi Zhang, Liang Xiao, Usman Naseem, Shoujin Wang, Liang Hu

CHIFRAUD: A Long-term Web Text Dataset for Chinese Fraud Detection (2025.coling-main)

Challenge:	Existing clickbait detection models rely on analyzing the objective semantics of posts or correlating posts with article content only, but fail to identify and exploit the manipulation intention of clickbaiting from a user’s subjective perspective.
Approach:	They propose a multiview clickbait detection model to model subjective and objective preferences simultaneously to capture clickbaiting from a user's subjective perspective.
Outcome:	The proposed model outperforms state-of-the-art models on two real-world datasets and shows that it integrates subjective and objective preferences simultaneously.

Copied to clipboard

Min Tang, Lixin Zou, Zhe Jin, ShuJie Cui, Shiuan Ni Liang, Weiqing Wang

Transductive Learning for Unsupervised Text Style Transfer (2021.emnlp-main)

Challenge:	Detecting fraudulent online text is essential as they exploit human greed and deceive individuals.
Approach:	They propose to build a long-term dataset of Chinese fraudulent texts collected over 12 months.
Outcome:	The proposed dataset includes 59,106 entries extracted from billions of web pages and includes large language model-based detectors and pre-trained language model approaches.

Copied to clipboard

Fei Xiao, Liang Pang, Yanyan Lan, Yan Wang, Huawei Shen, Xueqi Cheng

Backdoor Collapse: Eliminating Unknown Threats Via Known Backdoor Aggregation In Language Models (2026.acl-long)

Challenge:	Existing methods for style transfer are based on an inductive learning approach, which represents the style as embeddings, decoder parameters, or discriminator parameters and directly applies these general rules to the test cases.
Approach:	They propose a retrieval-based context-aware style representation that involves top-K relevant sentences in the target style in the transfer process.
Outcome:	The proposed method outperforms several strong baselines and is general and effective to the task of unsupervised style transfer.

Copied to clipboard

Liang Lin, Miao Yu, Moayad Aloqaily, Zhenhong Zhou, Kun Wang, Linsey Pang, Prakhar Mehrotra, Qingsong Wen

CogGPT: Unleashing the Power of Cognitive Dynamics on Large Language Models (2024.findings-emnlp)

Challenge:	Existing defenses rely on impractical assumptions about trigger settings to mitigate backdoor attacks . a recent study found that small amounts of training data can systematically induce harmful behaviors in large language models.
Approach:	They propose a backdoor defense framework that requires no prior knowledge of trigger settings . they use a two-stage process to aggregate backdoor representations and fine-tune recovery .
Outcome:	The proposed defense reduces the average Attack Success Rate to 4.41% across multiple benchmarks . the proposed framework generalizes across different types of backdoors, confirming its robustness in practical deployment scenarios.

Copied to clipboard

Yaojia Lv, Haojie Pan, Zekun Wang, Jiafeng Liang, Yuanxing Liu, Ruiji Fu, Ming Liu, Zhongyuan Wang, Bing Qin

GraphCache: Message Passing as Caching for Sentence-Level Relation Extraction (2022.findings-naacl)

Challenge:	Recent advances in large language models (LLMs) focus on replicating human cognition in specific contexts, overlooking the inherently dynamic nature of cognition.
Approach:	They propose a task to assess cognitive dynamics of large language models (LLMs) they introduce a benchmark and two evaluation metrics to validate the benchmark and evaluate it through participant surveys.
Outcome:	The proposed task overcomes the limitations of existing methods and is available for download.

Copied to clipboard

Yiwei Wang, Muhao Chen, Wenxuan Zhou, Yujun Cai, Yuxuan Liang, Bryan Hooi

How Do Humans Write Code? Large Models Do It the Same Way Too (2024.emnlp-main)

Challenge:	Existing work only encodes entity types and textual context within individual instances, which limits the performance of sentence-level relation extraction (RE).
Approach:	They propose a module that aggregates the features from sentences to learn global representations of properties and augments local features within individual sentences.
Outcome:	The proposed module can learn global representations of properties from sentences and augment local features within individual sentences.

Copied to clipboard

Long Li, Xuzheng He, Haozhe Wang, Linlin Wang, Liang He

Too Long, Do Re-weighting for Efficient LLM Reasoning Compression (2026.acl-long)

Challenge:	Program-of-Thought (PoT) replaces natural language-based Chain-ofThough (CoT) but introduces more reasoning errors, such as incorrect formulas or flawed logic, compared to CoT.
Approach:	They propose a method that integrates CoT and Program-of-Thought to achieve more accurate reasoning and reinforcement learning.
Outcome:	The proposed method achieves an average improvement of 6.5% on the Llama-Base model and 4.3% on the Mistral-Bass model across 8 mathematical calculation datasets.

Copied to clipboard

Zhong-Zhi Li, Xiao Liang, Zihao Tang, Lei Ji, Peijie Wang, Haotian Xu, Xing W, Haizhen Huang, Weiwei Deng, Yeyun Gong, Zhijiang Guo, Xiao Liu, Fei Yin, Cheng-Lin Liu

A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos (2025.findings-acl)

Challenge:	Large Language Models (LLMs) have recently achieved remarkable progress on complex reasoning tasks by leveraging extended Chain-of-Thought (CoT) techniques.
Approach:	They propose a method that uses Extended Chain-of-Thought (EFT) to reduce the number of output tokens by nearly 40% while maintaining the accuracy of the reasoning.
Outcome:	The proposed method reduces the number of output tokens by nearly 40% while maintaining the accuracy of the reasoning.

Copied to clipboard

Yang Yao, Xuan Tong, Ruofan Wang, Yixu Wang, Lujundong Li, Liang Liu, Yan Teng, Yingchun Wang

A Regularization-based Transfer Learning Method for Information Extraction via Instructed Graph Decoder (2024.lrec-main)

Challenge:	Large Reasoning Models (LRMs) have advanced beyond traditional Large Language Models, yet they pose heightened safety risks.
Approach:	They propose a first jailbreak attack targeting Large Reasoning Models . they exploit a Chaos Machine component to transform attack prompts with diverse one-to-one mappings based on the reasoning chain .
Outcome:	The proposed attack exploits the unique vulnerabilities of LRMs by integrating a Chaos Machine. success rates of the mousetrap attack are as high as 96%, 86% and 98% respectively.

Copied to clipboard

Kedi Chen, Jie Zhou, Qin Chen, Shunyu Liu, Liang He

CLaw: Benchmarking Chinese Legal Knowledge in Large Language Models - A Fine-grained Corpus and Reasoning Analysis (2025.findings-emnlp)

Challenge:	Existing methods for information extraction (IE) focus on training task-specific models, while common knowledge among different IE tasks is not explicitly modeled.
Approach:	They propose a regularization-based transfer learning method for IE via an instructed graph decoder which decodes various complex structures into a graph uniformly based on corresponding instructions.
Outcome:	The proposed method can learn common knowledge from existing datasets and transfer it to a new dataset with new labels.

Copied to clipboard

Xinzhe Xu, Liang Zhao, Hongshen Xu, null Chenchenc

Difference-Masking: Choosing What to Mask in Continued Pretraining (2023.findings-emnlp)

Challenge:	a new benchmark is designed to evaluate LLMs on Chinese legal knowledge and its application in reasoning . general pre-training that ingests legal texts without specialized focus compromises reliability of LLM responses . achieving trustworthy legal reasoning in LLM requires a robust synergy of accurate knowledge retrieval and strong general reasoning capabilities.
Approach:	They propose a benchmark specifically engineered to evaluate LLMs on Chinese legal knowledge and its application in reasoning.
Outcome:	The proposed benchmark evaluates LLMs on Chinese legal knowledge and its application in reasoning.

Copied to clipboard

Alex Wilf, Syeda Akter, Leena Mathur, Paul Liang, Sheryl Mathew, Mengrou Shou, Eric Nyberg, Louis-Philippe Morency

DentalGPT: Incentivizing Multimodal Reasoning in Dentistry (2026.findings-acl)

Challenge:	Existing approaches to masked prediction have shown that deciding what to mask can substantially improve learning outcomes.
Approach:	They propose a masking strategy that automatically chooses what to mask during continued pretraining by considering what makes a task domain different from the pretraining domain.
Outcome:	The proposed masking strategy outperforms baselines on language-only and multimodal video tasks.

Copied to clipboard

Zhenyang Cai, Jiaming Zhang, Junjie Zhao, Ziyi Zeng, Yanchao Li, Liang Jingyi, Junying Chen, Yunjin Yang, Jiajun You, Shuzhi Deng, null Xieruiqiii, Yuanting Chen, Xiangyi Feng, Jianquan Li, Liangyi Chen, Junwen Wang, Shan Jiang, Benyou Wang

Composable Text Controls in Latent Space with ODEs (2023.emnlp-main)

Challenge:	Current multimodal large language models (MLLMs) show limited understanding of dental images.
Approach:	They propose a dental-specialized multimodal large language model trained via staged multimodal alignment and reinforcement learning.
Outcome:	The proposed model outperforms state-of-the-art models on disease classification and dental VQA tasks.

Copied to clipboard

Guangyi Liu, Zeyu Feng, Yuan Gao, Zichao Yang, Xiaodan Liang, Junwei Bao, Xiaodong He, Shuguang Cui, Zhen Li, Zhiting Hu

CriticBench: Benchmarking LLMs for Critique-Correct Reasoning (2024.findings-acl)

Challenge:	Existing approaches to composable text operations often require plug-and-play . a single LM can perform arbitrary text operation composition in the latent space .
Approach:	They propose an efficient approach for composable text operations in the latent space of text . they connect pretrained LMs to the laten space and adapt them to the space .
Outcome:	The proposed approach improves on existing methods in the latent space of text.

Copied to clipboard

Zicheng Lin, Zhibin Gou, Tian Liang, Ruilin Luo, Haowei Liu, Yujiu Yang

Dual-Axis Generative Reward Model Toward Semantic and Turn-taking Robustness in Interactive Spoken Dialogue Models (2026.acl-long)

Challenge:	CriticBench is a benchmark designed to assess LLMs’ abilities to critique and refine their reasoning across a variety of tasks.
Approach:	They propose a benchmark to assess LLMs' ability to critique and correct reasoning across a variety of tasks.
Outcome:	The proposed benchmark examines the performance of 17 large language models in generation, critique, and correction reasoning.

Copied to clipboard

Yifu Chen, Shengpeng Ji, Zhengqing Liu, Qian Chen, Wen Wang, Ziqing Wang, Yangzhuo Li, Tianle Liang, Zhou Zhao

PivotAttack: Rethinking the Search Trajectory in Hard-Label Text Attacks via Pivot Words (2026.findings-acl)

Challenge:	Reinforcement learning (RL) has improved text- and vision-language models, but its application in SDMs is hindered.
Approach:	They propose a dual-axis Generative Reward Model that provides semantic quality and interaction timing for SDMs.
Outcome:	The proposed model achieves state-of-the-art performance on interaction-quality assessment across a wide spectrum of datasets.

Copied to clipboard

Yuzhi Liang, Shiliang Xiao, Jingsong Wei, Qiliang Lin, Xia Li

Convolutional Interaction Network for Natural Language Inference (D18-1)

Challenge:	Existing hard-label text attacks rely on inefficient "outside-in" strategies that traverse vast search spaces.
Approach:	They propose a query-efficient "inside-out" framework that perturbs Pivot Sets to induce label flips.
Outcome:	The proposed framework outperforms state-of-the-art methods in both Attack Success Rate and query efficiency.

Copied to clipboard

Jingjing Gong, Xipeng Qiu, Xinchi Chen, Dong Liang, Xuanjing Huang

Human-Inspired Obfuscation for Model Unlearning: Local and Global Strategies with Hyperbolic Representations (2025.findings-emnlp)

Challenge:	Attention-based neural models have achieved great success in natural language inference (NLI).
Approach:	They propose a general model to capture the interaction between two sentences, which can be an alternative to the attention mechanism for NLI.
Outcome:	The proposed model can capture complex interactions on three large datasets.

Copied to clipboard

Zekun Wang, Jingjie Zeng, Yingxu Li, Liang Yang, Hongfei Lin

Reason-KE++: Aligning the Process, Not Just the Outcome, for Faithful LLM Knowledge Editing (2026.findings-acl)

Challenge:	Existing methods for unlearning large language models struggle to balance effective forgetting with maintaining model utility.
Approach:	They propose a human-inspired unlearning framework that simulates forgetting on fuzzy data and represents them in hyperbolic and Euclidean spaces.
Outcome:	The proposed framework is able to forget sensitive content while maintaining the model’s language understanding, fluency, and benchmark performance.

Copied to clipboard

Yuchen Wu, Liang Ding, Li Shen, Dacheng Tao

Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations (2026.acl-long)

Challenge:	Current methods for modifying parameters to integrate new knowledge are not accurate enough.
Approach:	They propose an SFT+RL framework that instills process-level faithfulness by a stage-aware Reward mechanism and a Stage-assisted Reward Mechanism.
Outcome:	The proposed framework instills process-level faithfulness while boosting final accuracy.

Copied to clipboard

Wen Luo, Guangyue Peng, Wei Li, Shaohang Wei, Feifan Song, Liang Wang, Nan Yang, Xingxing Zhang, Jing Jin, Furu Wei, Houfeng Wang

Zero-shot Sharpness-Aware Quantization for Pre-trained Language Models (2023.emnlp-main)

Challenge:	Previous work shows that large language models generate hallucinations, yet the origins and mechanisms of these signals remain unclear.
Approach:	They propose to validate and disentangle two different pathways for truthfulness cues . they also propose to use the same mechanism to derive self-contained evidence from the generated answer .
Outcome:	The proposed applications improve hallucination detection performance by integrating two different inputs.

Copied to clipboard

Miaoxi Zhu, Qihuang Zhong, Li Shen, Liang Ding, Juhua Liu, Bo Du, Dacheng Tao

JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance Detection (2022.acl-long)

Challenge:	Existing zero-shot quantization methods are based on overfitting problem in adversarial learning process, leading to sub-optimal performance.
Approach:	They propose a zero-shot sharpness-aware quantization framework for the quantization of various PLMs by optimizing a minimax problem.
Outcome:	The proposed framework can achieve significant performance gains on discriminative and generative PLMs.

Copied to clipboard

Bin Liang, Qinglin Zhu, Xiang Li, Min Yang, Lin Gui, Yulan He, Ruifeng Xu

GroupToM-Bench: Benchmarking Group Theory of Mind and Nonlinear Social Emergence in MLLMs (2026.acl-long)

Challenge:	Existing methods achieve promising performance in in-target stance detection when trained and tested on the same datasets.
Approach:	They propose a joint contrastive learning framework to generalize stance features for unseen targets.
Outcome:	The proposed framework achieves state-of-the-art on three benchmark datasets.

Copied to clipboard

Weidong Tang, Jierui Li, Yueling Hou, Zihan Mei, Can Zhang, Xinyan Wan, Zhiyuan Liang, Pengfei Zhou, Yang You, Wangbo Zhao

Linguistics & Cognitive NLP

Challenge:	Existing models for general intelligence fail to model how mental states interact and crystallize into group-level outcomes.
Approach:	They propose a multimodal benchmark for group-level Theory of Mind (ToM) to probe nonlinear collective behavior.
Outcome:	The proposed model performs significantly below human levels, exposing blind spots in modeling social structures and nonlinear collective behavior.

Continual Learning with Semi-supervised Contrastive Distillation for Incremental Neural Machine Translation (2024.acl-long)

Copied to clipboard

Yunlong Liang, Fandong Meng, Jiaan Wang, Jinan Xu, Yufeng Chen, Jie Zhou

IEPile: Unearthing Large Scale Schema-Conditioned Information Extraction Corpus (2024.acl-short)

Challenge:	Multi-domain learning is a good solution for solving domain tasks but it requires retraining when adding a new domain.
Approach:	They propose to exploit unlabeled data from the same distributions of the older domains to avoid catastrophic forgetting.
Outcome:	The proposed framework exploits unlabeled data from the same distributions of the older domains to avoid catastrophic forgetting.

Copied to clipboard

Honghao Gui, Lin Yuan, Hongbin Ye, Ningyu Zhang, Mengshu Sun, Lei Liang, Huajun Chen

Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts (2026.acl-long)

Challenge:	Large Language Models exhibit a significant performance gap in Information Extraction (IE) high-quality instruction data is the vital key for enhancing LLMs' specific capabilities .
Approach:	They propose a bilingual (English and Chinese) IE instruction corpus that contains 0.32B tokens.
Outcome:	The proposed model improves the performance of LLMs for IE with zero-shot generalization.

Copied to clipboard

Sijia Luo, Xiaokang Zhang, Yuxuan Hu, Bohan Zhang, Ke Wang, Jinbo Su, Mengshu Sun, Lei Liang, Jing Zhang

Challenge:	Existing methods for storing key-value caches during long-horizon rollouts cause performance collapses.
Approach:	They propose a new training paradigm that empowers stable RL training under sparse rollouts.
Outcome:	The proposed model reduces rollout overhead while maintaining the performance.

Curriculum Knowledge Distillation for Emoji-supervised Cross-lingual Sentiment Analysis (2022.emnlp-main)

Copied to clipboard

Jianyang Zhang, Tao Liang, Mingyang Wan, Guowu Yang, Fengmao Lv

Exploring the Capability of Multimodal LLMs with Yonkoma Manga: The YManga Dataset and Its Challenging Tasks (2024.findings-emnlp)

Challenge:	Existing sentiment analysis models do not have sufficient sentiment corpus to detect sentiment in low-resource languages.
Approach:	They propose a cross-lingual sentiment analysis approach to transfer sentiment knowledge across languages . they use emojis to bridge the source and target languages to find the sentiment .
Outcome:	The proposed approach bridges the source and target languages using emojis . it can learn delicate sentiment knowledge, avoiding cross-lingual gaps .

Copied to clipboard

Qi Yang, Jingjie Zeng, Liang Yang, Zhihao Yang, Hongfei Lin

OpenVNA: A Framework for Analyzing the Behavior of Multimodal Language Understanding System under Noisy Scenarios (2024.acl-demos)

Challenge:	YManga dataset is the first specifically designed for yonkoma manga understanding .
Approach:	They propose to use a dataset of 1,015 yonkoma strips with 10,150 human annotations to define three tasks for panel sequence detection, intent generation and description generation for masked panels.
Outcome:	The proposed dataset contains 1,015 high-quality yonkoma strips with 10,150 human annotations.

Copied to clipboard

Ziqi Yuan, Baozheng Zhang, Hua Xu, Zhiyun Liang, Kai Gao

Multi-Stage Pre-training Enhanced by ChatGPT for Multi-Scenario Multi-Domain Dialogue Summarization (2023.findings-emnlp)

Challenge:	OpenVNA is an open-source framework for analyzing the behavior of multimodal language understanding systems under noisy conditions.
Approach:	They propose to use OpenVNA to analyze behavior of multimodal language understanding systems under noisy conditions.
Outcome:	The proposed framework provides high flexibility and extensibility, enabling customization with user-defined noise types and models.

Copied to clipboard

Weixiao Zhou, Gengyao Li, Xianfu Cheng, Xinnian Liang, Junnan Zhu, Feifei Zhai, Zhoujun Li

Tutorial on Multimodal Machine Learning (2022.naacl-tutorials)

Challenge:	Existing methods for dialogue summarization only apply to specific scenarios and domains.
Approach:	They propose a pre-trained model specifically designed for multi-scenario multi-domain dialogue summarization.
Outcome:	The proposed model significantly outperforms state-of-the-art models on three dialogue summarization datasets from different scenarios and domains.

Copied to clipboard

Louis-Philippe Morency, Paul Pu Liang, Amir Zadeh

Self-Supervised Learning for Pairwise Data Refinement (2020.aacl-main)

Challenge:	Multimodal machine learning is a challenging but crucial area with numerous applications in multimedia, affective computing, robotics, finance, HCI, and healthcare.
Approach:	This tutorial will describe an updated taxonomy on multimodal machine learning synthesizing its core technical challenges and major directions for future research.
Outcome:	The proposed taxonomy synthesizes the core technical challenges and major directions for future research.

Copied to clipboard

Gustavo Hernandez Abrego, Bowen Liang, Wei Wang, Zarana Parekh, Yinfei Yang, Yunhsuan Sung

Sarcasm-R1: Enhancing Sarcasm Detection through Focused Reasoning (2025.findings-emnlp)

Challenge:	Pairwise data constructed from weakly supervised signals is widely used for training deep learning models.
Approach:	They propose two methods to refine pairwise data that are aimed to obtain subsets that are more useful as learning examples.
Outcome:	The proposed methods achieve most machine translation gains in the first iteration, but following iterations further improve its intrinsic evaluation.

Copied to clipboard

Qi Yang, Jingjie Zeng, Liang Yang, Kai Ma, Hongfei Lin

SKD-NER: Continual Named Entity Recognition via Span-based Knowledge Distillation with Reinforcement Learning (2023.emnlp-main)

Challenge:	Existing methods for sarcasm detection are limited by supervised learning or prompt engineering . a new approach decomposes sarcasm detection into three dimensions: language, context, and emotion .
Approach:	They propose a method that decomposes sarcasm detection into three dimensions: language, context, and emotion.
Outcome:	The proposed method outperforms state-of-the-art methods in most cases.

Copied to clipboard

Yi Chen, Liang He

Large Language Models are not Fair Evaluators (2024.acl-long)

Challenge:	Continual learning for named entity recognition (CL-NER) aims to enable models to continuously learn new entity types while retaining the ability to recognize previously learned ones.
Approach:	They propose a model that leverages knowledge distillation to retain memory and employs reinforcement learning strategies to optimize the soft labeling and distillation losses generated by the teacher model to effectively prevent catastrophic forgetting.
Outcome:	The proposed model outperforms state-of-the-art models on two benchmark datasets showing that it significantly improves the performance of the CL-NER task.

Copied to clipboard

Peiyi Wang, Lei Li, Liang Chen, Zefan Cai, Dawei Zhu, Binghuai Lin, Yunbo Cao, Lingpeng Kong, Qi Liu, Tianyu Liu, Zhifang Sui

Aligning Large Language Models via Fine-grained Supervision (2024.acl-short)

Challenge:	Existing evaluation frameworks that use large language models as referees are insufficient for accurately assessing their alignment with human intent.
Approach:	They propose a calibration framework to address positional bias in large language models as evaluators by manually annotating the “win/tie/lose” outcomes of responses from ChatGPT and Vicuna-13B in the Vicun A Benchmark’s question prompt.
Outcome:	The proposed framework alleviates evaluation bias, resulting in closer alignment with human judgments.

Copied to clipboard

Dehong Xu, Liang Qiu, Minseok Kim, Faisal Ladhak, Jaeyoung Do

RTQA : Recursive Thinking for Complex Temporal Knowledge Graph Question Answering with Large Language Models (2025.emnlp-main)

Challenge:	Pre-trained large-scale language models often generate biased or toxic text, misaligning with human intentions.
Approach:	They propose to use human feedback to improve LLM alignment by fine-grained token supervision . they ask annotators to edit less preferred responses to make them more favorable .
Outcome:	The proposed method improves LLM alignment by up to 5.1% in terms of win rate compared with the traditional model.

Copied to clipboard

Zhaoyan Gong, Juan Li, Zhiqiang Liu, Lei Liang, Huajun Chen, Wen Zhang

Enhancing Medical Dialogue Generation through Knowledge Refinement and Dynamic Prompt Adjustment (2025.findings-acl)

Challenge:	Current temporal knowledge graph question answering methods focus on implicit temporal constraints and lack the capability to handle complex temporal queries.
Approach:	They propose a temporal knowledge graph question answering framework that recursively decomposes questions into sub-problems and employs multi-path answer aggregation to improve fault tolerance.
Outcome:	The proposed framework outperforms existing methods on multiTQ and TimelineKGQA benchmarks.

Copied to clipboard

Hongda Sun, Jiaren Peng, Wenzhong Yang, Liang He, Bo Du, Rui Yan

Consecutive Batch Model Editing with HooK Layers (2024.emnlp-main)

Challenge:	Medical dialogue systems (MDS) struggle to identify relevant medical knowledge and generate accurate responses.
Approach:	They propose a medical dialogue system that integrates knowledge refining and dynamic prompt adjustment to improve medical knowledge and accuracy.
Outcome:	The proposed system outperforms state-of-the-art systems in both generation quality and medical entity accuracy.

Copied to clipboard

Shuaiyi Li, Yang Deng, Deng Cai, Hongyuan Lu, Liang Chen, Wai Lam

Challenge:	Existing models that retrain are time- and resource-consuming, but they lack the memory to support sequential and batch editing.
Approach:	They propose a model editing method that supports sequential and batch editing . they use a small amount of memory to store several hook layers that remain unchanged over time .
Outcome:	The proposed method is memory-friendly and can store hook layers that remain unchanged over time.

Boosting Large Language Models with Continual Learning for Aspect-based Sentiment Analysis (2024.findings-emnlp)

Copied to clipboard

Xuanwen Ding, Jie Zhou, Liang Dou, Qin Chen, Yuanbin Wu, Arlene Chen, Liang He

Synergizing Large Language Models and Pre-Trained Smaller Models for Conversational Intent Discovery (2024.findings-acl)

Challenge:	Existing studies focus on improving the performance of domain-specific models based on the target dataset.
Approach:	They propose a Large Language Model-based Continual Learning (LLM-CL) model for ABSA that learns the target domain’s ability while maintaining the history domains’ abilities.
Outcome:	The proposed model obtains new state-of-the-art over 19 datasets.

Copied to clipboard

Jinggui Liang, Lizi Liao, Hao Fei, Jing Jiang

Document-Level Event Argument Extraction With a Chain Reasoning Paradigm (2023.acl-long)

Challenge:	Current attempts at CID rely on pretrained Small Language Models (SLMs) this lacks the ability to label new intents and is a challenge for small language models.
Approach:	They propose to combine Large Language Models (LLMs) with pre-trained SLMs for CID to enhance the semantic comprehension of LLMs.
Outcome:	The proposed approach improves the semantic comprehension of LLMs and the operational agility of SLMs by realigning existing descriptors within the SLM’s feature space to correct cluster distortion and promote robust learning of representations.

Copied to clipboard

Jian Liu, Chen Liang, Jinan Xu, Haoyan Liu, Zhe Zhao

Revisiting Knowledge Distillation for Autoregressive Language Models (2024.acl-long)

Challenge:	Document-level event argument extraction aims to identify event arguments beyond sentence level, where a significant challenge is to model long-range dependencies.
Approach:	They propose a chain reasoning paradigm which captures long-range interdependence due to the chains’ compositional nature and generates decomposable first-order logic rules for reasoning.
Outcome:	The proposed method outperforms previous methods on two benchmarks and is robust enough to defend against adversarial attacks.

Copied to clipboard

Qihuang Zhong, Liang Ding, Li Shen, Juhua Liu, Bo Du, Dacheng Tao

ArMATH: a Dataset for Solving Arabic Math Word Problems (2022.lrec-1)

Challenge:	Autoregressive language models (LMs) are expensive and memory intensive, preventing the development of industrial applications.
Approach:	They propose an adaptive teaching approach to improve the KD of autoregressive language models by distilling knowledge into a small student model.
Outcome:	The proposed method can achieve consistent and significant performance gains across all model types and sizes.

Copied to clipboard

Reem Alghamdi, Zhenwen Liang, Xiangliang Zhang

I-MCTS: Enhancing Agentic AutoML via Introspective Monte Carlo Tree Search (2026.findings-eacl)

Challenge:	This paper is the first to use deep learning methods to solve Arabic MWPs . it is also the first study to use transfer learning to solve MWp across different languages .
Approach:	They contribute to the first large-scale dataset for Arabic Math Word Problems . they use deep learning methods to solve Arabic MWPs and a transfer learning model to promote performance .
Outcome:	The proposed model improves Arabic MWP solvers by 3% over the existing model.

Copied to clipboard

Zujie Liang, Feng Wei, Wujiang Xu, Yuxi Qian, Lin Chen, Xinhui Wu

Monolingual and Multilingual Reduction of Gender Bias in Contextualized Representations (2020.coling-main)

Challenge:	Existing LLM-based agents struggle with low diversity and suboptimal code generation.
Approach:	They propose an approach that iteratively expands tree nodes through an introspective process that meticulously analyzes solutions and results from parent and sibling nodes.
Outcome:	The proposed approach shows a 4% improvement in performance compared to the strong open-source AutoML agents.

Copied to clipboard

Sheng Liang, Philipp Dufter, Hinrich Schütze

Backpack Language Models (2023.acl-long)

Challenge:	Prior work identifies a linear gender subspace and removes gender information by eliminating the subspace.
Approach:	They propose to use DensRay to obtain interpretable dense subspaces by applying it to attention heads and layers of BERT.
Outcome:	The proposed method performs on-par with prior approaches, but is more robust and preserves language model performance better.

Copied to clipboard

John Hewitt, John Thickstun, Christopher Manning, Percy Liang

POLYCHARTQA: Benchmarking Large Vision-Language Models with Multilingual Chart Question Answering (2026.acl-long)

Challenge:	We train a 170Mparameter Backpack language model on OpenWebText, matching the loss of a 6Bparameter Transformer.
Approach:	They propose a neural architecture that learns multiple non-contextual sense vectors for each word in a vocabulary and represents a word as a context-dependent, non-negative linear combination of sense vector.
Outcome:	The proposed model outperforms a GPT-2's word embeddings on lexical similarity evaluations and can be used to perform controllable text generation and debiasing.

Copied to clipboard

Yichen Xu, Liangyu Chen, Liang Zhang, Zihao Yue, Jianzhe Ma, Wenxuan Wang, Qin Jin

Watermark under Fire: A Robustness Evaluation of LLM Watermarking (2025.findings-emnlp)

Challenge:	Existing chart understanding benchmarks are overwhelmingly English-centric, limiting their accessibility and relevance to global audiences.
Approach:	They propose a multilingual chart question answering benchmark that enables efficient multilingual generation via data translation and code reuse.
Outcome:	The proposed benchmark systematically evaluates multilingual chart understanding on state-of-the-art LVLMs and shows a significant performance gap between English and other languages.

Copied to clipboard

Jiacheng Liang, Zian Wang, Spencer Hong, Shouling Ji, Ting Wang

Multi-modal Stance Detection: New Datasets and Model (2024.findings-acl)

Challenge:	Various watermarking methods have been proposed to identify LLM-generated texts . lack of unified evaluation platforms has left many critical questions unanswered .
Approach:	They systematize existing LLM watermarkers and watermark removal attacks and develop a unified platform that integrates them.
Outcome:	The proposed systematizes existing LLM watermarkers and watermark removal attacks, mapping out their design spaces.

Copied to clipboard

Bin Liang, Ang Li, Jingqian Zhao, Lin Gui, Min Yang, Yue Yu, Kam-Fai Wong, Ruifeng Xu

ParroT: Translating during Chat using Large Language Models tuned with Human Translation and Feedback (2023.findings-emnlp)

Challenge:	Existing methods for stance detection for pure texts have limited results to multi-modal content.
Approach:	They propose a multi-modal stance detection framework that leverages target information to learn multi-modal stance features from textual and visual modalities.
Outcome:	The proposed framework achieves state-of-the-art in multi-modal stance detection on five datasets based on Twitter .

Copied to clipboard

Wenxiang Jiao, Jen-tse Huang, Wenxuan Wang, Zhiwei He, Tian Liang, Xing Wang, Shuming Shi, Zhaopeng Tu

CLHA: A Simple Yet Effective Contrastive Learning Framework for Human Alignment (2024.lrec-main)

Challenge:	Large language models (LLMs) like ChatGPT are only accessible through restricted APIs, which creates barriers to new research and advancements in the field.
Approach:	They propose a framework to enhance and regulate the translation abilities during chat . they reformulate translation data into the instruction-following style and introduce a "Hint" field .
Outcome:	The proposed framework enhances and regulates the translation abilities during chat . it reformulates translation data into the instruction-following style and introduces a "Hint" field .

Copied to clipboard

Feiteng Fang, Liang Zhu, Xi Feng, Jinchang Hou, Qixuan Zhao, Chengming Li, Xiping Hu, Ruifeng Xu, Min Yang

MolRAG: Unlocking the Power of Large Language Models for Molecular Property Prediction (2025.acl-long)

Challenge:	Large language models (LLMs) have attracted considerable attention from academic and industrial communities due to their outstanding performance in various natural language processing tasks.
Approach:	They propose a Contrastive Learning Framework for Human Alignment to evaluate the noise within the data and dynamically adjust the training process.
Outcome:	The proposed framework surpasses other algorithms in terms of reward model scores, automatic evaluations, and human assessments on the widely used dataset "Helpful and Harmless"

Copied to clipboard

Ziting Xian, Jiawei Gu, Lingbo Li, Shangsong Liang

Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models (2024.findings-acl)

Challenge:	Recent LLMs exhibit limited effectiveness on molecular property prediction task due to semantic gap between representations and natural language and lack of domain-specific knowledge.
Approach:	They propose a framework that integrates Chain-of-Thought reasoning for molecular property prediction.
Outcome:	The proposed framework outperforms pre-trained LLMs on four datasets and matches supervised methods.

Copied to clipboard

Junfei Wu, Qiang Liu, Ding Wang, Jinghao Zhang, Shu Wu, Liang Wang, Tieniu Tan

Reducing Spurious Correlations in Aspect-based Sentiment Analysis with Explanation from Large Language Models (2023.findings-emnlp)

Challenge:	Object hallucination has been an Achilles’ heel which hinders the broader applications of large vision-language models (LVLMs).
Approach:	They propose a logical closed loop-based framework for Object Hallucination Detection and Mitigation that uses logical consistency probing to raise questions with logical correlations to determine hallucinations.
Outcome:	The proposed method can be applied to all existing LVLMs and is effective and general.

Copied to clipboard

Qianlong Wang, Keyang Ding, Bin Liang, Min Yang, Ruifeng Xu

Reason from Fallacy: Enhancing Large Language Models’ Logical Reasoning through Logical Fallacy Understanding (2024.findings-naacl)

Challenge:	Aspect-based sentiment analysis models are susceptible to learning spurious correlations between words . a recent study shows that feature engineering is time-consuming and costly .
Approach:	They propose to use a template to prompt LLMs to generate an appropriate explanation for the sentiment polarity of each aspect to reduce spurious correlations.
Outcome:	The proposed methods improve ABSA models and their generalization ability.

Copied to clipboard

Yanda Li, Dixuan Wang, Jiaqing Liang, Guochao Jiang, Qianyu He, Yanghua Xiao, Deqing Yang

Aegis:An Advanced LLM-Based Multi-Agent for Intelligent Functional Safety Engineering (2024.emnlp-industry)

Challenge:	Large Language Models (LLMs) have demonstrated good performance in many reasoning tasks, but struggle with some more complex reasoning tasks including logical reasoning.
Approach:	They propose five concrete tasks from three cognitive dimensions of WHAT, WHY, and HOW to evaluate LLMs’ capability of logical fallacy understanding.
Outcome:	The proposed dataset can be used to evaluate LLMs’ LFU capability and to fine-tune LLM models to obtain significantly enhanced performance on logical reasoning.

Copied to clipboard

Lu Shi, Bin Qi, Jiarui Luo, Yang Zhang, Zhanzhao Liang, Zhaowei Gao, Wenke Deng, Lin Sun

PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit (2022.naacl-demo)

Challenge:	Aegis is an advanced LLM-based multi-agent for intelligent functional safety engineering that can perform all phases of a vehicle's lifecycle, including design, development, production, operation, and decommissioning.
Approach:	They introduce Aegis: An Advanced LLM-Based Multi-Agent for Intelligent Functional Safety Engineering.
Outcome:	The proposed solution can perform Hazard Analysis and Risk Assessment (HARA), document Functional Safety Requirements (FSR), and plan test cases for Automatic Emergency Braking (AEB) systems.

Copied to clipboard

Hui Zhang, Tian Yuan, Junkun Chen, Xintong Li, Renjie Zheng, Yuxin Huang, Xiaojie Chen, Enlei Gong, Zeyu Chen, Xiaoguang Hu, Dianhai Yu, Yanjun Ma, Liang Huang

SDBench: A Survey-based Domain-specific LLM Benchmarking and Optimization Framework (2025.acl-long)

Challenge:	PaddleSpeech is an open-source speech toolkit that supports speech-to-text and text-to speech tasks.
Approach:	They describe the design philosophy and core architecture of PaddleSpeech to support several essential speech-to-text and text-to speech tasks.
Outcome:	The proposed framework achieves competitive or state-of-the-art performance on various speech datasets and implements the most popular methods.

Copied to clipboard

Cheng Guo, Hu Kai, Shuxian Liang, Yiyang Jiang, Yi Gao, Xian-Sheng Hua, Wei Dong

Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form Generation (2025.emnlp-main)

Challenge:	acquiring domain-specific knowledge often requires professional expert manpower.
Approach:	They propose a generic framework for generating evaluation datasets for domain-specific LLMs.
Outcome:	The proposed framework reduces the reliance on expert manpower while ensuring that the collected data is uniformly distributed.

Copied to clipboard

Ziyin Zhang, Jiahao Xu, Tian Liang, Xingyu Chen, Zhiwei He, Rui Wang, Zhaopeng Tu

VET: Verifiable Execution Tracing for Reliable Text-to-SQL Generation (2026.findings-acl)

Challenge:	Conventional speculative decoding methods use a predefined length policy for proposing drafts, but the reality deviates from this assumption.
Approach:	They propose a self-verification length policy that adaptively determines the lengths of draft sequences by referring to the draft entropy.
Outcome:	The proposed method achieves 17% speedup on MT-Bench and 22% speedup in long-form reasoning.

Copied to clipboard

Dongyu Wang, Jingyu Li, Lan Zhang, null Ganggang.yu, Liang Huang

Can Language Models Replace Programmers for Coding? REPOCOD Says ‘Not Yet’ (2025.acl-long)

Challenge:	Existing methods for text-to-SQL generation are prone to hallucinations and grounding . authors present a novel reasoning paradigm that transforms text- to-Sql from unverifiable textual rationales into step-wise executable semantics.
Approach:	They propose a reasoning paradigm that transforms text-to-SQL from unverifiable textual rationales into step-wise executable semantics.
Outcome:	The proposed reasoning paradigm transforms text-to-SQL from unverifiable textual rationales into step-wise executable semantics.

Copied to clipboard

Shanchao Liang, Nan Jiang, Yiran Hu, Lin Tan

Improving Neural Machine Translation by Bidirectional Training (2021.emnlp-main)

Challenge:	Existing benchmarks for code generation use short completions, synthetic examples, or focus on limited scale repositories, failing to represent real-world coding tasks.
Approach:	They propose a Python code-generation benchmark that contains 980 whole-function generation tasks with realistic dependencies from 11 popular projects.
Outcome:	The proposed benchmarks are short completions, synthetic examples, or focus on limited scale repositories, failing to represent real-world coding tasks.

Copied to clipboard

Liang Ding, Di Wu, Dacheng Tao

SAC: Neural Speech Codec with Semantic-Acoustic Dual-Stream Quantization (2026.acl-long)

Challenge:	Experimental results show that bidirectional training pushes the SOTA neural machine translation performance significantly higher.
Approach:	They propose a bidirectional training strategy that updates model parameters at the early stage and tunes it normally.
Outcome:	The proposed approach pushes the SOTA neural machine translation performance significantly higher on 15 translation tasks on 8 language pairs.

Copied to clipboard

Wenxi Chen, Ruiqi Yan, Yushen Chen, Zhikang Niu, Ziyang Ma, Xiquan Li, Yuzhe Liang, null Wenhanlin, Shunshun Yin, Ming Tao, Xinsheng Wang, Xie Chen

Are Large Language Models Reliable Reviewers? A Benchmark for Error Detection in Financial Documents (2026.findings-acl)

Challenge:	Existing speech codecs struggle to balance high-quality reconstruction with semantically rich representations, limiting their effectiveness in both generative and understanding tasks.
Approach:	They propose a neural speech codec with semantic-acoustic dual-stream quantization that disentangles semantic and acousian modeling into two dedicated streams.
Outcome:	The proposed codec outperforms state-of-the-art speech tokenizers in auto-propagating text-to-speech models.

Copied to clipboard

Ying He, Zhouhong Gu, Zhecheng Hu, Yubo Zhou, Hao Shen, Jiaqing Liang, Zhaoqian Dai, Ma Shuguang, Fei Yu, Yanghua Xiao, Zhixu Li

FlowRAG: Synergizing Explicit Reasoning via Frequency-Aware Multi-Granularity Graph Flow (2026.findings-acl)

Challenge:	Existing LLMs struggle to identify errors in financial documents, a study shows . 18% of financial practitioners make errors daily, one-third make errors several times weekly, and 59% make errors multiple times monthly.
Approach:	They introduce FinED-Bench, a publicly available Benchmark for financial error detection . it covers nine real-world financial scenarios and includes over 900 documents in 2025 . supervised fine-tuning can significantly improve the performance of weaker LLMs, they show .
Outcome:	The proposed benchmark covers nine real-world financial scenarios and includes over 900 documents reported in 2025 that are unseen by existing language models.

Copied to clipboard

Bihao Zhan, Zongsheng Cao, Jie Zhou, Bo Zhang, Liang He

Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration (2022.acl-long)

Challenge:	Existing methods for Graph-based retrieval-augmented generation rely on implicit semantic relevance propagation.
Approach:	They propose a semantic-aware retrieval framework that improves both semantic recall and explicit reasoning.
Outcome:	Extensive experiments show that FlowRAG improves both semantic recall and explicit reasoning.

Copied to clipboard

Xiwen Liang, Fengda Zhu, Li Lingling, Hang Xu, Xiaodan Liang

MathPrompter: Mathematical Reasoning using Large Language Models (2023.acl-industry)

Challenge:	Existing methods of fine-tuning vision-language navigation models require extra human-labeled data and lack self-exploration capabilities in environments.
Approach:	They propose a method that can self-explore environments without human labeling . they use a large-scale cross-modal pretrained model to build an in-domain dataset .
Outcome:	The proposed model can self-explore environments without human labeling without human supervision and generates structured instructions without human intervention.

Copied to clipboard

Shima Imani, Liang Du, Harsh Shrivastava

Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories (2026.acl-long)

Challenge:	Recent advances in natural language processing (NLP) can be attributed to massive scaling of Large Language Models (LLMs).
Approach:	They propose a technique that improves performance of Large Language Models (LLMs) on arithmetic problems along with increased reliance in the predictions.
Outcome:	The proposed technique improves performance on arithmetic problems and increases confidence in the output results.

Copied to clipboard

Peiyang Liu, Zhirui Chen, Xi Wang, Di Liang, Youru Li, Zhi Cai, Wei Ye

MultiCMET: A Novel Chinese Benchmark for Understanding Multimodal Metaphor (2023.findings-emnlp)

Challenge:	MCTS methods retain only the single highest-reward trajectory, discarding comparative signals present in the many explored paths.
Approach:	They propose a framework that transforms supervision extraction into a synthesis procedure.
Outcome:	The proposed framework matches or exceeds baselines on 60K CRPS-synthesized examples on out-of-domain benchmarks.

Copied to clipboard

Dongyu Zhang, Jingwei Yu, Senyuan Jin, Liang Yang, Hongfei Lin

GMH: A General Multi-hop Reasoning Model for KG Completion (2021.emnlp-main)

Challenge:	Existing research on multimodal metaphors does not address categorizing the source and target domains in metaphors beyond the English language.
Approach:	They propose a Cascading Domain Knowledge Integration benchmark to detect metaphors by introducing domain-specific lexical features.
Outcome:	The proposed dataset includes 13,820 text-image pairs of advertisements with manual annotations of the occurrence of metaphors, domain categories, and sentiments metaphors convey.

Copied to clipboard

Yao Zhang, Hongru Liang, Adam Jatowt, Wenqiang Lei, Xin Wei, Ning Jiang, Zhenglu Yang

ACR: Adaptive Context Refactoring via Context Refactoring Operators for Multi-Turn Dialogue (2026.findings-acl)

Challenge:	Knowledge graphs are incomplete with many facts missing, causing performance bottlenecks in many applications.
Approach:	They propose a general multi-hop reasoning task that can be formulated as a search process and can be extended to long-distance reasoning scenarios.
Outcome:	The proposed model improves on baselines in short and long distance reasoning scenarios.

Copied to clipboard

Jiawei Shen, Jia Zhu, Hanghui Guo, Weijie Shi, Yue Cui, Qingyu Niu, Guoqing Ma, Jingjiang Liu, Yidan Liang, Yilin Wang, Shimin Di, Jiajie Xu

SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State Machine (2025.findings-naacl)

Challenge:	Existing approaches to multi-turn dialogues lack contextual consistency and dependencies, and models struggle to maintain factual faithfulness as interaction turns increase.
Approach:	They propose an adaptive context refactoring framework that monitors and reshapes the interaction history to mitigate contextual inertia and state drift.
Outcome:	The proposed model outperforms baselines while reducing token consumption.

Copied to clipboard

Xiaochen Wang, Junqing He, Liang Chen, Gholamreza Haffari, Yiru Wang, Zhe Yang, Xiangdi Meng, Kunhao Pan, Zhifang Sui

Unicoder: A Universal Language Encoder by Pre-training with Multiple Cross-lingual Tasks (D19-1)

Challenge:	Multi-hop Question Answering (MHQA) is a challenging task that requires models to answer multiple questions with multiple passages.
Approach:	They propose a self-guided prompting finite state machine to improve multi-hop reasoning abilities by iterating over multiple questions and correcting itself to improve accuracy.
Outcome:	The proposed approach outperforms baselines on Musique and other datasets.

Copied to clipboard

Haoyang Huang, Yaobo Liang, Nan Duan, Ming Gong, Linjun Shou, Daxin Jiang, Ming Zhou

Cool-Fusion: Fuse Large Language Models without Training (2025.acl-long)

Challenge:	Existing models that can handle cross-lingual tasks with limited or no training data are insensitive to different languages.
Approach:	They propose to use Unicoder to train models in one language and apply it to other languages.
Outcome:	Experiments show that Unicoder learns the mappings among different languages from more perspectives.

Copied to clipboard

Cong Liu, Xiaojun Quan, Yan Pan, Weigang Wu, Xu Chen, Liang Lin

UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generation (2024.acl-long)

Challenge:	Cool-Fusion is a simple yet effective approach to combine two or more heterogeneous large language models .
Approach:	They propose a method that fuses the knowledge of two or more heterogeneous large language models to leverage complementary strengths.
Outcome:	The proposed method increases accuracy from three strong source LLMs on GSM8K by 17.4%.

Copied to clipboard

Xun Liang, Shichao Song, Simin Niu, Zhiyu Li, Feiyu Xiong, Bo Tang, Yezhaohui Wang, Dawei He, Cheng Peng, Zhonghao Wang, Haiying Deng

SEGMENT+: Long Text Processing with Short-Context Language Models (2024.emnlp-main)

Challenge:	Large language models (LLMs) produce hallucinated text, compromising their practical utility in professional contexts.
Approach:	They have developed an unconstrained hallucination generation evaluation benchmark that contains hallucines generated by large language models with minimal restrictions.
Outcome:	The proposed benchmarks are based on a Chinese-language dataset that is lacking in the field.

Copied to clipboard

Wei Shi, Shuang Li, Kerun Yu, Jinglei Chen, Zujie Liang, Xinhui Wu, Yuxi Qian, Feng Wei, Bo Zheng, Jiaqing Liang, Jiangjie Chen, Yanghua Xiao

Order Doesn’t Matter, But Reasoning Does: Training LLMs with Order-Centric Augmentation (2025.emnlp-main)

Challenge:	Existing frameworks that increase context window do not guarantee robust performance across long input tasks.
Approach:	They propose a framework that enables language models to handle extended inputs within limited context windows efficiently.
Outcome:	The framework improves performance on long-document question-answering and Needle-in-a-Haystack tasks.

Copied to clipboard

Qianxi He, Qianyu He, Jiaqing Liang, Weikang Zhou, Zeye Sun, Fei Yu, Yanghua Xiao

In-context Contrastive Learning for Event Causality Identification (2024.emnlp-main)

Challenge:	Logical reasoning is essential for large language models (LLMs) to ensure accurate and coherent inferences.
Approach:	They propose an order-centric data augmentation framework based on commutativity in logical reasoning that randomly shuffles independent premises to introduce condition order augmentation.
Outcome:	The proposed framework improves LLMs’ reasoning performance and adaptability to diverse logical structures.

Copied to clipboard

Liang Chao, Wei Xiang, Bang Wang

Modular and Parameter-Efficient Multimodal Fusion with Prompting (2022.findings-acl)

Challenge:	Recent prompt learning-based approaches have shown promising improvements on the ECI task . however, they are subject to the delicate design of multiple prompts and positive correlations between the main task and derivate tasks.
Approach:	They propose an event causality identification model that uses contrastive learning to enhance both positive and negative demonstrations.
Outcome:	The proposed model improves on the event-related causality identification task . it uses contrastive learning to enhance both positive and negative demonstrations .

Copied to clipboard

Sheng Liang, Mengjie Zhao, Hinrich Schuetze

UnCo: Uncertainty-Driven Collaborative Framework of Large and Small Models for Grounded Multimodal NER (2025.emnlp-main)

Challenge:	Recent research has made impressive progress in large-scale multimodal pre-training.
Approach:	They propose to use prompt vectors to align multimodal modalities by pretraining text inputs with prompts or embedding vectors.
Outcome:	The proposed method achieves comparable performance to several other multimodal fusion methods in low-resource settings.

Copied to clipboard

Jielong Tang, Yang Yang, Jianxing Yu, Zhen-Xing Wang, Haoyuan Liang, Liang Yao, Jian Yin

Immediate Inference: The Missing Foundation in Large Language Model Logical Reasoning (2026.acl-long)

Challenge:	Existing methods to identify unseen multimodal entities struggle with limited knowledge and generalization.
Approach:	They propose a framework that leverages the strengths of small fine-tuned models and MLLMs to generate unambiguous predictions.
Outcome:	Extensive experiments show that the proposed framework retains the in-domain knowledge of small models while utilizing the capabilities of MLLMs to handle unseen entities.

Copied to clipboard

Sihang Jiang, Zhiyu Lu, Keyi Wang, Jiaqing Liang, Yanghua Xiao, Xiaojun Meng, Jiansheng Wei

Media Source Matters More Than Content: Unveiling Political Bias in LLM-Generated Citations (2025.emnlp-main)

Challenge:	Recent work on LLMs has focused on fine-grained skill decomposition and consistency probing at the propositional level.
Approach:	They propose a benchmark evaluating immediate inference that evaluates elemental operations over categorical propositions and proposes a model that uses immediate inferential reasoning.
Outcome:	The proposed benchmark demonstrates that models lack robust operator grounding, oscillating between structural reasoning and surface pattern matching, inconsistent handling of quantifiers and negation.

Copied to clipboard

Sunhao Dai, Zhanshuo Cao, Wenjie Wang, Liang Pang, Jun Xu, See-Kiong Ng, Tat-Seng Chua

CLOMO: Counterfactual Logical Modification with Large Language Models (2024.acl-long)

Challenge:	generative search engines rely on in-line citations as the key gateway to original webpages . a recent study shows that LLMs tend to cite left-leaning sources at higher rates compared to traditional retrieval systems .
Approach:	They construct a dataset of news articles labeled with left- or right-leaning stances . they find that LLMs tend to cite left-leansing sources at higher rates than traditional retrieval systems .
Outcome:	The proposed dataset shows that LLMs tend to cite left-leaning sources at higher rates than traditional retrieval systems.

Copied to clipboard

Yinya Huang, Ruixin Hong, Hongming Zhang, Wei Shao, Zhicheng Yang, Dong Yu, Changshui Zhang, Xiaodan Liang, Linqi Song

SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues (2021.acl-long)

Challenge:	Existing studies on evaluating model reasoning are limited in both form and content.
Approach:	They propose a task to cultivate counterfactual thought processes within large language models and an evaluation metric to evaluate their natural language output instead of modeling the task as a multiple-choice problem.
Outcome:	The proposed evaluation metric aligns well with human preference.

Copied to clipboard

Liang Qiu, Yuan Liang, Yizhou Zhao, Pan Lu, Baolin Peng, Zhou Yu, Ying Nian Wu, Song-Chun Zhu

Towards Making the Most of Dialogue Characteristics for Neural Chat Translation (2021.emnlp-main)

Challenge:	Existing studies focus on identifying entities' relations from the semantics of dialogues-they utilize either the attention mechanism or a refined token graph to locate informative words.
Approach:	They propose a sequential structure prediction task to incrementally parse SocAoG for dynamic inference upon any incoming utterance.
Outcome:	Empirical results show that the proposed model infers social relations more accurately than the state-of-the-art methods.

Copied to clipboard

Yunlong Liang, Chulun Zhou, Fandong Meng, Jinan Xu, Yufeng Chen, Jinsong Su, Jie Zhou

MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective (2022.acl-long)

Challenge:	Neural Chat Translation (NCT) models that use dialogue characteristics of chat are often incoherent and speakerirrelevant.
Approach:	They propose to introduce the modeling of dialogue characteristics into the NCT model by capturing the inherent dialogue characteristics.
Outcome:	The proposed model can translate conversational text between speakers of different languages.

Copied to clipboard

Xiao Wang, Shihan Dou, Limao Xiong, Yicheng Zou, Qi Zhang, Tao Gui, Liang Qiao, Zhanzhan Cheng, Xuanjing Huang

MegaAgent: A Large-Scale Autonomous LLM-based Multi-Agent System Without Predefined SOPs (2025.findings-acl)

Challenge:	Named Entity Recognition models are feature-engineering and machine learning based.
Approach:	They propose a new NER learning framework that uses entity mentions to improve model performance.
Outcome:	The proposed model achieves better performance on OOV entities on various settings and datasets.

Copied to clipboard

Qian Wang, Tianyu Wang, Zhenheng Tang, Qinbin Li, Nuo Chen, Jingsheng Liang, Bingsheng He

Task-Oriented Dialogue as Dataflow Synthesis (2020.tacl-1)

Challenge:	Existing multi-agent systems lack agent coordination and rely on predefined procedures . existing systems lack adaptive task coordination when task is big and complex .
Approach:	They propose a large-scale autonomous LLM-based multi-agent system that generates agents based on task complexity and enables dynamic task decomposition, parallel execution, efficient communication and comprehensive system monitoring.
Outcome:	The proposed system outperforms existing systems in task completion efficiency and scalability.

Copied to clipboard

Jacob Andreas, John Bufe, David Burkett, Charles Chen, Josh Clausman, Jean Crawford, Kate Crim, Jordan DeLoach, Leah Dorner, Jason Eisner, Hao Fang, Alan Guo, David Hall, Kristin Hayes, Kellie Hill, Diana Ho, Wendy Iwaszuk, Smriti Jha, Dan Klein, Jayant Krishnamurthy, Theo Lanman, Percy Liang, Christopher H. Lin, Ilya Lintsbakh, Andy McGovern, Aleksandr Nisnevich, Adam Pauls, Dmitrij Petters, Brent Read, Dan Roth, Subhro Roy, Jesse Rusak, Beth Short, Div Slomin, Ben Snyder, Stephon Striplin, Yu Su, Zachary Tellman, Sam Thomson, Andrei Vorobev, Izabela Witoszko, Jason Wolfe, Abby Wray, Yuchen Zhang, Alexander Zotov

Task Oriented In-Domain Data Augmentation (2024.emnlp-main)

Challenge:	Existing approaches to task-oriented dialogue represent dialogue state as a dataflow graph . microsoft's SMCalFlow dataset features complex dialogues about events, weather, places, and people .
Approach:	They propose a dataflow graph-based dialogue agent that maps each user utterance to a program that extends this graph.
Outcome:	The proposed framework improves representability and predictability in natural dialogues . it uses dataflow graphs and metacomputation to map user intents to a program .

Copied to clipboard

Xiao Liang, Xinyu Hu, Simiao Zuo, Yeyun Gong, Qiang Lou, Yi Liu, Shao-Lun Huang, Jian Jiao

Neutralizing Bias in LLM Reasoning using Entailment Graphs (2025.findings-acl)

Challenge:	Existing methods for large language models suffer from two major issues: in-domain data are scarce compared with general domain-agnostic data.
Approach:	They propose a task-oriented in-domain data augmentation framework that uses in- domain data selection and task-orientated synthetic passage generation to adapt LLMs to two domains: advertisement and math.
Outcome:	The proposed framework improves LLM performance by 8% in the advertisement domain and 7.5% in the math domain.

Copied to clipboard

Liang Cheng, Tianyi Li, Zhaowei Wang, Tianyang Liu, Mark Steedman

Towards Understanding and Improving Knowledge Distillation for Neural Machine Translation (2023.acl-long)

Challenge:	Natural Language Inference (NLI) is a foundational understanding task in language understanding.
Approach:	They propose a framework to construct counterfactual reasoning data and fine-tune LLMs to reduce attestation bias.
Outcome:	The proposed framework reduces hallucinations from attestation bias on original and bias-neutralized datasets while keeping hypotheses unchanged.

Copied to clipboard

Songming Zhang, Yunlong Liang, Shuaibo Wang, Yufeng Chen, Wenjuan Han, Jian Liu, Jinan Xu

S+PAGE: A Speaker and Position-Aware Graph Neural Network Model for Emotion Recognition in Conversation (2022.aacl-main)

Challenge:	Existing knowledge distillation techniques for neural machine translation lack special treatment on the top-1 information, which is limiting the potential of KD.
Approach:	They propose a method to distill knowledge from top-1 predictions of teachers and a technique to infuse more additional knowledge by distilling on the data without ground-truth targets.
Outcome:	The proposed method outperforms the vanilla word-level KD and outperfies the existing methods on three different students with different capacity gaps.

Copied to clipboard

Chen Liang, Jing Xu, Yangkun Lin, Chong Yang, Yongliang Wang

Improved Neural Protoform Reconstruction via Reflex Prediction (2024.lrec-main)

Challenge:	Emotion recognition in conversation (ERC) is a task arousing increasing interest in many fields.
Approach:	They propose a novel GNN-based ERC model that captures speaker and position information.
Outcome:	The proposed model captures speaker and position-aware conversation structure information.

Copied to clipboard

Liang Lu, Jingzhi Wang, David R. Mortensen

Challenge:	comparative method allows linguists to infer protoforms from their reflexes based on sound change . authors argue that this approach ignores one of the most important aspects of the comparative approach .
Approach:	They propose a comparative method that allows linguists to infer protoforms from their reflexes . they propose to use a system where candidate protoform from a reconstruction model are reranked by a reflex prediction model.
Outcome:	The comparative method surpasses state-of-the-art methods on Chinese and Romance datasets.

NLPositionality: Characterizing Design Biases of Datasets and Models (2023.acl-long)

Copied to clipboard

Sebastin Santy, Jenny Liang, Ronan Le Bras, Katharina Reinecke, Maarten Sap

SHIFT: Selected Helpful Informative Frame for Video-guided Machine Translation (2025.emnlp-main)

Challenge:	Design biases in NLP systems often stem from creator’s positionality, i.e., views and lived experiences shaped by identity and background.
Approach:	They propose a framework for characterizing design biases and quantifying the positionality of NLP datasets and models.
Outcome:	The proposed framework characterizes design biases and quantifies alignment with dataset labels and model predictions.

Copied to clipboard

Boyu Guan, Chuang Han, Yining Zhang, Yupu Liang, Zhiyang Zhang, Yang Zhao, Chengqing Zong

Self-Powered LLM Modality Expansion for Large Speech-Text Models (2024.emnlp-main)

Challenge:	Video-guided machine translation (VMT) aims to improve translation quality by integrating contextual information from paired short video clips.
Approach:	They propose a plug-and-play framework for video-guided machine translation with multimodal large language models.
Outcome:	The proposed framework improves performance of MLLMs while reducing computational cost.

Copied to clipboard

Tengfei Yu, Xuebo Liu, Zhiyi Hou, Liang Ding, Dacheng Tao, Min Zhang

RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation (2024.emnlp-demo)

Challenge:	Large language models exhibit remarkable performance across diverse tasks . however, these methods require significant resource demands and tend to overfit specific tasks.
Approach:	They propose a self-powered LSM that leverages augmented automatic speech recognition data generated by the model itself for more effective instruction tuning.
Outcome:	The proposed model mitigates speech anchor bias and improves the fusion of speech and text modalities in large language models.

Copied to clipboard

Qinyu Luo, Yining Ye, Shihao Liang, Zhong Zhang, Yujia Qin, Yaxi Lu, Yesai Wu, Xin Cong, Yankai Lin, Yingli Zhang, Xiaoyin Che, Zhiyuan Liu, Maosong Sun

AutoMedEval: Harnessing Language Models for Automatic Medical Capability Evaluation (2025.acl-long)

Challenge:	Xia et al., 2018) demonstrate that a large language model can generate and maintain high-quality code documentation.
Approach:	They propose a large language model powered open-source framework for generating, maintaining, and updating code documentation.
Outcome:	The proposed framework generates high-quality documentation for the entire project.

Copied to clipboard

Xiechi Zhang, Zetian Ouyang, Linlin Wang, Gerard De Melo, Zhu Cao, Xiaoling Wang, Ya Zhang, Yanfeng Wang, Liang He

Progressive Multi-Granularity Training for Non-Autoregressive Translation (2021.findings-acl)

Challenge:	Existing evaluation methods based on large language models (LLMs) are expensive and lack expertise due to limitations in human expertise.
Approach:	They propose an open-source automatic evaluation model with 13B parameters specifically engineered to measure the question-answering proficiency of medical LLMs.
Outcome:	The proposed model surpasses baselines in terms of correlation with human judgments.

Copied to clipboard

Liang Ding, Longyue Wang, Xuebo Liu, Derek F. Wong, Dacheng Tao, Zhaopeng Tu

HacRED: A Large-Scale Relation Extraction Dataset Toward Hard Cases in Practical Applications (2021.findings-acl)

Challenge:	Non-autoregressive translation models are weak at learning high-mode knowledge, argues a new study . despite the improved learning difficulty, there are still complicated word orders and structures in the synthetic sentences, making the NAT performance sub-optimal.
Approach:	They propose to train non-autoregressive translation models to learn fine-grained lower-mode knowledge . they break down sentence-level examples into three types and increase granularities .
Outcome:	The proposed method improves phrase translation accuracy and model reordering ability against strong NAT baselines.

Copied to clipboard

Qiao Cheng, Juntao Liu, Xiaoye Qu, Jin Zhao, Jiaqing Liang, Zhefeng Wang, Baoxing Huai, Nicholas Jing Yuan, Yanghua Xiao

Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answering (2025.acl-long)

Challenge:	Relation extraction (RE) is an essential topic in natural language processing and has attracted extensive attention.
Approach:	They propose a case-oriented construction framework to build a hard case relation extraction dataset with 65,225 relational facts annotated from 9,231 documents.
Outcome:	The proposed model achieves a high 96% F1 score on data quality and is far lower than humans.

Copied to clipboard

Linhao Ye, Lang Yu, Zhikai Lei, Qin Chen, Jie Zhou, Liang He

LM-Lexicon: Improving Definition Modeling via Harmonizing Semantic Experts (2026.eacl-long)

Challenge:	Existing retrieval-augmented generation methods are insufficient for multi-hop question answering . however, they tend to generate hallucinations due to semantic mismatching .
Approach:	They propose to optimize question semantic space for dynamic retrieval-augmented multi-hop question answering by optimizing the semantic embeddings.
Outcome:	The proposed method outperforms existing RAG methods in both in- and out-of-domain settings.

Copied to clipboard

Yang Liu, Jiaye Yang, Weikang Li, Jiahui Liang, Yang Li, Lingyong Yan

MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows (2026.acl-long)

Challenge:	LM-LEXICON is a definition modeling approach that integrates data clustering, semantic expert learning, and model merging.
Approach:	They propose a definition modeling approach that integrates data clustering, semantic expert learning, and model merging using a sparse mixture-of-experts architecture.
Outcome:	The proposed model outperforms existing methods on five widely used benchmarks and achieves a BLEU score of 7%.

Copied to clipboard

Xiquan Li, Junxi Liu, Yuzhe Liang, Zhikang Niu, Wenxi Chen, Xie Chen

Interpretable Proof Generation via Iterative Backward Reasoning (2022.naacl-main)

Challenge:	Recent advances in Text-to-Audio Generation (TTA) systems suffer from slow inference speed, authors report . authors demonstrate that MeanAudia achieves state-of-the-art performance in single-step audio generation .
Approach:	They propose a text-to-audio generator capable of rendering realistic sound with only one function evaluation.
Outcome:	The proposed system achieves state-of-the-art performance in single-step audio generation.

Copied to clipboard

Hanhao Qu, Yu Cao, Jun Gao, Liang Ding, Ruifeng Xu

SDiaReward: Modeling and Benchmarking Spoken Dialogue Rewards with Modality and Colloquialness (2026.acl-long)

Challenge:	Existing proof generation tasks require reasoning capabilities, but they usually just request for an answer without the reasoning procedure that would make it interpretable.
Approach:	They propose an iterative backward reasoning model to solve the proof generation tasks on rule-based Question Answering.
Outcome:	The proposed model improves in-domain performance and cross-domain transferability over existing models.

Copied to clipboard

Jingyu Lu, Yuhan Wang, Fan Zhuo, Xize Cheng, Changhao Pan, Xueyi Pu, Yifu Chen, Chenyuhao Wen, Tianle Liang, Zhou Zhao

Speech & Audio in NLP

Challenge:	SDiaReward is an end-to-end spoken dialogue system that integrates paralinguistic nuances and spontaneous nature of human conversation.
Approach:	They propose an end-to-end multi-turn reward model trained on SDiaReward-Dataset . it is a collection of episode-level preference pairs targeting modality and colloquiality gaps .
Outcome:	The proposed model outperforms general-purpose audio LLMs in episode-level evaluation.

Sources of Hallucination by Large Language Models on Inference Tasks (2023.findings-emnlp)

Copied to clipboard

Nick McKenna, Tianyi Li, Liang Cheng, Mohammad Hosseini, Mark Johnson, Mark Steedman

CREATER: CTR-driven Advertising Text Generation with Controlled Pre-Training and Contrastive Fine-Tuning (2022.naacl-industry)

Challenge:	Large Language Models (LLMs) are claimed to be capable of Natural Language Inference (NLI)
Approach:	They propose to use LLMs to probe their behavior using controlled experiments.
Outcome:	The proposed models perform significantly worse on NLI test samples which do not conform to these biases than those which do.

Copied to clipboard

Penghui Wei, Xuanhua Yang, ShaoGuo Liu, Liang Wang, Bo Zheng

ToxiTrace: Gradient-Aligned Training for Explainable Chinese Toxicity Detection (2026.findings-acl)

Challenge:	a paper focuses on automatically generating the text of an ad to capture user interest for achieving higher click-through rate.
Approach:	They propose a CTR-driven advertising text generation approach to generate ad texts based on user reviews.
Outcome:	The proposed approach outperforms existing approaches on industrial datasets and on large-scale unpaired reviews.

Copied to clipboard

Boyang Li, Hongzhe Shou, Yuanyuan Liang, JingBin Zhang, Fang Zhou

MADial-Bench: Towards Real-world Evaluation of Memory-Augmented Dialogue Generation (2025.naacl-long)

Challenge:	Existing toxic content detection methods focus on sentence-level classification but fail to provide readable and contiguous toxic evidence spans.
Approach:	They propose an explainability-oriented method for Chinese toxic content detection methods . they refine saliency cues into fine-grained toxic spans with lightweight LLM guidance .
Outcome:	The proposed method improves classification accuracy and toxic span extraction while preserving efficient encoder-based inference and producing more coherent explanations.

Copied to clipboard

Junqing He, Liang Zhu, Rui Wang, Xi Wang, Gholamreza Haffari, Jiaxing Zhang

DTCA: Decision Tree-based Co-Attention Networks for Explainable Claim Verification (2020.acl-main)

Challenge:	Existing evaluation metrics for memory-augmented dialogue systems lack practical value . current evaluation methods only consider passive memory retrieval while ignoring diverse memory recall with rich triggering factors.
Approach:	They propose to use long-term memory to create human-like dialogues using chatbots.
Outcome:	The proposed benchmark covers memory retrieval and memory recognition tasks with both passive and proactive memory recall data.

Copied to clipboard

Lianwei Wu, Yuan Rao, Yongqiang Zhao, Hao Liang, Ambreen Nazir

Universal Semantic Tagging for English and Mandarin Chinese (2021.naacl-main)

Challenge:	Recent methods to discover evidence for explainable claim verification are nontransparent and unexplained.
Approach:	They propose a Decision Tree-based Co-Attention model to discover evidence for explainable claim verification using neural networks.
Outcome:	The proposed model boosts the F1-score by more than 3.11%, 2.41% on two public datasets.

Copied to clipboard

Wenxi Li, Yiyang Hou, Yajie Ye, Li Liang, Weiwei Sun

Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models (2026.findings-acl)

Challenge:	Existing approaches to generating semantic annotations for different languages are attracting more and more interest.
Approach:	They propose to extend Universal Semantic Tagging to Mandarin Chinese and evaluate its performance.
Outcome:	The proposed scheme is only tested in four Indo–European languages . accuracies are 92.7% and 94.6% for Chinese and English respectively .

Copied to clipboard

Guoming Ling, Zhongzhan Huang, Yupei Lin, Junxin Li, Shanshan Zhong, Hefeng Wu, Liang Lin

The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit (2025.acl-long)

Challenge:	Recent research indicates that Large Reasoning Models suffer from a strategic bottleneck at reasoning path planning.
Approach:	They propose a framework that reformulates reasoning as a dynamic search for the optimal thinking strategy.
Outcome:	The proposed framework improves accuracy and computational cost while reducing generation length by over 22%.

Copied to clipboard

Huixue Zhou, Hengrui Gu, Zaifu Zhan, Xi Liu, Kaixiong Zhou, Yongkang Xiao, Mingfu Liang, Srinivas Prasad Govindan, Piyush Chawla, Jiyan Yang, Xiangfei Meng, Huayu Li, Buyun Zhang, Liang Luo, Wen-Yen Chen, Yiping Han, Bo Long, Rui Zhang, Tianlong Chen

Resonating with RoPE: Spectral Quantization for High-Fidelity Key Cache Compression (2026.acl-long)

Challenge:	Existing frameworks for Large Language Models (LLMs) for Click-Through Rate prediction require a careful balance between computational efficiency and predictive accuracy.
Approach:	They propose a framework that integrates Retrieval-Augmented Generation with a novel multi-head early exit architecture to address both challenges.
Outcome:	The proposed framework reduces retrieval time while maintaining high model performance.

Copied to clipboard

Xuefei Wang, Haoyu Tang, Tianyuan Liang, Zhibin Wang, Yupeng Hu, Weili Guan

Challenge:	Existing approaches to reduce memory footprint of long-context LLMs rely on RoPE-induced oscillations.
Approach:	They propose a frequency-domain framework that converts RoPE-induced oscillations into sparse spectral representations.
Outcome:	The proposed framework achieves efficient compression with performance comparable to FP16 benchmarks.

A Closer Look at Few-Shot Out-of-Distribution Intent Detection (2022.coling-1)

Copied to clipboard

Li-Ming Zhan, Haowen Liang, Lu Fan, Xiao-Ming Wu, Albert Y.S. Lam

Multiple Knowledge-Enhanced Interactive Graph Network for Multimodal Conversational Emotion Recognition (2024.findings-emnlp)

Challenge:	Existing methods for few-shot out-of-distribution (OOD) intent detection are not adequate . despite its importance, few- shot OOD intent detection is a challenging problem .
Approach:	They propose a latent representation generation and self-supervision approach to solve few-shot OOD intent detection problem.
Outcome:	The proposed approach is highly effective and could improve state-of-the-art methods for few-shot OOD intent detection.

Copied to clipboard

Geng Tu, Jun Wang, Zhenyu Li, Shiwei Chen, Bin Liang, Xi Zeng, Min Yang, Ruifeng Xu

Large Language Models Can Learn Representation in Natural Language (2024.findings-acl)

Challenge:	Multimodal Emotion Recognition in Conversations models struggle due to lack of Common Sense Knowledge (CSK).
Approach:	They propose a multimodal approach to integrate multiple knowledge into the edge representations by integrating textual and visual CSK.
Outcome:	The proposed model outperforms state-of-the-art methods on two popular datasets.

Copied to clipboard

Yiduo Guo, Yaobo Liang, Dongyan Zhao, Nan Duan

Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training (2025.acl-long)

Challenge:	Large Language Models (LLMs) are unable to complete complex tasks involving multiple entities, such as tool APIs.
Approach:	They propose a method which uses natural language representations to refine entity descriptions for improved retrieval and LLM utilization.
Outcome:	The proposed method improves GPT-4's performance on classification tasks and API call tasks.

Copied to clipboard

Youliang Yuan, Wenxiang Jiao, Wenxuan Wang, Jen-tse Huang, Jiahao Xu, Tian Liang, Pinjia He, Zhaopeng Tu

CR-UTP: Certified Robustness against Universal Text Perturbations on Large Language Models (2024.findings-acl)

Challenge:	Large Language Models exhibit a level of intelligence that is both impressive and everevolving, but their ability to refuse generating unsafe content is a double-edged sword.
Approach:	They propose a method to tackle a refusal position bias within safety tuning data that compromises the models’ ability to appropriately refuse generating unsafe content.
Outcome:	The proposed method significantly improves model safety without compromising performance and surpasses baseline methods in defending against attacks.

Copied to clipboard

Qian Lou, Xin Liang, Jiaqi Xue, Yancheng Zhang, Rui Xie, Mengxin Zheng

SKA-Bench: A Fine-Grained Benchmark for Evaluating Structured Knowledge Understanding of LLMs (2025.findings-emnlp)

Challenge:	Existing certified robustness methods for certifying input-specific text perturbations have shown promise in certifyling UTPs, but masking only adversarial words can eliminate the attack.
Approach:	They propose a method to certify a language model’s robustness against UTPs by using random smoothing.
Outcome:	The proposed method achieves high certified accuracy under extensive masking and achieves state-of-the-art results in multiple settings.

Copied to clipboard

Zhiqiang Liu, Enpei Niu, Yin Hua, Mengshu Sun, Lei Liang, Huajun Chen, Wen Zhang

Rethinking Task-Specific Knowledge Distillation: Contextualized Corpus as Better Textbook (2022.emnlp-main)

Challenge:	Existing evaluations for Structured Knowledge (SK) understanding are non-rigorous and focus on a single type of SK.
Approach:	They propose a structured knowledge understanding benchmark that includes four widely used structured knowledge forms.
Outcome:	The proposed benchmark is based on four widely used structured knowledge forms . it includes a question, an answer, positive knowledge units, and noisy knowledge units .

Copied to clipboard

Chang Liu, Chongyang Tao, Jianxin Liang, Tao Shen, Jiazhan Feng, Quzhe Huang, Dongyan Zhao

Temp-R1: A Unified Autonomous Agent for Complex Temporal KGQA via Reverse Curriculum Reinforcement Learning (2026.acl-long)

Challenge:	Existing methods for knowledge distillation use a two-stage paradigm: general distillation with a task-agnostic general corpus and task-specific distillation using augmented task- specific corpus.
Approach:	They propose a contextualized corpus that contextualizes task corpus with large-scale general corpus through relevance-based text retrieval to improve student learning.
Outcome:	The proposed model improves on the GLUE benchmark and shows that it is better than generalized corpus and augmented task-specific corpus.

Copied to clipboard

Zhaoyan Gong, Zhiqiang Liu, Songze Li, Xiaoke Guo, Yuanxiang Liu, Xinle Deng, Zhizhen Liu, Lei Liang, Huajun Chen, Wen Zhang

Learning distributed sentence vectors with bi-directional 3D convolutions (2020.coling-main)

Challenge:	Existing methods rely on fixed workflows and expensive closed-source APIs, limiting flexibility and scalability.
Approach:	They propose a temporal reasoning agent that trains on difficult questions first . they expand the action space with specialized internal actions alongside external action .
Outcome:	The proposed agent improves 19.8% over baselines on complex questions and multi-tasks.

Copied to clipboard

Bin Liu, Liang Wang, Guosheng Yin

A Novel Aspect-Guided Deep Transition Model for Aspect Based Sentiment Analysis (D19-1)

Challenge:	Existing methods that render words or characters into images separately, but instead use text's visual features as input, we use 3-dimensional convolutions to learn distributed sentence representation.
Approach:	They propose to use text's visual features as input to learn distributed sentence representation using 3-dimensional sentence tensors and multiple 3-dimensional convolutions with different lengths are applied to the sentence .
Outcome:	The proposed model performs well on several downstream natural language processing tasks.

Copied to clipboard

Yunlong Liang, Fandong Meng, Jinchao Zhang, Jinan Xu, Yufeng Chen, Jie Zhou

HAUSER: Towards Holistic and Automatic Evaluation of Simile Generation (2023.acl-long)

Challenge:	Existing models use aspect-independent encoders for sentence representation generation.
Approach:	They propose an aspect-guided deep transition model which guides the sentence encoding from scratch with a specially-designed deep transition architecture.
Outcome:	The proposed model outperforms existing models on multiple datasets on aspect-category sentiment analysis and aspectterm sentiment analysis without additional features.

Copied to clipboard

Qianyu He, Yikai Zhang, Jiaqing Liang, Yuncheng Huang, Yanghua Xiao, Yunwen Chen

EventRAG: Enhancing LLM Generation with Event Knowledge Graphs (2025.acl-long)

Challenge:	Similes are a crucial part of creative writing, but there is still a lack of evaluation metrics for simile generation.
Approach:	They propose to use similes as a tool to evaluate simile generation metrics . they propose to combine five criteria and automatic metrics for each criterion .
Outcome:	The proposed metrics are significantly more correlated with human ratings from each perspective compared with prior automatic metrics.

Copied to clipboard

Zairun Yang, Yilin Wang, Zhengyan Shi, Yuan Yao, Lei Liang, Keyan Ding, Emine Yilmaz, Huajun Chen, Qiang Zhang

Enhancing Dialogue Summarization with Topic-Aware Global- and Local- Level Centrality (2023.eacl-main)

Challenge:	Existing approaches to text generation often neglect event structures that shape real-world narratives.
Approach:	They propose a framework that integrates structured event semantics with iterative retrieval and inference to enhance text generation.
Outcome:	Experiments on UltraDomain and MultiHopRAG show that the proposed framework outperforms baseline RAG systems in generation effectiveness, logical consistency, and multi-hop reasoning accuracy.

Copied to clipboard

Xinnian Liang, Shuangzhi Wu, Chenhao Cui, Jiaqi Bai, Chao Bian, Zhoujun Li

CMU-MOSEAS: A Multimodal Language Dataset for Spanish, Portuguese, German and French (2020.emnlp-main)

Challenge:	Experimental results show that our model outperforms strong baselines on three public dialogue summarization datasets: CSDS, MC, and SAMSUM.
Approach:	They propose a topic-aware global-local centrality model to help select the salient context from all sub-topics.
Outcome:	The proposed model outperforms baselines on three public dialogue summarization datasets: CSDS, MC, and SAMSUM.

Copied to clipboard

AmirAli Bagher Zadeh, Yansheng Cao, Simon Hessner, Paul Pu Liang, Soujanya Poria, Louis-Philippe Morency

Deep Attention Diffusion Graph Neural Networks for Text Classification (2021.emnlp-main)

Challenge:	Existing datasets in multimodal language are limited and disproportionately affect native speakers of other languages . authors propose a large-scale dataset for Spanish, Portuguese, German and French .
Approach:	They propose a large-scale multimodal language dataset for Spanish, Portuguese, German and French.
Outcome:	The proposed dataset is the largest of its kind with 40,000 total labelled sentences . it covers a diverse set topics and speakers and carries supervision of 20 labels including sentiment, emotions, and attributes.

Copied to clipboard

Yonghao Liu, Renchu Guan, Fausto Giunchiglia, Yanchun Liang, Xiaoyue Feng

Knowledge-Guided Dynamic Modality Attention Fusion Framework for Multimodal Sentiment Analysis (2024.findings-emnlp)

Challenge:	Existing methods for text classification based on graph neural networks (GNNs) consider only one-hop neighborhoods and low-frequency information within texts, which suffer from over-smoothing issues if many graph layers are stacked.
Approach:	They propose a deep attention diffusion Graph Neural Network model to learn text representations by bridging the chasm of interaction difficulties between a word and its distant neighbors.
Outcome:	The proposed model outperforms existing methods on standard benchmark datasets on a set of textual features.

Copied to clipboard

Xinyu Feng, Yuming Lin, Lihua He, You Li, Liang Chang, Ya Zhou

It’s Not Bragging If You Can Back It Up: Can LLMs Understand Braggings? (2025.acl-long)

Challenge:	Existing methods focus on equally treating the contribution of each modality or statically using text as the dominant modality to conduct interaction, which neglects the situation where each modal may become dominant.
Approach:	They propose a Knowledge-Guided Dynamic Modality Attention Fusion Framework (KuDA) that uses sentiment knowledge to guide the model dynamically selecting the dominant modality and adjusting the contributions of each modality.
Outcome:	The proposed model can be used to highlight the contribution of dominant modality through the correlation evaluation loss.

Copied to clipboard

Jingjie Zeng, Huayang Li, Liang Yang, Yuanyuan Sun, Hongfei Lin

Challenge:	Bragging is a pervasive social-linguistic phenomenon that reflects complex human interaction patterns.
Approach:	They propose to use bragging recognition, bragging explanation, and bragging generation tasks to examine bragging in large language models (LLMs) .
Outcome:	The proposed models can identify bragging intent, social appropriateness, and account for context sensitivity and provide new insights into how LLMs process bragging.

VisDiaHalBench: A Visual Dialogue Benchmark For Diagnosing Hallucination in Large Vision-Language Models (2024.acl-long)

Copied to clipboard

Qingxing Cao, Junhao Cheng, Xiaodan Liang, Liang Lin

LinkBERT: Pretraining Language Models with Document Links (2022.acl-long)

Challenge:	Despite the significant success of large vision-language models, some studies have revealed that LVLMs suffer from the hallucination problem when given long-term misleading textual history.
Approach:	They propose a visual dialogue hallucination evaluation benchmark VisDiaHalBench to investigate the halluciation problem of large vision-language models when given long-term misleading textual history.
Outcome:	The proposed benchmark consists of samples with five-turn questions about an edited image and its original version.

Copied to clipboard

Michihiro Yasunaga, Jure Leskovec, Percy Liang

Unifying Human and Statistical Evaluation for Natural Language Generation (N19-1)

Challenge:	Existing language model pretraining methods do not capture dependencies or knowledge that span across documents.
Approach:	They propose a language model pretraining method that leverages links between documents . they use masked language modeling and document relation prediction to model LMs .
Outcome:	The proposed method outperforms existing methods on downstream tasks across two domains.

Copied to clipboard

Tatsunori B. Hashimoto, Hugh Zhang, Percy Liang

Dynamic and Efficient Inference for Text Generation via BERT Family (2023.acl-long)

Challenge:	Human evaluation captures quality but fails to capture diversity . statistical evaluation fails to catch models that plagiarize from training set .
Approach:	They propose a framework which evaluates both diversity and quality based on the optimal error rate of predicting whether a sentence is human-generated.
Outcome:	The proposed framework evaluates diversity and quality on summarization and chit-chat dialogue.

Copied to clipboard

Xiaobo Liang, Juntao Li, Lijun Wu, Ziqiang Cao, Min Zhang

C-World: A Computer Use Agent Environment Creator (2026.acl-long)

Challenge:	Existing methods to improve performance of pre-trained language models are limited due to large-scale parameters and the universal autoregressive decoding paradigm.
Approach:	They propose a novel fine-tuning method which can make a single pre-trained model support Dynamic and Efficient infERence and achieve an adaptive trade-off between model performance and latency.
Outcome:	The proposed method achieves higher BLEU scores than the strong autoregressive Transformer model on translation tasks with 3 12 times speedup and faster inference speed compared with the BART model on four GLGE benchmark tasks.

Copied to clipboard

Ziqiao Xi, Shuang Liang, Qi Liu, Jiaqing Zhang, Letian Peng, Fang Nan, Meshal Nayim, Tianhui Zhang, Rishika Mundada, Lianhui Qin, Biwei Huang, Kun Zhou

Challenge:	C-World enables users to build agent environments on demand.
Approach:	They propose a system that enables users to build agent environments on demand.
Outcome:	The proposed system outperforms baselines on 119k samples and achieves Spearman = 0.883 ranking correlation with real execution.

ServImage: An Image Generation and Editing Benchmark from Real-world Commercial Imaging Services (2026.acl-long)

Copied to clipboard

Fengxian Ji, Jingpu Yang, Zirui Song, Lang Gao, Junhong Liang, Zhenhao Chen, Jinghui Zhang, Xiuying Chen

GuideTree: Guideline-Induced Review Trees for Long Medical Records (2026.acl-industry)

Challenge:	Recent image generation and editing models demonstrate robust adherence to instructions and high visual quality on academic benchmarks.
Approach:	They propose a benchmark that correlates image outputs with economic value in commercial design projects.
Outcome:	ServImage benchmarks show image generation models perform well on academic benchmarks but are uncertain on commercial projects.

Copied to clipboard

Chengze Ge, Ruiqing Zhang, Yining Wang, Shengping Liu, Liang Jiaen, null Weihuang, Weihua Chen

Respond in my Language: Mitigating Language Inconsistency in Response Generation based on Large Language Models (2024.acl-long)

Challenge:	Medical record reviewers must produce consistent, traceable, guideline-compliant outcomes . longcontext inference is expensive and often degrades as inputs grow .
Approach:	a new method compiles textual guidelines into a fixed review tree . a cost-aware split-and-prune search is used to update the tree offline . the algorithm produces consistent, traceable, guideline-compliant outcomes .
Outcome:	The proposed system outperforms the strongest non-expert baselines by 84.5–92.8 Macro-F1 . it reduces average I/O volume to 74K input+output characters and average latency to 22s .

Copied to clipboard

Liang Zhang, Qin Jin, Haoyang Huang, Dongdong Zhang, Furu Wei

Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Exploration (2026.findings-acl)

Challenge:	Large Language Models (LLMs) show strong instruction understanding ability across multiple languages, but are easily biased towards English in instruction tuning.
Approach:	They propose to use a model with Pseudo-Inconsistent Penalization to prevent the model from generating English responses when given non-English language prompts during training and prior Enhanced decoding to improve the language consistency of the model.
Outcome:	The proposed methods significantly improve the language consistency of the model without multilingual data.

Copied to clipboard

Linzhuang Sun, Tianyu Guo, Hao Liang, Ruitong Liu, Yuying Li, Qifeng Cai, Jingxuan Wei, Yuchen Wu, Bihui Yu, Xiangxiang Zhang, Wentao Zhang, Bin Cui

Ask-and-Verify: Span Candidate Generation and Verification for Attribute Value Extraction (2022.emnlp-industry)

Challenge:	Structured Query Language (SQL) is the cornerstone for data-driven decision-making.
Approach:	They propose a benchmark to rigorously evaluate Large Language Models within a dynamic interaction framework.
Outcome:	The proposed benchmark aims to rigorously evaluate LLMs within a dynamic interaction framework.

Copied to clipboard

Yifan Ding, Yan Liang, Nasser Zalmout, Xian Li, Christan Grant, Tim Weninger

Exploring the Impact of Negative Samples of Contrastive Learning: A Case Study of Sentence Embedding (2022.findings-acl)

Challenge:	Existing reading comprehension models can over-generate attribute values which hinders precision.
Approach:	They propose a product attribute value extraction task that captures key factual information from product descriptions and a new end-to-end pipeline framework called Ask-and-Verify.
Outcome:	The proposed framework outperforms existing models by up to 3.1% F1 absolute improvement points while scaling to thousands of attributes.

Copied to clipboard

Rui Cao, Yihao Wang, Yuxin Liang, Ling Gao, Jie Zheng, Jie Ren, Zheng Wang

SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility (2026.acl-long)

Challenge:	Unsupervised contrastive learning is emerging as a powerful technique for extracting knowledge from unlabeled data.
Approach:	They propose a momentum contrastive learning model with negative sample queue for sentence embedding with a simulated model with EMA update mechanism.
Outcome:	The proposed model achieves a Spearman’s correlation of 77.27% on the semantic text similarity task and a maximum traceable distance metric.

Copied to clipboard

Xuyang Zhi, Peilun Zhou, Chengqiang Lu, Hang Lv, Yiwei Liang, Rongyang Zhang, Yan Gao, null Yiwu, Yao Hu, Hongchao Gu, Defu Lian, Hao Wang, Enhong Chen

Challenge:	Large Language Models (LLMs) are shifting the focus from single verifiable tasks toward complex, open-ended real-world scenarios.
Approach:	They propose a framework that automatically adjusts reward weights and data importance to synchronize learning intent with data utility for optimal performance.
Outcome:	The proposed framework improves model capabilities across all domains and scales.

A Survey of Ontology Expansion for Conversational Understanding (2024.emnlp-main)

Copied to clipboard

Jinggui Liang, Yuxia Wu, Yuan Fang, Hao Fei, Lizi Liao

Data Interpreter: An LLM Agent for Data Science (2025.findings-acl)

Challenge:	Current methods for conversational understanding rely on static ontologies, limiting their ability to handle new and unforeseen user needs.
Approach:	They propose to review the state-of-the-art techniques in OnExp for conversational understanding and highlight emerging frontiers . they categorize existing literature into three main areas: (1) New Intent Discovery, (2) New Slot-Value Discovery, and (3) Joint OnExp.
Outcome:	The proposed methods highlight several emerging frontiers in OnExp to improve agent performance in real-world scenarios and discuss their corresponding challenges.

Copied to clipboard

Sirui Hong, Yizhang Lin, Bang Liu, Bangbang Liu, Binhao Wu, Ceyao Zhang, Danyang Li, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Li Zhang, Lingyao Zhang, Min Yang, Mingchen Zhuge, Taicheng Guo, Tuo Zhou, Wei Tao, Robert Tang, Xiangtao Lu, Xiawu Zheng, Xinbing Liang, Yaying Fei, Yuheng Cheng, Yongxin Ni, Zhibin Gou, Zongze Xu, Yuyu Luo, Chenglin Wu

PclGPT: A Large Language Model for Patronizing and Condescending Language Detection (2024.findings-emnlp)

Challenge:	Large Language Models (LLMs) excel in various domains but face challenges when applied to data science workflows due to their complex, multi-stage nature.
Approach:	They propose a hierarchical graph-based agent that represents complexity and a progressive strategy for step-by-step verification, refinement, and consistent context management.
Outcome:	The proposed agent surpasses state-of-the-art baselines on the MATH dataset and performs better on InfiAgent-DABench.

Copied to clipboard

Hongbo Wang, LiMingDa LiMingDa, Junyu Lu, Hebin Xia, Liang Yang, Bo Xu, Ruizhu Liu, Hongfei Lin

Explainable Multi-hop Verbal Reasoning Through Internal Monologue (2021.naacl-main)

Challenge:	Patronizing and condescending language is an essential branch of toxic language . pre-trained language models perform poorly in detecting PCL due to its implicit toxicity traits .
Approach:	They propose a novel LLM benchmark for patronizing and condescending language . they use a dataset to analyze the toxicity of patronizing condescending languages .
Outcome:	The proposed model can detect patronizing and condescending language (PCL) the model can be used to analyze the toxicity of the language and to improve the detection.

Copied to clipboard

Zhengzhong Liang, Steven Bethard, Mihai Surdeanu

A Variational Hierarchical Model for Neural Cross-Lingual Summarization (2022.acl-long)

Challenge:	Existing state-of-the-art language models do not make intermediate reasoning steps explicit . large pretrained language models such as BERT and RoBERTa have been successfully used in multi-hop reasoning problems .
Approach:	They propose to decompose multi-hop reasoning problems into several simple ones and use natural language to guide intermediate reasoning hops.
Outcome:	The proposed model can generate subgoals and perform inference in natural language at each reasoning step.

Copied to clipboard

Yunlong Liang, Fandong Meng, Chulun Zhou, Jinan Xu, Yufeng Chen, Jinsong Su, Jie Zhou

MT3: A Synergistic Multi-Task RL Framework for Specializing MLLMs in Text Image Machine Translation (2026.acl-long)

Challenge:	Existing studies on cross-lingual summarization focus on pipeline methods or jointly training an end-to-end model through an auxiliary MT or MS objective.
Approach:	They propose a hierarchical model for the cross-lingual summarization task . the model is based on the conditional variational auto-encoder .
Outcome:	The proposed model generates better cross-lingual summaries than comparison models in the few-shot setting.

Copied to clipboard

Zhaopeng Feng, Yupu Liang, Shaosheng Cao, Jiayuan Su, Jiahan Ren, Zhijie Zhou, Wenxuan Huang, Jian Wu, Zuozhu Liu

Beta Distribution Guided Aspect-aware Graph for Aspect Category Sentiment Analysis with Affective Knowledge (2021.emnlp-main)

Challenge:	Text Image Machine Translation (TIMT) is a critical subfield of machine translation . it requires accurate optical character recognition, robust visual-text reasoning, and high-quality translation a challenge .
Approach:	They propose a multi-task optimization framework to specialize MLLMs into expert TIMT models.
Outcome:	The proposed model outperforms baselines on the latest in-domain MIT-10M benchmark.

Copied to clipboard

Bin Liang, Hang Su, Rongdi Yin, Lin Gui, Min Yang, Qin Zhao, Xiaoqi Yu, Ruifeng Xu

Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability (2026.acl-long)

Challenge:	Existing methods for aspect category sentiment analysis do not necessarily occur in a sentence.
Approach:	They propose a Beta Distribution-guided aspect-aware graph construction based on external knowledge . they use aspect-related words as the pivots to derive aspect-relevant weights .
Outcome:	The proposed approach outperforms the state-of-the-art methods on 6 benchmark datasets.

Copied to clipboard

Xiao Liang, Zhong-Zhi Li, Zhenghao Lin, Eric Hanchen Jiang, Hengyuan Zhang, Yelong Shen, Kai-Wei Chang, Ying Nian Wu, Yeyun Gong, Weizhu Chen

Knowledge-Augmented Multimodal Clinical Rationale Generation for Disease Diagnosis with Small Language Models (2025.acl-long)

Challenge:	Large language models have demonstrated strong reasoning capabilities through step-by-step chain-of-thought (CoT) reasoning, but their strictly sequential nature constrains test-time scalability.
Approach:	They propose an end-to-end reinforcement learning framework to enhance LLMs' DAC-style reasoning capacity by decomposing a problem into subproblems and solving them sequentially.
Outcome:	The proposed model surpasses CoT by 8.6% and 6.3% on competition-level benchmarks and is available at the [github.com/MasterVito/DAC-RL].

Copied to clipboard

Shuai Niu, Jing Ma, Hongzhan Lin, Liang Bai, Zhihua Wang, Richard Yi Da Xu, Yunya Song, Xian Yang

An Auxiliary Task Boosted Multi-task Learning Method for Service Account Retrieval with Limited Human Annotation (2023.emnlp-industry)

Challenge:	Existing models struggle to balance predictive accuracy with human-understandable rationales.
Approach:	They propose to enhance LLMs by leveraging rationale distillation and domain knowledge injection for trustworthy multimodal rationale generation.
Outcome:	Experiments on real-world medical datasets show that ClinRaGen achieves state-of-the-art performance in disease diagnosis and rationale generation.

Copied to clipboard

Yuanzhou Yao, Zhao Zhang, Kaijia Yang, Huasheng Liang, Qiang Yan, Yongjun Xu

L4: Mutual Learning Helps Lifelong Language Learning (2025.emnlp-industry)

Challenge:	Existing approaches to service account retrieval have limited human annotation, resulting in labor-intensive and time-consuming tasks.
Approach:	They propose an Auxiliary task Boosted Multi-Task Learning method which introduces multiple auxiliary tasks and enhances the performance of the main task, service account retrieval.
Outcome:	The proposed method improves the performance of the main task, service account retrieval.

Copied to clipboard

Jiyong Li, Dilshod Azizov, Shangsong Liang

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models (2026.findings-acl)

Challenge:	Existing distillation methods rely on domain-specific teachers, limiting their ability to update in real-time and adapt to dynamic environments.
Approach:	They propose a framework that enables continuous mutual learning from task streams without relying on domain-specific teachers.
Outcome:	The proposed framework reduces catastrophic forgetting while improving performance on various benchmark datasets making it suitable for real-world, dynamic natural language processing (NLP) applications.

Copied to clipboard

Hengyuan Zhang, Zhihao Zhang, Ercong Nie, Mingyang Wang, Zunhai Su, Yiwei Wang, Qianli Wang, Shuzhou Yuan, Xufeng Duan, Qibo Xue, Zeping Yu, Chenming Shang, Xiao Liang, Jing Xiong, Hui Shen, Chaofan Tao, Zhengwu Liu, Senjie Jin, Zhiheng Xi, Dongdong Zhang, Sophia Ananiadou, Tao Gui, Ruobing Xie, Hayden Kwok-Hay So, Hinrich Schuetze, Xuanjing Huang, Qi Zhang, Ngai Wong

KGHaluBench: A Knowledge Graph-Based Hallucination Benchmark for Evaluating the Breadth and Depth of LLM Knowledge (2026.findings-eacl)

Challenge:	Existing literature on mechanistic interpretation (MI) treats it as an observational science, leaving practical applications underexplored.
Approach:	They propose a survey structured around the pipeline to identify and improve MI models.
Outcome:	The proposed framework enables tangible improvements in Alignment, Capability, and Efficiency.

Copied to clipboard

Alex Robertson, Huizhi Liang, Mahbub Gani, Rohit Kumar, Srijith Rajamohan

InfoMetIC: An Informative Metric for Reference-free Image Caption Evaluation (2023.acl-long)

Challenge:	Existing benchmarks for large language models are limited by static and narrow questions, leading to limited coverage and misleading evaluations.
Approach:	They propose a Knowledge Graph-based hallucination benchmark that assesses Large Language Models across the breadth and depth of their knowledge and provides a fairer and more comprehensive insight into LLM truthfulness.
Outcome:	The proposed framework assesses LLMs across breadth and depth of their knowledge, and provides a fairer and more comprehensive insight into LLM truthfulness.

Copied to clipboard

Anwen Hu, Shizhe Chen, Liang Zhang, Qin Jin

PEDANTS: Cheap but Effective and Interpretable Answer Equivalence (2024.findings-emnlp)

Challenge:	Existing image captioning metrics provide a single score to measure caption qualities, which are less explainable and informative.
Approach:	They propose an Informative Metric for Reference-free Image Caption evaluation to support this feedback . they propose to provide a text precision score, a vision recall score and an overall quality score .
Outcome:	The proposed method improves on existing metrics on multiple benchmarks and compares coarse-grained scores with human judgements.

Copied to clipboard

Zongxia Li, Ishani Mondal, Huy Nghiem, Yijun Liang, Jordan Boyd-Graber

Simpler and Faster Learning of Adaptive Policies for Simultaneous Translation (D19-1)

Challenge:	Current short-form QA evaluations lack diverse styles of evaluation data and rely on expensive and slow LLMs.
Approach:	They propose a rubric for machine QA that is more stable than an exact match and neural methods.
Outcome:	The proposed evaluations improve on the existing short-form QA evaluations using the Trivia community.

Copied to clipboard

Baigong Zheng, Renjie Zheng, Mingbo Ma, Liang Huang

MMA: Cross-Domain Knowledge Integration via Mixture of Multi-Domain Agents (2025.findings-emnlp)

Challenge:	Recent work on simultaneous translation is difficult because of its latency and quality.
Approach:	They propose a supervised-learning framework to learn adaptive policies from parallel text sequences . they use a model that predicts when a target word is read or WRITE if context provides enough information .
Outcome:	Experiments on German=>English show that the proposed method can learn flexible policies with better BLEU scores and similar latencies compared to previous work.

Copied to clipboard

Kehang Jia, Juntao Li, Xiaobo Liang, Yisheng Xiao, Yixuan Yang, Min Zhang

Challenge:	achieving synergistic improvements between generalization and domain specialization remains a challenge in pre-training and post-training.
Approach:	They propose a test-time cross-domain knowledge integration method that integrates general-purpose and domain-specific models to enhance their performance on complex, domainspecific tasks.
Outcome:	The proposed method combines the outputs of general-purpose and domain-specific models to improve their performance on complex, domainspecific tasks.

Self-Renewal Prompt Optimizing with Implicit Reasoning (2024.findings-emnlp)

Copied to clipboard

Zihan Liang, Ben Chen, Zhuoran Ran, Zihan Wang, Huangyu Dai, Yufei Ma, Dehong Gao, Xiaoyan Cai, Libin Yang

UniMath: A Foundational and Multimodal Mathematical Reasoner (2023.emnlp-main)

Challenge:	Recent advances in NLP have been driven by the development of Large Language Models (LLMs).
Approach:	They propose a self-renewal approach to optimize LLM outputs to better align with human preferences without supervised fine-tuning.
Outcome:	The proposed approach improves outputs to better align with human preferences across LLMs and tasks without supervised fine-tuning.

Copied to clipboard

Zhenwen Liang, Tianyu Yang, Jipeng Zhang, Xiangliang Zhang

Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach (2021.emnlp-main)

Challenge:	Existing methods for interpreting and processing diverse mathematical modalities are limited . existing systems are limited in interpreting complex mathematical tasks and implementing them in a multimodal manner.
Approach:	They propose a multimodal mathematical reasoning system that utilizes a fine-tuned T5 model augmented with a variational autoencoder (VAE)-based image tokenizer.
Outcome:	The proposed model achieves state-of-the-art performance on SVAMP, GeoQA, and TableMWP datasets and is generalized on two additional datasets.

Copied to clipboard

Simiao Zuo, Chen Liang, Haoming Jiang, Xiaodong Liu, Pengcheng He, Jianfeng Gao, Weizhu Chen, Tuo Zhao

An Empirical Study of Sentiment-Enhanced Pre-Training for Aspect-Based Sentiment Analysis (2023.findings-acl)

Challenge:	Existing approaches to adversarial regularization treat adversarials and defending players equally, which is undesirable because only the defending player contributes to the generalization performance.
Approach:	They propose a method which formulates adversarial regularization as a Stackelberg game and induces a competition between a leader and a follower.
Outcome:	The proposed method outperforms existing adversarial regularization baselines on a set of machine translation and natural language understanding tasks.

Copied to clipboard

Yice Zhang, Yifan Yang, Bin Liang, Shiwei Chen, Bing Qin, Ruifeng Xu

AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models (2026.acl-long)

Challenge:	Existing approaches to Aspect-Based Sentiment Analysis (ABSA) are lacking in a comprehensive evaluation and fair comparison.
Approach:	They propose to use a knowledge-mining method to build a large-scale knowledge-annotated SPT corpus and integrate sentiment knowledge into pre-training.
Outcome:	The proposed method is able to build a large-scale knowledge-annotated SPT corpus and compares with other methods.

Copied to clipboard

Jiacheng Liang, Tanqiu Jiang, Yuhui Wang, Rongyi Zhu, Fenglong Ma, Ting Wang

Efficient Low-rank Multimodal Fusion With Modality-Specific Factors (P18-1)

Challenge:	Large reasoning models (LRMs) generate coherent reasoning paths before conclusions, but they introduce new vulnerabilities.
Approach:	They propose a framework that leverages a weaker but less-aligned model to simulate execution reasoning for initial hijacking attempts and iteratively refines attacks by exploiting reasoning patterns leaked through the target LRM’s refusals.
Outcome:	The proposed framework achieves 100% success rate within one or few turns, neutralizing reasoning-based defenses even when evaluated by robustly aligned external models.

Copied to clipboard

Zhun Liu, Ying Shen, Varun Bharadhwaj Lakshminarasimhan, Paul Pu Liang, AmirAli Bagher Zadeh, Louis-Philippe Morency

D2TV: Dual Knowledge Distillation and Target-oriented Vision Modeling for Many-to-Many Multimodal Summarization (2023.findings-emnlp)

Challenge:	Multimodal research is a growing field of artificial intelligence, and fusion is one of the main research problems.
Approach:	They propose a low-rank multimodal fusion method which integrates multiple unimodal representations into one compact multimodal representation.
Outcome:	The proposed method achieves competitive results on multimodal sentiment analysis, speaker trait analysis, and emotion recognition tasks while reducing computational complexity.

Copied to clipboard

Yunlong Liang, Fandong Meng, Jiaan Wang, Jinan Xu, Yufeng Chen, Jie Zhou

Intention Analysis Makes LLMs A Good Jailbreak Defender (2025.coling-main)

Challenge:	Existing studies focus on improving MMS models by filtering summary-unrelated visual features with implicit learning or explicitly complex training objectives.
Approach:	They propose a multimodal multimodal summarization task that aims to generate summaries in any language with document inputs in any languages and the corresponding image sequence.
Outcome:	The proposed task can generate summaries in any language with document inputs in any languages and the corresponding image sequence.

Copied to clipboard

Yuqi Zhang, Liang Ding, Lefei Zhang, Dacheng Tao

AgentInit: Initializing LLM-based Multi-Agent Systems via Diversity and Expertise Orchestration for Effective and Efficient Collaboration (2025.findings-emnlp)

Challenge:	Existing methods to align large language models with human values overlook the intrinsic nature of jailbreaks, which limits their effectiveness in complex scenarios.
Approach:	They propose a simple yet highly effective defense strategy, i.e., Intention Analysis (IA). They show that IA suppresses LLM’s tendency to follow jailbreak prompts, thereby enhancing safety.
Outcome:	The proposed strategy reduces harmfulness of LLMs and outperforms GPT-3.5 in attack success rate.

Copied to clipboard

Chunhao Tian, Yutong Wang, Xuebo Liu, Zhexuan Wang, Liang Ding, Miao Zhang, Min Zhang

Selected Languages are All You Need for Cross-lingual Truthfulness Transfer (2025.coling-main)

Challenge:	Existing MAS initialization methods do not fully account for the collaborative needs of the generated agents in subsequent stages.
Approach:	They propose to use a Natural Language to Format mechanism to optimize the structure of agent teams and incorporate a natural language to format mechanism to ensure consistency and standardization.
Outcome:	The proposed method outperforms state-of-the-art initialization methods and pre-defined strategies across various frameworks and tasks while reducing token consumption.

Copied to clipboard

Weihao Liu, Ning Wu, Wenbiao Ding, Shining Liang, Ming Gong, Dongmei Zhang

Unbiased Math Word Problems Benchmark for Mitigating Solving Bias (2022.findings-naacl)

Challenge:	Existing methods for truthfulness enhancement in English are limited to multilingual scenarios.
Approach:	They propose a method for cross-lingual truthfulness transfer that uses language bias and transfer contributions to select an optimal subset of all tested languages and employ translation instruction tuning for cross language truthfulness transfers.
Outcome:	The proposed method reduces multilingual representation disparity and boosts cross-lingual truthfulness transfer of LLMs.

Copied to clipboard

Zhicheng Yang, Jinghui Qin, Jiaqi Chen, Xiaodan Liang

DB-LLM: Accurate Dual-Binarization for Efficient LLMs (2024.findings-acl)

Challenge:	Existing solvers with data bias and learning bias only learn shallow heuristics rather than deep semantics for understanding problems.
Approach:	They propose a MWP dataset named UnbiasedMWP which is constructed by varying the grounded expressions in collected data and annotating them manually.
Outcome:	The proposed dataset has significantly fewer biases than its original data and other datasets, posing a promising benchmark for fairly evaluating the solvers’ reasoning skills rather than matching nearest neighbors.

Copied to clipboard

Hong Chen, Chengtao Lv, Liang Ding, Haotong Qin, Xiabin Zhou, Yifu Ding, Xuebo Liu, Min Zhang, Jinyang Guo, Xianglong Liu, Dacheng Tao

MathMixup: Boosting LLM Mathematical Reasoning with Difficulty-Controllable Data Synthesis and Curriculum Learning (2026.findings-acl)

Challenge:	Existing methods for ultra-low bit quantization cause severe accuracy drops . a novel Dual-Binarization method is proposed for efficient Large Language Models .
Approach:	They propose a Dual-Binarization method that takes 2-bit-width and binarization into account . they propose DB-LLM, which uses a 2-bit binarized weighted model to represent weights efficiently .
Outcome:	The proposed method surpasses the current State-of-the-Art in ultra-low bit quantization and achieves 20% reduction in computational consumption compared to the SOTA method under the same bit-width.

Copied to clipboard

Xuchen Li, Jing Chen, Xuzhao Li, Hao Liang, Xiaohuan Zhou, Taifeng Wang, Wentao Zhang

LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offline (2025.findings-acl)

Challenge:	Existing data synthesis methods suffer from limited diversity and lack precise control over problem difficulty, making them insufficient for efficient training paradigms such as curriculum learning.
Approach:	They propose a data synthesis paradigm that generates high-quality, difficulty-controllable mathematical reasoning problems through hybrid and decomposed strategies.
Outcome:	The proposed paradigm outperforms existing methods and improves mathematical reasoning abilities.

Copied to clipboard

Biao Fu, Minpeng Liao, Kai Fan, Chengxi Li, Liang Zhang, Yidong Chen, Xiaodong Shi

Intrinsic Mutual Information as a Modulator for Preference Optimization (2026.findings-acl)

Challenge:	Large language models perform well in offline machine translation when the complete source sentence is provided . however, in many real scenarios, the source tokens arrive in a streaming manner and simultaneous machine translation is required .
Approach:	They propose a new paradigm that includes constructing supervised fine-tuning data for simultaneous machine translation (SiMT) to achieve SiMT, source and target tokens are rearranged into interleaved sequences, separated by special tokens according to varying latency requirements.
Outcome:	The proposed approach achieves state-of-the-art performance across various SiMT benchmarks and evaluation metrics while maintaining efficient auto-regressive decoding.

Copied to clipboard

Peng Liao, Peijia Zheng, Lingbo Li, Shangsong Liang, Lin Chen

Challenge:	Existing methods for offline preference optimization involve additional hyperparameter tuning, resulting in substantial time overhead.
Approach:	They propose a lightweight framework for offline preference optimization that leverages hyperparameter modulation to decouple preference contributions.
Outcome:	The proposed framework achieves superior performance over existing methods while reducing training overhead by more than 15%.

Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training (2026.acl-long)

Copied to clipboard

Kailai Yang, Xiao Liu, Lei Ji, Hao Li, Xiao Liang, Zhiwei Liu, Yeyun Gong, Peng Cheng, Mao Yang

RealChart2Code: Bridging the Gap in Real-World Chart-to-Code Generation via Multi-Task Evaluation (2026.acl-long)

Challenge:	Existing methods for reweighting data mixtures rely on manual designation with certain heuristics based on intuition or empirical results.
Approach:	They propose a model-based framework that learns to re-weight domains by reinforcement learning on large quantities of data mixing trajectories with corresponding feedback from an evaluation environment.
Outcome:	The proposed framework outperforms baselines in achieving balanced performance across source and target fields and domain spaces without retraining.

Copied to clipboard

Jiajun Zhang, Yuying Li, Zhixun Li, Xingyu Guo, Jingzhuo Wu, Leqi Zheng, Yiran Yang, Jianke Zhang, Qingbin Li, Shannan Yan, Changguo Jia, Junfei Wu, Zilei Wang, Qiang Liu, Liang Wang

Hidden States as Early Signals: Step-level Trace Evaluation and Pruning for Efficient Test-Time Scaling (2026.findings-acl)

Challenge:	Vision-Language Models (VLMs) have demonstrated impressive capabilities in code generation across various domains, but their ability to replicate complex, multi-panel visualizations remains largely unassessed.
Approach:	They propose a large-scale benchmark to evaluate chart generation from large- scale raw data and assess iterative code refinement in a multi-turn conversational setting.
Outcome:	The new benchmark evaluates 14 leading VLMs on real-world data and shows they struggle with complex plot structures and authentic data.

Copied to clipboard

Zhixiang Liang, Beichen Huang, Zheng Wang, Minjia Zhang

Multi-Modal Knowledge Graph Transformer Framework for Multi-Modal Entity Alignment (2023.findings-emnlp)

Challenge:	Existing approaches to speed up parallel scaling have relied on similarity-based or confidence-based pruning, but these signals do not reliably indicate trace quality.
Approach:	They propose a pruning framework that evaluates reasoning steps using hidden states and dynamically prunes unpromising traces during generation.
Outcome:	The proposed framework reduces end-to-end inference latency by 45%–70% on average compared to self-consistency while improving reasoning accuracy.

Copied to clipboard

Qian Li, Cheng Ji, Shu Guo, Zhaoji Liang, Lihong Wang, Jianxin Li

Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs (2026.findings-acl)

Challenge:	Multi-modal entity alignment (MMEA) is a critical task that aims to identify equivalent entity pairs across multi-modal knowledge graphs (MMKGs).
Approach:	They propose a novel MMEA transformer that hierarchically introduces neighbor features, multi-modal attributes, and entity types to enhance alignment task.
Outcome:	The proposed transformer hierarchically introduces neighbor features, multi-modal attributes, and entity types to enhance the alignment task.

Copied to clipboard

Jinbo Liu, Defu Cao, Yifei Wei, Tianyao Su, Yuan Liang, Yushun Dong, Yan Liu, Yue Zhao, Xiyang Hu

Reconstruct Before Summarize: An Efficient Two-Step Framework for Condensing and Summarizing Meeting Transcripts (2023.emnlp-main)

Challenge:	Multi-agent LLMs are rapidly moving from prototype to real-world use . network topology is a first-order security parameter in multi-aggent systems .
Approach:	They propose a framework for comparing topology-conditioned memory leakage in multi-agent LLM systems.
Outcome:	The proposed framework evaluates topology-conditioned memory leakage in multi-agent LLM systems.

Copied to clipboard

Haochen Tan, Han Wu, Wei Shao, Xinyun Zhang, Mingjie Zhan, Zhaohui Hou, Ding Liang, Linqi Song

PBoS: Probabilistic Bag-of-Subwords for Generalizing Word Embedding (2020.findings-emnlp)

Challenge:	Existing approaches to meeting summarization are limited due to noise, lengthy transcripts, and scattered salient information.
Approach:	They propose a two-step framework for meeting summarization that leverages a self-supervised paradigm to reconstruct transcripts and a relative positional bucketing algorithm to equip models to generate the summary.
Outcome:	The proposed method significantly reduces memory consumption and processing time on two meeting summarization datasets.

Copied to clipboard

Zhao Jinman, Shawn Zhong, Xiaomin Zhang, Yingyu Liang

Context-aware Watermark with Semantic Balanced Green-red Lists for Large Language Models (2024.emnlp-main)

Challenge:	Existing word embeddings assume fixed finite-size vocabularies, hindering their ability to provide useful word representations for out-of-vocaulary words.
Approach:	They propose a model that generalizes word embeddings without extra contextual information . they use the spellings of words to model subword segmentation and compute subword-based compositional word embeds.
Outcome:	The proposed model can generate meaningful subword segmentations without any source of explicit morphological knowledge.

Copied to clipboard

Yuxuan Guo, Zhiliang Tian, Yiping Song, Tianlun Liu, Liang Ding, Dongsheng Li

UniSonate: A Unified Model for Speech, Music, and Sound Effect Generation with Text Instructions (2026.acl-long)

Challenge:	Recent research suggests that watermarking methods cause degradation of text quality due to semantic disparities between the watermarked text and the unwatermarked text.
Approach:	They propose a semantic-aware watermark method that generates a watermark key considering contexts to split a green/red list for watermark injection.
Outcome:	The proposed method reduces performance drop due to adding bias on green lists . it also allows green lists to cover almost all semantics .

Copied to clipboard

Chunyu Qiang, Xiaopeng Wang, Kang Yin, Yuzhe Liang, Yuxin Guo, Teng Ma, Ziyu Zhang, Tianrui Wang, Cheng Gong, Yushen Chen, Ruibo Fu, Longbiao Wang, Jianwu Dang

Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation (P19-3)

Challenge:	Generative audio modeling has been fragmented into specialized tasks such as text-to-speech (TTS), text- to-music (TTM), and text-ta (TTA) specialized models require reference audio for timbre cloning and strict phoneme alignment, whereas TTA models generate unstructured textures from open-ended captions.
Approach:	They propose a unified flow-matching framework capable of synthesizing speech, music, sound effects . they propose 'token injection mechanism' that projects unstructured environmental sounds into structured temporal latent space .
Outcome:	The proposed framework achieves state-of-the-art performance in instruction-based TTS and TTM while maintaining competitive fidelity in TTA.

Copied to clipboard

Zhiting Hu, Haoran Shi, Bowen Tan, Wentao Wang, Zichao Yang, Tiancheng Zhao, Junxian He, Lianhui Qin, Di Wang, Xuezhe Ma, Zhengzhong Liu, Xiaodan Liang, Wanrong Zhu, Devendra Sachan, Eric Xing

Collaboration of Fusion and Independence: Hypercomplex-driven Robust Multi-Modal Knowledge Graph Completion (2026.acl-long)

Challenge:	Texar is an open-source text generation toolkit that supports a broad set of text generation tasks.
Approach:	They introduce Texar, an open-source text generation toolkit that supports text generation tasks.
Outcome:	Texar supports machine translation, summarization, dialog, content manipulation, and more.

Copied to clipboard

Zhiqiang Liu, Yichi Zhang, Mengshu Sun, Lei Liang, Wen Zhang

HELENE: Hessian Layer-wise Clipping and Gradient Annealing for Accelerating Fine-tuning LLM with Zeroth-order Optimization (2025.emnlp-main)

Challenge:	Existing multi-modal knowledge graphs lack modality-specific information and are limited in their ability to capture nuanced semantic interplay between modalities.
Approach:	They propose a multi-modal knowledge graph completion method which integrates both paradigms . they use a fine-grained Entity Representation Factorization module and a Robust Relation-aware Modality Fusion module to obtain robust representations for three independent modalities and one fused modality.
Outcome:	The proposed method achieves coexistence and collaboration of fused and independent modality representations while maintaining modality-specific information.

Copied to clipboard

Huaqin Zhao, Jiaxi Li, Yi Pan, Shizhe Liang, Xiaofeng Yang, Fei Dou, Tianming Liu, Jin Lu

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing (2026.acl-industry)

Challenge:	Large language models (LLMs) face memory challenges due to the high cost of backpropagation.
Approach:	They propose a zeroth-order (ZO) optimization that matches memory usage to inference . they propose scalable and memory-efficient zeroth order (ZE) optimizer that integrates annealed A-GNB gradients with diagonal Hessian estimation and layer-wise clipping as a second-order pre-conditioner.
Outcome:	The proposed algorithm outperforms state-of-the-art methods with an average speedup of 20 over MeZO on RoBERTa-large and OPT-1.3B.

Copied to clipboard

Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Zirui Tang, Boyu Niu, Yuanhong Zheng, Dongsheng Ma, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Fangdong Wang, Jingzhou Chen, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, RuiLiang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Dechen Lin, null Shenguanlin, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He

AdaV: Adaptive Text-visual Redirection for Vision-Language Models (2025.findings-acl)

Challenge:	Document images are characterized by higher resolutions, denser content, and more complex structural layouts.
Approach:	They propose a 1.2B-parameter document parsing vision-language model that decouples layout analysis from local content recognition.
Outcome:	The proposed model surpasses general-purpose and domain-specific models on multiple benchmarks while maintaining significantly lower computational overhead.

Copied to clipboard

Jiayi Han, Liang Du, Yiwen Wu, Guanming Liang, Xiangguo Zhou, Weibo Zheng, Donghong Han, Zixun Sun

Hyperspherical Multi-Prototype with Optimal Transport for Event Argument Extraction (2024.acl-long)

Challenge:	Vision-language models often generate excessive visual tokens, leading to poor performance . a novel training-free visual token pruning method is proposed to improve performance despite the computational cost associated with VLMs.
Approach:	They propose a training-free visual token pruning method that reduces biased token pruning . they plan to open-source the code upon publication .
Outcome:	The proposed method reduces biased token pruning and enhances model robustness with limited visual token budget.

Copied to clipboard

Guangjun Zhang, Hu Zhang, YuJie Wang, Ru Li, Hongye Tan, Jiye Liang

GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning (2021.findings-acl)

Challenge:	Event Argument Extraction (EAE) aims to extract arguments for specified events from a text . previous work focused on long-distance dependencies of arguments, modeling co-occurrence relationships .
Approach:	They propose a model that takes inductive biases as targets to locate prototypes . they set multiple prototypes to represent each role to capture intra-class differences .
Outcome:	The proposed model achieves state-of-the-art on the RAMS and WikiEvents datasets.

Copied to clipboard

Jiaqi Chen, Jianheng Tang, Jinghui Qin, Xiaodan Liang, Lingbo Liu, Eric Xing, Liang Lin

Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm (2024.findings-acl)

Challenge:	Existing methods to solve geometric problems are dependent on handcraft rules and limited on small-scale datasets.
Approach:	They propose a Geometric Question Answering dataset with 5,010 geometric problems with corresponding annotated programs to illustrate the solving process.
Outcome:	The proposed method is significantly lower than human performance on the proposed dataset than on a publicly available dataset.

Copied to clipboard

Yuanzhen Xie, Xinzhou Jin, Tao Xie, Matrixmxlin Matrixmxlin, Liang Chen, Chenyun Yu, Cheng Lei, Chengxiang Zhuo, Bo Hu, Zang Li

SCOP: Evaluating the Comprehension Process of Large Language Models from a Cognitive View (2025.acl-long)

Challenge:	In-context learning of large-language models has achieved remarkable success in the field of natural language processing . however, the single-step chain-of-thought prompting approach faces challenges such as attention diffusion and inadequate performance in complex tasks like text-to-SQL.
Approach:	They propose a workflow paradigm method to enhance the attention and problem-solving scope of large-language models through decomposition.
Outcome:	The proposed method outperforms existing methods on three datasets and improves the upper limit of LLM-based approaches.

Copied to clipboard

Yongjie Xiao, Hongru Liang, Peixin Qin, Yao Zhang, Wenqiang Lei

Emphasising Structured Information: Integrating Abstract Meaning Representation into LLMs for Enhanced Open-Domain Dialogue Evaluation (2025.findings-emnlp)

Challenge:	despite the potential of large language models, it is difficult to fully count on them in real-world scenarios.
Approach:	They propose to examine how LLMs perform during the comprehension process from a cognitive perspective.
Outcome:	The proposed model analyzes how LLMs perform during the comprehension process from a cognitive perspective.

Copied to clipboard

Bohao Yang, Kun Zhao, Dong Liu, Chen Tang, Liang Zhan, Chenghua Lin

PsyScam: A Benchmark for Psychological Techniques in Real-World Scams (2025.findings-emnlp)

Challenge:	Existing evaluation metrics struggle to evaluate adversarial negative examples . existing metrics struggle in handling adversarials, resulting in low correlations with human judgments.
Approach:	They propose a framework that integrates AMR and domain-specific language models for automatic open-domain dialogue evaluation.
Outcome:	The proposed evaluation framework achieves strong correlations with human judgments across multiple datasets.

Copied to clipboard

Shang Ma, Tianyi Ma, Jiahao Liu, Wei Song, Zhenkai Liang, Xusheng Xiao, Yanfang Ye

Challenge:	PTs are employed by scammers to manipulate victims and cause lasting psychological trauma.
Approach:	They propose a benchmark to capture the PTs employed in real-worldscam reports and investigate how LLMs can be utilized to generate variants of scams based on the pts and the contexts provided by thesescams.
Outcome:	The proposed model can generate variants of scams based on the PTs employed in real-world scam reports and the contexts provided by these scams.

Generalizing Word Embeddings using Bag of Subwords (D18-1)

Copied to clipboard

Jinman Zhao, Sidharth Mudgal, Yingyu Liang

TransBench: Breaking Barriers for Transferable Graphical User Interface Agents in Dynamic Digital Environments (2025.findings-acl)

Challenge:	Existing word embeddings techniques have a fixed vocabulary, i.e., they can only provide vectors over a finite set of common words that appear frequently in a given corpus.
Approach:	They propose a subword-level word vector generation model that views words as bags of character n-grams and provides good vectors for rare or unseen words.
Outcome:	The proposed model performs state-of-the-art in English word similarity task and in joint prediction of part-of speech tag and morphosyntactic attributes in 23 languages.

Copied to clipboard

Yuheng Lu, Qian Yu, Hongru Wang, Zeming Liu, Wei Su, Yanping Liu, Yuhang Guo, Maocheng Liang, Yunhong Wang, Haifeng Wang

Challenge:	Existing GUI agents struggle to adapt to dynamic and interconnected nature of real-world digital environments, authors show .
Approach:	They propose a benchmark to evaluate the transferability of GUI agents across three key dimensions . transBench includes 15 app categories with diverse functionalities .
Outcome:	The proposed benchmark shows that existing GUI agents struggle to adapt to dynamic, interconnected environments.

TMFN: A Target-oriented Multi-grained Fusion Network for End-to-end Aspect-based Multimodal Sentiment Analysis (2024.lrec-main)

Copied to clipboard

Di Wang, Yuzheng He, Xiao Liang, Yumin Tian, Shaofeng Li, Lin Zhao

To Judge or Not to Judge: Can Large Language Models Leverage the Dispute Focus in Legal Judgment? (2026.acl-long)

Challenge:	Existing methods for multimodal aspect-based sentiment analysis focus on fusing image regional information and textual words.
Approach:	They propose a multimodal aspect-based sentiment analysis method that integrates regional and global image information with global image data.
Outcome:	Experiments show that the proposed method outperforms state-of-the-art methods on two benchmark datasets.

Copied to clipboard

Luoming Hu, Liang Yang, Jingjie Zeng, Zijie Xing

A Multi-persona Framework for Argument Quality Assessment (2025.acl-long)

Challenge:	Existing research on large language models for legal judgment prediction fails to address the complexity of civil judicial cases.
Approach:	They propose a framework that leverages the dispute focus to guide LLMs through a structured, judge-like cognitive workflow.
Outcome:	The proposed framework can guide LLMs through a structured, judge-like cognitive workflow.

Copied to clipboard

Bojun Jin, Jianzhu Bao, Yufang Hou, Yang Sun, Yice Zhang, Huajie Wang, Bin Liang, Ruifeng Xu

Challenge:	Existing methods for argument quality assessment do not consider multi-perspective evaluation due to subjective nature of arguments.
Approach:	They propose a multi-persona framework for argument quality assessment that simulates diverse evaluator perspectives through large language models.
Outcome:	The proposed framework outperforms baselines while providing comprehensive multi-perspective rationales on IBM-Rank-30k and IBM-ArgQ-5.3kArgs datasets.

MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models (2025.coling-main)

Copied to clipboard

Zihao Wei, Jingcheng Deng, Liang Pang, Hanxing Ding, Huawei Shen, Xueqi Cheng

Just Like a Human Would, Direct Access to Sarcasm Augmented with Potential Result and Reaction (2023.acl-long)

Challenge:	Existing studies on knowledge editing focus on monolingual scenarios, neglecting the complexities presented by multilingual contexts and multi-hop reasoning.
Approach:	They propose a benchmark to evaluate the adaptability of multilingual knowledge editing methods.
Outcome:	The proposed benchmark evaluates the adaptability of multilingual knowledge editing methods across five languages.

Copied to clipboard

Changrong Min, Ximing Li, Liang Yang, Zhilin Wang, Bo Xu, Hongfei Lin

Primacy Effect of ChatGPT (2023.emnlp-main)

Challenge:	sarcasm is a form of irony conveying mockery and contempt . social media has become increasingly popular for identifying sarcasm .
Approach:	They develop a method to detect sarcasm from social media using augmented potentials.
Outcome:	The proposed method outperforms baselines on benchmark datasets.

Copied to clipboard

Yiwei Wang, Yujun Cai, Muhao Chen, Yuxuan Liang, Bryan Hooi

ChemReason-Bench: Benchmarking Large Language Models for Procedural Reasoning in Experimental Chemistry (2026.acl-long)

Challenge:	Existing machine learning models may lead to poor performance in discriminative natural language understanding tasks.
Approach:	They propose to use ChatGPT to query large amounts of human-written text to find the answer to a question.
Outcome:	The proposed model has a high chance to select labels at earlier positions as the answer.

Copied to clipboard

Jinwei Zhang, Xucheng Liang, Yu Zhang, Ruijie Yu, Xiaokang Yang, Yaohui Jin, Yanyan Xu

EXPLAIN: Enhancing Retrieval-Augmented Generation with Entity Summary (2025.acl-industry)

Challenge:	Experimental protocols in organic synthesis specify not only the intended transformation, but also an executable sequence of operations and conditions.
Approach:	They propose a human-validated benchmark for verifiable experimental procedure reasoning . they instantiate 7306 benchmark tasks across six complementary formats .
Outcome:	The proposed benchmarks show that the evaluations are less diagnostic of procedure-level decision making.

Copied to clipboard

Yaozhen Liang, Xiao Liu, Jiajun Yu, Zhouhua Fang, Qunsheng Zou, Linghan Zheng, Yong Li, Zhiwei Liu, Haishuai Wang

Beyond Memorization: The Challenge of Random Memory Access in Language Models (2024.acl-long)

Challenge:	Existing document question answering methods reduce inference costs and input tokens.
Approach:	They propose a retrieval-augmented generation method that automatically extracts useful entities and generates summaries from documents.
Outcome:	The proposed method surpasses baseline retrieval-augmented generation (RAG) and long-context question answering (LC) methods achieve higher accuracy by processing entire documents, but at the cost of increased computational Corresponding authors.

Copied to clipboard

Tongyao Zhu, Qian Liu, Liang Pang, Zhengbao Jiang, Min-Yen Kan, Min Lin

CSMCIR: CoT-Enhanced Symmetric Alignment with Memory Bank for Composed Image Retrieval (2026.findings-acl)

Challenge:	Recent advances in Language Models (LMs) have shown their effectiveness in knowledge-intensive tasks.
Approach:	They investigate whether a generative language model is able to access its memory sequentially or randomly.
Outcome:	The proposed LMs are able to access memory sequentially or randomly.

Copied to clipboard

Zhipeng Qian, Zihan Liang, Yufei Ma, Ben Chen, Huangyu Dai, Yiwei Ma, Jiayi Ji, Chenyi Lei, Han Li, Xiaoshuai Sun

MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models (2025.findings-acl)

Challenge:	Existing approaches to search for images using single-modality are limited by representation space fragmentation.
Approach:	They propose a unified representation framework that achieves efficient query-target alignment . they introduce a multi-level Chain-of-Thought prompting strategy that guides MLMs to generate discriminative, semantically compatible captions for target images .
Outcome:	The proposed framework achieves efficient query-target alignment through synergistic components.

Copied to clipboard

Boyang Xue, Hongru Wang, Rui Wang, Sheng Wang, Zezhong Wang, Yiming Du, Bin Liang, Wenxuan Zhang, Kam-Fai Wong

Towards Better Document-level Relation Extraction via Iterative Inference (2022.emnlp-main)

Challenge:	Existing studies on LLM confidence estimations in languages other than English have been limited to English.
Approach:	They propose to use question-related language to prompt LLMs to assess their confidence in large language models.
Outcome:	The proposed model improves on question-related language prompts for LS tasks, while English exhibits notable linguistic dominance in confidence estimations.

Copied to clipboard

Liang Zhang, Jinsong Su, Yidong Chen, Zhongjian Miao, Min Zijun, Qingguo Hu, Xiaodong Shi

Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors (2026.acl-long)

Challenge:	Existing methods only consider feature information of entity pairs, but our model exploits both feature information and previous predictions of entity pair.
Approach:	They propose a document-level relation extraction model with iterative inference to extract relations between entities from raw texts.
Outcome:	The proposed model outperforms existing methods on three commonly-used datasets.

Copied to clipboard

Zhiwei Zhang, Fei Zhao, Rui Wang, Zezhong Wang, Bin Liang, Jiakang Wang, Yao Hu, Shaosheng Cao, Kam-Fai Wong

SINCon: Mitigate LLM-Generated Malicious Message Injection Attack for Rumor Detection (2025.acl-long)

Challenge:	Large language models (LLMs) can call tools effectively, but they remain brittle in multi-turn execution.
Approach:	They propose a framework that converts execution errors into on-policy corrective supervision within the RL training loop.
Outcome:	The proposed framework improves the error recovery rate of Qwen3-8B by 5.7% absolute and overall accuracy by 4.0% on BFCL v4 Multi-Turn.

Copied to clipboard

Mingqing Zhang, Qiang Liu, Xiang Tao, Shu Wu, Liang Wang

Enhancing Lexical Relation Mining with Structured Sememe Knowledge (2026.acl-long)

Challenge:	Existing methods define important nodes as important and target them for attacks if the model treats nodes’ predictive influence more uniformly . Existing approaches target high predictive influence nodes but are vulnerable to malicious message injection attacks.
Approach:	They propose a defense mechanism that encourages the model to learn graph representations where nodes with varying importance have a more uniform influence on predictions.
Outcome:	Extensive experiments on the Twitter and Weibo datasets show that similarizing the predictive Influence of nodes with Contrastive Learning significantly enhances resistance against LLM-driven message injection attacks.

Copied to clipboard

Hansi Wang, Qiliang Liang, Yue Wang, Yang Liu

Dynamic Feature Fusion for Sign Language Translation Using HyperNetworks (2025.findings-naacl)

Challenge:	Existing top-performing methods for Lexical Relation Mining rely on pre-trained language models yet fail to distinguish nuanced lexical relations.
Approach:	They propose a framework to leverage structured sememe knowledge to enhance LRC and LE.
Outcome:	The proposed method outperforms existing methods on benchmarks and outperformed the LLMs.

Copied to clipboard

Ruiquan Zhang, Rui Zhao, Zhicong Wu, Liang Zhang, Haoqi Zhang, Yidong Chen

Infinity-Parser: Layout-Aware Reinforcement Learning with High-quality Document Parsing Dataset (2026.findings-acl)

Challenge:	Using RGB and keypoint streams, sign language translation is highly dependent on the brain's ability to process color, shape, and motion simultaneously.
Approach:	They propose a hypernetwork-based fusion method that extracts salient features from RGB and keypoint streams and introduces self-distillation and SST contrastive learning to maintain feature advantages while aligning the global semantic space.
Outcome:	The proposed method achieves state-of-the-art performance on two public sign language datasets, reducing model parameters by about two-thirds.

Copied to clipboard

Baode Wang, Biao Wu, Weizhen Li, Meng Fang, Zuming Huang, Jun Huang, Yanjie Liang, Haozhe Wang, Ling Chen, Wei Chu, Yuan Qi

A Multi-Format Transfer Learning Model for Event Argument Extraction via Variational Information Bottleneck (2022.coling-1)

Challenge:	Existing supervised fine-tuning methods struggle to generalize across document types, leading to poor performance.
Approach:	They propose layoutRL, a reinforcement learning framework that optimizes layout understanding through composite rewards integrating normalized edit distance, paragraph count accuracy, and reading order preservation.
Outcome:	The proposed model outperforms specialized document parsing systems and general-purpose vision-language models on a broad range of document types, languages, and structural complexities.

Copied to clipboard

Jie Zhou, Qi Zhang, Qin Chen, Qi Zhang, Liang He, Xuanjing Huang

Cocktail: A Comprehensive Information Retrieval Benchmark with LLM-Generated Documents Integration (2024.findings-acl)

Challenge:	Event argument extraction (EAE) aims to extract arguments with given roles from texts.
Approach:	They propose a multi-format transfer learning model with variational information bottleneck to learn from existing datasets.
Outcome:	The proposed model improves on three benchmark datasets and obtains state-of-the-art performance on EAE.

Copied to clipboard

Sunhao Dai, Weihao Liu, Yuqi Zhou, Liang Pang, Rongju Ruan, Gang Wang, Zhenhua Dong, Jun Xu, Ji-Rong Wen

mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding (2024.findings-emnlp)

Challenge:	Large Language Models (LLMs) have led to an influx of AI-generated content on the internet, transforming corpus of Information Retrieval (IR) systems from human-written to a coexistence with LLM-generated contents.
Approach:	They propose a benchmark named Cocktail that compares IR models with LLMs to find relevant documents and passages from a corpus.
Outcome:	The proposed benchmark aims to evaluate IR models in the mixed-sourced data landscape of the LLM era.

Copied to clipboard

Anwen Hu, Haiyang Xu, Jiabo Ye, Ming Yan, Liang Zhang, Bo Zhang, Ji Zhang, Qin Jin, Fei Huang, Jingren Zhou

A Self-Attentive Model with Gate Mechanism for Spoken Language Understanding (D18-1)

Challenge:	Existing Multimodal Large Language Models lack general structure understanding abilities for text-rich document images.
Approach:	They propose to use unified structure learning to boost the performance of MLLMs by encoding structure information into text-rich images.
Outcome:	The proposed model achieves state-of-the-art on 10 visual document understanding benchmarks.

Copied to clipboard

Changliang Li, Liang Li, Ji Qi

Personalized Text Generation with Contrastive Activation Steering (2025.acl-long)

Challenge:	Spoken language understanding (SLU) involves intent determination and slot filling . existing joint learning methods only consider joint learning by sharing parameters on surface level rather than semantic level.
Approach:	They propose a self-attentive model to fully utilize the semantic correlation between slot and intent.
Outcome:	The proposed model outperforms existing methods in both intent detection and slot filling tasks on ATIS benchmarks.

Copied to clipboard

Jinghao Zhang, Yuting Liu, Wenjie Wang, Qiang Liu, Shu Wu, Liang Wang, Tat-Seng Chua

VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment (2024.emnlp-main)

Challenge:	Existing approaches to personalized text generation rely on retrieval-augmented generation and parameter-efficient fine-tuning.
Approach:	They propose a training-free framework that disentangles and represents personalized writing style as a vector in LLM’s activation-space.
Outcome:	The proposed framework achieves 8% relative improvement in personalized generation while reducing storage requirements by 1700 over PEFT method.

Copied to clipboard

Lei Li, Zhihui Xie, Mukai Li, Shunian Chen, Peiyi Wang, Liang Chen, Yazheng Yang, Benyou Wang, Lingpeng Kong, Qi Liu

mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding (2025.acl-long)

Challenge:	Large vision-language models (LVLMs) are evolving rapidly and require data with human supervision to achieve better alignment.
Approach:	They introduce VLFeedback, the first large-scale vision-language feedback dataset . they train Silkie, an LVLM fine-tuned via direct preference optimization .
Outcome:	The proposed model outperforms its base model in helpfulness, visual faithfulness, and safety metrics and exhibits enhanced resilience against red-teaming attacks.

Copied to clipboard

Anwen Hu, Haiyang Xu, Liang Zhang, Jiabo Ye, Ming Yan, Ji Zhang, Qin Jin, Fei Huang, Jingren Zhou

Graph Reasoning Paradigm: Structured and Symbolic Reasoning with Topology-Aware Reinforcement Learning for Large Language Models (2026.acl-long)

Challenge:	Multimodal Large Language Models (MLLMs) have improved document understanding performance but generate thousands of visual tokens for a single document image, leading to excessive GPU memory and slower inference times.
Approach:	They propose a high-resolution document compression module to generate 324 tokens for a single document image.
Outcome:	The proposed module reduces first token latency by more than 50% and improves document comprehension performance.

Copied to clipboard

Runxuan Liu, Xianhao Ou, Xinyan Ma, Jiyuan Wang, Jiafeng Liang, Jiaqi Li, Tao He, Zheng Chu, Rongchuan Mu, Zekun Wang, Baoxin Wang, Dayong Wu, Ming Liu, Shijin Wang, Guoping Hu, Bing Qin

Towards Debiasing Sentence Representations (2020.acl-main)

Challenge:	Existing methods for long chain-of-thought (LCoT) are coarse-grained, reward hacking, and poor generalization.
Approach:	They propose a Long Chain-of-Thought (LCoT) model that integrates reinforcement learning with verifiable rewards with a process-aware verification approach.
Outcome:	The proposed model improves reasoning and code generation tasks while reducing the cost of training and performance bottlenecks.

Copied to clipboard

Paul Pu Liang, Irene Mengze Li, Emily Zheng, Yao Chong Lim, Ruslan Salakhutdinov, Louis-Philippe Morency

Fact-Tree Reasoning for N-ary Question Answering over Knowledge Graphs (2022.findings-acl)

Challenge:	Recent work has shown word-level embeddings reflect and propagate social biases present in training corpora.
Approach:	They propose a method to debias word embeddings to reduce biases at sentence level . they hope their work will inspire future research on characterizing and removing biase .
Outcome:	The proposed method reduces biases and preserves performance on downstream tasks such as sentiment analysis and natural language understanding.

Copied to clipboard

Yao Zhang, Peiyao Li, Hongru Liang, Adam Jatowt, Zhenglu Yang

Revisiting Token Dropping Strategy in Efficient BERT Pretraining (2023.acl-long)

Challenge:	Current Question Answering over Knowledge Graphs (KGQA) tasks focus on binary facts, but neglect n-ary facts.
Approach:	They propose a new fact-tree reasoning framework that transforms the question into a fact tree and performs iterative fact reasoning on the fact tree to infer the correct answer.
Outcome:	The proposed framework performs iterative fact reasoning on the fact tree to infer the correct answer.

Copied to clipboard

Qihuang Zhong, Liang Ding, Juhua Liu, Xuebo Liu, Min Zhang, Bo Du, Dacheng Tao

ALICE: Active Learning with Contrastive Natural Language Explanations (2020.emnlp-main)

Challenge:	Token dropping is a recently-proposed strategy to speed up the pretraining of masked language models, such as BERT.
Approach:	They propose a semantic-consistent learning method to improve token dropping by skipping the computation of a subset of input tokens at several middle layers.
Outcome:	The proposed method achieves consistent and significant performance gains across all tasks and model sizes.

Copied to clipboard

Weixin Liang, James Zou, Zhou Yu

Learning Representations from Imperfect Time Series Data via Tensor Rank Regularization (P19-1)

Challenge:	Annotating a large dataset with annotations is costly and infeasible.
Approach:	They propose an expert-in-the-loop training framework that utilizes contrastive natural language explanations to improve data efficiency in learning.
Outcome:	The proposed framework outperforms baseline models trained with 40-100% more training data on bird species classification and social relationship classification tasks.

Copied to clipboard

Paul Pu Liang, Zhun Liu, Yao-Hung Hubert Tsai, Qibin Zhao, Ruslan Salakhutdinov, Louis-Philippe Morency

PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowcharts (2025.findings-acl)

Challenge:	Existing methods to regularize multimodal data are imperfect due to imperfect modalities, missing entries or noise corruption.
Approach:	They propose a method to regularize multimodal data by tensor rank minimization . they use correlations between time and modalities to generate low-rank tenses .
Outcome:	The proposed model achieves good results across various levels of imperfection.

Copied to clipboard

Ming Zhang, Yuhui Wang, Yujiong Shen, Tingyi Yang, Changhao Jiang, Yilong Wu, Shihan Dou, Qinhao Chen, Zhiheng Xi, Zhihao Zhang, Yi Dong, Zhen Wang, Zhihui Fei, Mingyang Wan, Tao Liang, Guojun Ma, Qi Zhang, Tao Gui, Xuanjing Huang

Flooding-X: Improving BERT’s Resistance to Adversarial Attacks via Loss-Restricted Fine-Tuning (2022.acl-long)

Challenge:	Large Language Models (LLMs) have shown remarkable progress in dialogue and reasoning, but they struggle to solve strictly constrained dialogue tasks.
Approach:	They construct a dataset that contains 12,705 high-quality Chinese dialogue instructions from 440 flowcharts containing 5,055 process nodes.
Outcome:	The proposed model outperforms GPT-4o models on backward transitions and outperformed GPT-42 models on the same dataset.

Copied to clipboard

Qin Liu, Rui Zheng, Bao Rong, Jingyi Liu, ZhiHua Liu, Zhanzhan Cheng, Liang Qiao, Tao Gui, Qi Zhang, Xuanjing Huang

SceMQA: A Scientific College Entrance Level Multimodal Question Answering Benchmark (2024.acl-short)

Challenge:	Existing approaches to generating adversarial perturbations scale up the cost of training computational complexity by the number of gradient steps it takes to obtain the adversarials.
Approach:	They propose a flood method which aims at better generalization and a criterion to bring hyper-parameter-dependent flooding into effect with a narrowed-down search space by measuring how the gradient steps taken within one epoch affect the loss of each batch.
Outcome:	The proposed method improves BERT’s resistance to textual adversarial attacks by a large margin and achieves state-of-the-art robust accuracy on various text classification and GLUE tasks.

Copied to clipboard

Zhenwen Liang, Kehan Guo, Gang Liu, Taicheng Guo, Yujun Zhou, Tianyu Yang, Jiajun Jiao, Renjie Pi, Jipeng Zhang, Xiangliang Zhang

A Multi-Agent Framework with Automated Decision Rule Optimization for Cross-Domain Misinformation Detection (2025.emnlp-main)

Challenge:	SceMQA focuses on core science subjects including Mathematics, Physics, Chemistry, and Biology.
Approach:	They propose to use SceMQA to evaluate multimodal question answering at college entrance level.
Outcome:	The proposed model provides specific knowledge points for each problem and detailed explanations for each answer.

Copied to clipboard

Hui Li, Ante Wang, Kunquan Li, Zhihao Wang, Liang Zhang, Delai Qiu, Qingsong Liu, Jinsong Su

Contrastive Token Learning with Similarity Decay for Repetition Suppression in Machine Translation (2024.findings-emnlp)

Challenge:	Existing methods for misinformation detection are limited by domain knowledge and expert experience.
Approach:	They propose a Multi-Agent Framework for cross-domain misinformation detection with Automated Decision Rule Optimization (MARO) they first employ multiple expert agents to analyze target-domain news, then introduce a question-reflection mechanism that guides expert agents for higher-quality analysis.
Outcome:	The proposed framework improves on a common dataset and shows that iteratively improves over existing methods.

Copied to clipboard

Huangyu Dai, Ben Chen, Kaidi Chen, Ying Han, Zihan Liang, Wen Jiang

QSpell 250K: A Large-Scale, Practical Dataset for Chinese Search Query Spell Correction (2025.naacl-industry)

Challenge:	Neural machine translation (NMT) is pivotal for crosslingual conversation and trade . traditional solutions that penalize text redundancy or token reoccurrence have shown limited efficacy .
Approach:	They propose an algorithm that modulates suppression of tokens dynamically, informed by attention weights and inter-token distances.
Outcome:	The proposed algorithm outperforms existing methods in precision and generalizability.

Copied to clipboard

Dezhi Ye, Haomei Jia, Junwei Hu, Tian Bowen, Jie Liu, Haijin Liang, Jin Ma, Wenmin Wang

From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning (2026.findings-acl)

Challenge:	Chinese Search Query Spell Correction is a task designed to identify and correct typographical errors within queries.
Approach:	They propose a large-scale benchmark specifically developed for Chinese Query Spell Correction.
Outcome:	The proposed benchmark covers a broad range of topics, including formal entities, everyday colloquialisms and idiomatic expressions.

Copied to clipboard

Xiaoyu Xu, Minxin Du, Zitong LI, Zi Liang, Zhibiao Guo, Zhang Shiyu, Peizhao Hu, Qingqing Ye, Haibo Hu

Challenge:	Currently, the evaluation of unlearning is limited due to the lack of granularity in the model.
Approach:	They propose a framework for synthesizing high-quality forget sets that exploits the target model per se to elicit data that matches its internal knowledge distribution through seed-guided and adversarial prompting.
Outcome:	The proposed framework achieves a superior balance of relevance, diversity, and efficiency across benchmarks.

CR-LLM: A Dataset and Optimization for Concept Reasoning of Large Language Models (2024.findings-acl)

Copied to clipboard

Nianqi Li, Jingping Liu, Sihang Jiang, Haiyun Jiang, Yanghua Xiao, Jiaqing Liang, Zujie Liang, Feng Wei, Jinglei Chen, Zhenghong Hao, Bing Han

AutoScraper: A Progressive Understanding Web Agent for Web Scraper Generation (2024.emnlp-main)

Challenge:	Existing concept reasoning related datasets suffer from modeledge leakage and context leakage.
Approach:	They propose a concept reasoning for large language models with modeledge leakage prevention and context leakage preventive methods to improve the models' conceptual reasoning abilities.
Outcome:	The proposed method significantly improves the existing models and reasoning methods, achieving a 7% increase in accuracy compared to CoT and showing better granularity.

Copied to clipboard

Wenhao Huang, Zhouhong Gu, Chenghao Peng, Jiaqing Liang, Zhixu Li, Yanghua Xiao, Liqian Wen, Zulong Chen

Challenge:	Existing methods for web scraping suffer from limited adaptability and scalability when faced with a new website.
Approach:	They propose a framework that generates web scrapers with large language models and a new executability metric to measure the performance of web scraper generation tasks.
Outcome:	The proposed framework can handle diverse web environments more efficiently.

Low-Hallucination and Efficient Coreference Resolution with LLMs (2025.findings-emnlp)

Copied to clipboard

Yujian Gan, Yuan Liang, Jinxia Xie, Yanni Lin, Juntao Yu, Massimo Poesio

Beyond Semantic Similarity: Appraisal-Guided Chain-of-Thought Reasoning and Retrieval for Multimodal Emotional Support Conversations (2026.findings-acl)

Challenge:	Large Language Models have shown promising results in coreference resolution, but they face a critical issue: hallucinations.
Approach:	They propose a low-hallucination and efficient solution to the problem of hallucinations . they propose efficient constrained decoding for coreference resolution .
Outcome:	The proposed approach achieves better performance on the English OntoNotes development set.

Copied to clipboard

Yuqi Chu, Lizi Liao, Jinggui Liang, Boyang Li, Richang Hong

Direct Simultaneous Speech-to-Text Translation Assisted by Synchronized Streaming ASR (2021.findings-acl)

Challenge:	Existing retrieval-augmented generation paradigms rely on semantic similarity to retrieve historical dialogues that are surface analogous but therapeutically incongruent.
Approach:	They propose to use appraisal-guided reasoning chains to generate appraisal-based reasoning chains and apply a dual-signal verification mechanism to verify and correct them.
Outcome:	Extensive experiments on two ESC benchmarks show that the proposed model significantly outperforms state-of-the-art models.

Copied to clipboard

Junkun Chen, Mingbo Ma, Renjie Zheng, Liang Huang

Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models (2025.findings-emnlp)

Challenge:	Existing approaches to simultaneous speech-to-text translation suffer from error propagation and extra latency.
Approach:	They propose a new paradigm for simultaneous speech-to-text translation using two separate decoders . they use multitask learning to jointly learn these two tasks with a shared encoder .
Outcome:	The proposed method achieves substantially better translation quality at similar levels of latency.

Copied to clipboard

Zonghao Ying, Deyue Zhang, Zonglei Jing, Yisong Xiao, Quanchen Zou, Aishan Liu, Siyuan Liang, Xiangzheng Zhang, Xianglong Liu, Dacheng Tao

Concept2Box: Joint Geometric Embeddings for Learning Two-View Knowledge Graphs (2023.findings-acl)

Challenge:	Existing methods for implementing multi-turn jailbreaks struggle to balance semantic coherence with attack effectiveness, resulting in benign semantic drift or ineffective detection evasion.
Approach:	They propose a framework that reformulates harmful queries into benign reasoning tasks and leverages LLMs’ strong reasoning capabilities to compromise safety alignment.
Outcome:	The proposed framework achieves state-of-the-art attack effectiveness in complex conversational scenarios, with average ASRs increasing by up to 96%.

Copied to clipboard

Zijie Huang, Daheng Wang, Binxuan Huang, Chenwei Zhang, Jingbo Shang, Yan Liang, Zhengyang Wang, Xian Li, Christos Faloutsos, Yizhou Sun, Wei Wang

Self-Supervised Prompt Optimization (2025.findings-emnlp)

Challenge:	Existing methods to embed knowledge graphs have ignored the fact that they contain two fundamentally different views: high-level ontology-view concepts and fine-grained instance-view entities.
Approach:	They propose a novel geometric representation that jointly embeds the two views of a KG using dual geometric representations.
Outcome:	Experiments on the public DBpedia KG and a newly-created industrial KG show the proposed method works well.

Copied to clipboard

Jinyu Xiang, Jiayi Zhang, Zhaoyang Yu, Xinbing Liang, Fengwei Teng, Jinhao Tu, Fashen Ren, Xiangru Tang, Sirui Hong, Chenglin Wu, Yuyu Luo

A Multilingual Dataset and Empirical Validation for the Mutual Reinforcement Effect in Information Extraction (2026.findings-acl)

Challenge:	Existing prompt optimization methods rely heavily on external references such as ground truth or by humans, limiting their applicability in real-world scenarios where such data is unavailable or costly to obtain.
Approach:	They propose a cost-efficient framework that discovers effective prompts for both closed and open-ended tasks without external reference.
Outcome:	The proposed framework outperforms state-of-the-art prompt optimization methods with significantly lower costs and fewer samples.

Copied to clipboard

Chengguang Gan, Sunbowen Lee, Qingyu Yin, Yunhao Liang, Xinyang He, Hanjun Wei, Younghun Lim, Shijian Wang, Hexiang Huang, QingHao Zhang, Shiwen Ni, Tatsunori Mori

On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise Tasks (2020.findings-emnlp)

Challenge:	Existing work on the Mutual Reinforcement Effect in information extraction has not been empirically validated . 76 percent of the 21 sub-datasets exhibit the Mutual Reforcement effect across languages .
Approach:	They propose a multilingual MRE mix dataset that integrates 21 sub-datasets covering English, Japanese, and Chinese.
Outcome:	The proposed framework reduces manual annotation effort while preserving structural requirements of MRE tasks.

Copied to clipboard

Stephen Mussmann, Robin Jia, Percy Liang

Beyond Screenshots: Evaluating VLMs’ Understanding of UI Animations (2026.findings-acl)

Challenge:	Recent datasets heuristically choose examples to ensure label balance . state-of-the-art models trained on QQP and WikiQA have only 2.4% average precision .
Approach:	They show that recent datasets heuristically choose examples to ensure label balance . they instead use active learning to retrieve uncertain points from a large pool of unlabeled utterance pairs .
Outcome:	The proposed model improves on QQP and WikiQA by using more informative negative examples.

Copied to clipboard

Chen Liang, Xirui Jiang, Naihao Deng, Eytan Adar, Anhong Guo

Challenge:	Recent studies of Vision Language Models (VLMs) for UI understanding have focused primarily on static screenshots, leaving it unclear how well these models handle dynamic UI animations.
Approach:	They evaluate UI animation models' ability to perceive animation effects and interpret animation meaning . they use motion, context, and perceptual cues to probe factors affecting VLM performance .
Outcome:	The proposed model can detect primitive motion, but its interpretation is inconsistent . the proposed model is based on 300 annotated UI animation videos .

LLM-based Conversational Recommendation Agents with Collaborative Verbalized Experience (2025.findings-emnlp)

Copied to clipboard

Yaochen Zhu, Harald Steck, Dawen Liang, Yinhan He, Nathan Kallus, Jundong Li

Think Beyond Words: Exploring Context-Relevant Visual Commonsense for Diverse Dialogue Generation (2022.findings-emnlp)

Challenge:	Large language models (LLMs) have demonstrated impressive zero-shot capabilities in conversational recommender systems (CRS).
Approach:	They propose LLM-based CRS-based LLMs with Collaborative Verbalized Experience to enhance historical conversations by sampling trajectories of LLM agents on historical queries and establishing verbalized experience banks .
Outcome:	The proposed system improves on existing approaches to enhancing historical conversations by leveraging trajectories and verbalized experiences from LLMs on historical queries and user feedback.

Copied to clipboard

Yiting Liu, Liang Li, Beichen Zhang, Qingming Huang

A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers (2020.acl-main)

Challenge:	Existing approaches to generate intelligent open-domain dialogue agents only consider auxiliary commonsense stored in pure text, ignoring grounding information from the external visual world.
Approach:	They propose a VIsual Commonsense enhanced dialogue generaTOR that exploits auxiliary commonsense from images related to context to generate coherent and informative responses.
Outcome:	The proposed method outperforms the latest competitive methods in terms of coherence and diversity on two public datasets.

Copied to clipboard

Shen-yun Miao, Chao-Chun Liang, Keh-Yih Su

KELE: Residual Knowledge Erasure for Enhanced Multi-hop Reasoning in Knowledge Editing (2025.findings-emnlp)

Challenge:	Existing MWP corpora are limited in language patterns and problem types . a new corpus of 2,305 MWps is proposed that is more diverse in terms of lexicon usage .
Approach:	They propose to use ASDiv to measure lexicon usage diversity of a given MWP corpus.
Outcome:	The proposed corpus covers more problem types and text patterns than existing corpora and reflects the true capability of solvers more faithfully.

Copied to clipboard

Mengqi Zhang, Bowen Fang, Qiang Liu, Xiaotian Ye, Shu Wu, Pengjie Ren, Zhumin Chen, Liang Wang

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models (2024.acl-long)

Challenge:	Existing knowledge editing techniques show limitations when applied to multi-hop reasoning . residual single-hop knowledge causes edited models to revert to original answers .
Approach:	They propose a knowledge editing method that incorporates a Knowledge Erasure mechanism for Large language model Editing (KELE) they propose an erasure function for residual knowledge and an injection function for new knowledge .
Outcome:	The proposed method significantly improves multi-hop reasoning capability of edited models.

Copied to clipboard

Damai Dai, Chengqi Deng, Chenggang Zhao, R.x. Xu, Huazuo Gao, Deli Chen, Jiashi Li, Wangding Zeng, Xingkai Yu, Y. Wu, Zhenda Xie, Y.k. Li, Panpan Huang, Fuli Luo, Chong Ruan, Zhifang Sui, Wenfeng Liang

Why Multi-Interest Fairness Matters: Hypergraph Contrastive Multi-Interest Learning for Fair Conversational Recommender System (2025.findings-acl)

Challenge:	Mixture-of-Experts (MoE) architectures face challenges in ensuring expert specialization . despite the promising performance, scaling language models to an extremely large scale is associated with exceedingly high computational costs.
Approach:	They propose an architecture that allows for ultimate expert specialization by segmenting experts into mN ones and activating mK from them.
Outcome:	The proposed architecture achieves comparable performance with GShard with 2B parameters and computation.

Copied to clipboard

Yongsen Zheng, Zongxuan Xie, Guohua Wang, Ziyao Liu, Liang Lin, Kwok-Yan Lam

InsLogicBench: An Argumentation Logic Grounded Benchmark for Complex Insurance Claims Adjudication (2026.acl-long)

Challenge:	Unfairness is a well-known challenge in Recommender Systems (RSs) some approaches have started to improve fairness in offline or static contexts, but it often exacerbates over time, leading to significant problems like the Matthew effect, filter bubbles, and echo chambers.
Approach:	They propose a framework to promote multi-interest diversity fairness in RSs by establishing diverse hypergraphs through contrastive learning.
Outcome:	The proposed framework achieves state-of-the-art performance while effectively alleviating unfairness in two CRS-based datasets.

Copied to clipboard

Jin Liu, Yunpeng Liu, Keyi Wang, Jie Shi, Xiao Xu, Wenkang Huang, Xingzhong Xu, Xin Liang, Yanghua Xiao

LLM-REDIAL: A Large-Scale Dataset for Conversational Recommender Systems Created from User Behaviors with LLMs (2024.findings-acl)

Challenge:	Existing benchmarks for insurance claims adjudication are limited to information retrieval or simple multiple-choice setups.
Approach:	They propose a benchmark that provides complete reasoning traces linking factual inputs, relevant policy clauses, and final verdicts.
Outcome:	The proposed benchmark shows that models often produce correct decisions but fail to provide precise justifications, highlighting a critical discrepancy between decision accuracy and logical reasoning capabilities.

Copied to clipboard

Tingting Liang, Chenxin Jin, Lingzhi Wang, Wenqi Fan, Congying Xia, Kai Chen, Yuyu Yin

Looking Beyond Text: Reducing Language Bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance (2025.emnlp-main)

Challenge:	Existing CRS datasets suffer from data inextensibility and semantic inconsistency .
Approach:	They introduce the LLM-REDIAL dataset to facilitate the research in CRS by leveraging large language models to generate high-quality dialogues.
Outcome:	The proposed dataset is the largest multi-domain CRS dataset which consists of 47.6k multi-turn dialogues with 482.6k utterances across 4 domains.

Copied to clipboard

Haozhe Zhao, Shuzheng Si, Liang Chen, Yichi Zhang, Maosong Sun, Baobao Chang, Minjia Zhang

Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning (2026.acl-long)

Challenge:	Large vision-language models (LVLMs) have been criticized for their language bias.
Approach:	They propose to use a dual-attention mechanism to construct separate attention for visual and text inputs to enhance integration of visual inputs across models.
Outcome:	Experiments show that the proposed model debiases LVLMs from their language bias, enhancing visual comprehension and reducing hallucinations without additional resources.

Copied to clipboard

Zekai Lin, Chao Xue, Di Liang, Xingsheng Han, Peiyang Liu, Xianjie Wu, Lei Jiang, Yu Lu, Bob Simons, Shuang Liang, Minlong Peng

AgentDropout: Dynamic Agent Elimination for Token-Efficient and High-Performance LLM-Based Multi-Agent Collaboration (2025.acl-long)

Challenge:	Recent approaches to fine-tuning of large language models suffer from task interference and catastrophic forgetting.
Approach:	They propose a fine-tuning framework that adapts isolation decisions based on online estimates of parameter importance.
Outcome:	The proposed framework reduces interference and forgetting while releasing outdated parameters to recover plasticity.

Copied to clipboard

Zhexuan Wang, Yutong Wang, Xuebo Liu, Liang Ding, Miao Zhang, Jie Liu, Min Zhang

Target-Guided Open-Domain Conversation (P19-1)

Challenge:	Existing methods for MAS suffer from high token consumption and inefficiency due to frequent generation and communication among multiple agents.
Approach:	They propose a multi-agent system based on large language models that identifies redundant agents and communication across different communication rounds by optimizing the adjacency matrices of the communication graphs and eliminates them to enhance both token efficiency and task performance.
Outcome:	The proposed method reduces prompt token consumption and completion token consumption by 18.4% and improves task performance by 1.14.

Copied to clipboard

Jianheng Tang, Tiancheng Zhao, Chenyan Xiong, Xiaodan Liang, Eric Xing, Zhiting Hu

DiaHalu: A Dialogue-level Hallucination Evaluation Benchmark for Large Language Models (2024.findings-emnlp)

Challenge:	a new study aims to improve opendomain chat systems by integrating goals and strategy into the system.
Approach:	They propose a structured approach that introduces coarse-grained keywords to control intended content of system responses and attains smooth conversation transition through turn-level supervised learning.
Outcome:	The proposed system produces meaningful and effective conversations significantly better than other approaches.

Copied to clipboard

Kedi Chen, Qin Chen, Jie Zhou, He Yishen, Liang He

Revisiting Catastrophic Forgetting in Large Language Model Tuning (2024.findings-emnlp)

Challenge:	Existing benchmarks for hallucination detection are intentionally generated by large language models (LLMs) however, many focus on factuality while ignoring faithfulness.
Approach:	They propose a dialogue-level hallucination evaluation benchmark for large language models . they integrate the topic into prompts and facilitate a dialog between two LLMs .
Outcome:	The proposed benchmark covers four common multi-turn dialogue domains and five hallucination subtypes, extended from factuality and faithfulness hallucines.

Copied to clipboard

Hongyu Li, Liang Ding, Meng Fang, Dacheng Tao

Retrieval Augmented Instruction Tuning for Open NER with Large Language Models (2025.coling-main)

Challenge:	Catastrophic Forgetting (CF) compromises the effectiveness of large language models during fine-tuning, yet the underlying causes of CF remain largely unexplored.
Approach:	They propose a method to flatten the model loss landscape to mitigate CF by flattening the loss landscape.
Outcome:	The proposed method complements existing anti-forgetting strategies, further enhancing the resistance of LLMs to CF.

Copied to clipboard

Tingyu Xie, Jian Zhang, Yan Zhang, Yuanyuan Liang, Qi Li, Hongwei Wang

Token-wise Curriculum Learning for Neural Machine Translation (2021.findings-emnlp)

Challenge:	Existing studies have focused on integrating large language models (LLMs) with information extraction (IE) however, the best approach to incorporate information with LLMs for IE remains an open question.
Approach:	They propose to use a Chinese IT dataset to perform RA-IT for IE . they use semantically similar examples from the training dataset as the context .
Outcome:	The proposed approach is evaluated in English and Chinese scenarios.

Copied to clipboard

Chen Liang, Haoming Jiang, Xiaodong Liu, Pengcheng He, Weizhu Chen, Jianfeng Gao, Tuo Zhao

DialogGen: Multi-modal Interactive Dialogue System with Multi-turn Text-Image Generation (2025.findings-naacl)

Challenge:	Existing curriculum learning approaches to Neural Machine Translation (NMT) require sampling sufficient amounts of “easy” samples from training data at the early stage of training.
Approach:	They propose a token-wise curriculum learning approach that creates sufficient amounts of easy samples from training data.
Outcome:	The proposed approach outperforms baselines on five language pairs on low-resource languages.

Copied to clipboard

Minbin Huang, Yanxin Long, Xinchi Deng, Ruihang Chu, Jiangfeng Xiong, Xiaodan Liang, Hong Cheng, Qinglin Lu, Wei Liu

PITA: Prompting Task Interaction for Argumentation Mining (2024.acl-long)

Challenge:	Text-to-image (T2I) generation models have advanced in recent years, but effective interaction with these models is challenging for average users due to the need for specialized prompt engineering knowledge and the inability to perform multi-turn image generation.
Approach:	They propose to use off-the-shelf MLLMs and T2I models to build a multi-modal interactive dialogue system (MIDS) that can generate correct output modalities and coherence of output images.
Outcome:	The proposed pipeline can generate correct output modalities and coherent multi-modal outputs compared with other state-of-the-art models.

Copied to clipboard

Yang Sun, Muyi Wang, Jianzhu Bao, Bin Liang, Xiaoyan Zhao, Caihua Yang, Min Yang, Ruifeng Xu

Text Classification

Challenge:	Argumentation mining (AM) aims to detect arguments and their inherent relations from textual compositions.
Approach:	They propose a method to model the inter-relationships among three subtasks within a generative framework.
Outcome:	The proposed method achieves state-of-the-art performance on two AM benchmarks.

Let’s Rectify Step by Step: Improving Aspect-based Sentiment Analysis with Diffusion Models (2024.lrec-main)

Copied to clipboard

Shunyu Liu, Jie Zhou, Qunxi Zhu, Qin Chen, Qingchun Bai, Jun Xiao, Liang He

Mapping natural language commands to web elements (D18-1)

Challenge:	Empirical evaluations conducted on eight benchmark datasets underscore the compelling advantages offered by DiffusionABSA when compared against robust baseline models.
Approach:	They propose a diffusion model which extracts aspects step by step and learns a denoising process that progressively restores them in a reverse manner.
Outcome:	Empirical evaluations on eight benchmark datasets underscore the compelling advantages offered by DiffusionABSA when compared against robust baseline models.

Copied to clipboard

Panupong Pasupat, Tian-Shun Jiang, Evan Liu, Kelvin Guu, Percy Liang

MemeReaCon: Probing Contextual Meme Understanding in Large Vision-Language Models (2025.emnlp-main)

Challenge:	a dataset of over 50,000 natural language commands captures various phenomena, including functional references, relational reasoning, and visual reasoning.
Approach:	They propose a task that requires the user to choose the correct element on a web page . they use a dataset of over 50,000 natural language commands to map these to web pages .
Outcome:	The proposed task can be viewed as a reference game based on a dataset of over 50,000 natural language commands .

Copied to clipboard

Zhengyi Zhao, Shubo Zhang, Yuxi Zhang, Yanxi Zhao, Yifan Zhang, Zezhong Wang, Huimin Wang, Yutian Zhao, Bin Liang, Yefeng Zheng, Binyang Li, Kam-Fai Wong, Xian Wu

AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarios (2025.naacl-long)

Challenge:	Current approaches focus on isolated meme analysis, either for harmful content detection or standalone interpretation, overlooking a fundamental challenge: the same meme can express different intents depending on its conversational context.
Approach:	They propose a benchmark to evaluate how large vision language models understand memes in their original context.
Outcome:	The proposed benchmark evaluates how large vision language models understand meme intent in their original context.

Copied to clipboard

Xinyi Mou, Jingcong Liang, Jiayu Lin, Xinnong Zhang, Xiawei Liu, Shiyue Yang, Rong Ye, Lei Chen, Haoyu Kuang, Xuanjing Huang, Zhongyu Wei

Linguistics & Cognitive NLP

Challenge:	Large language models are increasingly employed to empower autonomous agents to simulate human behavior.
Approach:	They propose to evaluate LLM-driven agents through multi-turn interactions using a bottom-up approach to create diverse social scenarios constructed from extensive scripts.
Outcome:	The proposed model evaluates LLM-driven agents through multi-turn interactions emphasizing goal completion and implicit reasoning.

Semantic XPath: Structured Agentic Memory Access for Conversational AI (2026.acl-demo)

Copied to clipboard

Yifan Simon Liu, Ruifan Wu, Liam Gallagher, Jiazhou Liang, Armin Toroghi, Scott Sanner

Thinking Before You Speak: A Proactive Test-time Scaling Approach (2025.findings-emnlp)

Challenge:	Early ConvAI agents rely on an in-context approach that appends the growing conversation history to the model input, but this approach scales poorly under context-window limits.
Approach:	They propose a tree-structured memory module to access and update structured conversational memory.
Outcome:	The proposed system improves over flat-RAG baselines while using only 9.1% of the tokens required by in-context memory.

Copied to clipboard

Cong Liu, Wenchang Chai, Hejun Wu, Yan Pan, Pengxu Wei, Liang Lin

THOR-MoE: Hierarchical Task-Guided and Context-Responsive Routing for Neural Machine Translation (2025.acl-long)

Challenge:	Large Language Models often exhibit deficiencies with complex reasoning tasks, such as maths, due to the discrepancy between human reasoning patterns and those presented in training data.
Approach:	They propose to insert insights between consecutive reasoning steps to bridge this gap by generating insights between the next reasoning steps.
Outcome:	Experiments on mathematical datasets confirm the effectiveness of the proposed reasoning framework on complex problems.

Copied to clipboard

Yunlong Liang, Fandong Meng, Jie Zhou

GenPilot: A Multi-Agent System for Test-Time Prompt Optimization in Image Generation (2025.findings-emnlp)

Challenge:	Existing sparse Mixture-of-Experts (MoE) solutions may lead to sub-optimal performance . thor-moe uses domain/linguistics-specific knowledge, but lacks context-responsive routing policies .
Approach:	They propose a sparse Mixture-of-Experts (MoE) solution which uses task knowledge of NMT into MoE and provides hierarchical task-guided and context-responsive routing policies.
Outcome:	thor-MoE can achieve an average improvement of 0.75 BLEU with less than 22% activated parameters on multi-domain translation tasks.

Copied to clipboard

Wen Ye, Zhaocheng Liu, Gui Yuwei, Tingyu Yuan, Yunyue Su, Bowen Fang, Chaoyang Zhao, Qiang Liu, Liang Wang

Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models (2026.acl-long)

Challenge:	Existing methods for text-to-image synthesis lack systematic error analysis and refinement strategies, resulting in limited reliability and effectiveness.
Approach:	They propose a plug-and-play multi-agent system called GenPilot that integrates error analysis, clustering-based adaptive exploration, fine-grained verification and a memory module for iterative optimization.
Outcome:	The proposed method improves text consistency and structural coherence on images with a plug-and-play system.

Copied to clipboard

Chao Xue, Yao Wang, Mengqiao Liu, Di Liang, Xingsheng Han, Peiyang Liu, Xianjie Wu, Chenyao Lu, Lei Jiang, Yu Lu, Haibo Shi, Shuang Liang, Minlong Peng, Flora D. Salim

MCS: An In-battle Commentary System for MOBA Games (2022.coling-1)

Challenge:	Incomplete learning is widespread and heterogeneous in large language models . authors identify five recurrent sources of incomplete learning: missing prerequisite knowledge, conflicts between SFT supervision and pre-training knowledge, internal inconsistencies within SFT data, left-side forgetting during sequential fine-tuning, and insufficient optimization for rare or complex patterns.
Approach:	They propose a diagnostic-first framework that maps incomplete learning to causes . they identify five recurrent sources of incomplete learning: missing prerequisite knowledge, conflicts between supervision and pre-training knowledge, internal inconsistencies, left-side forgetting during sequential fine-tuning, and insufficient optimization for rare or complex patterns.
Outcome:	The proposed framework maps incomplete learning to causes using observable training and inference signals.

Copied to clipboard

Xiaofeng Qi, Chao Li, Zhongping Liang, Jigang Liu, Cheng Zhang, Yuanxin Wei, Lin Yuan, Guang Yang, Lanxiao Huang, Min Li

Challenge:	In-battle commentary is an important component of live streaming of e-sports competitions and is applicable to a wide range of scenarios like combat information analysis and live streaming.
Approach:	They propose a generative system for in-battle real-time commentary in mobile MOBA games and propose 'transform' method to convert match statistics and utterances into consistent encoding space.
Outcome:	The proposed system is based on real-time match statistics and events and can be used for live streaming, e-sports commentary and combat information analysis.

Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization (2021.acl-long)

Copied to clipboard

Chen Liang, Simiao Zuo, Minshuo Chen, Haoming Jiang, Xiaodong Liu, Pengcheng He, Tuo Zhao, Weizhu Chen

Jointly Learning Aspect-Focused and Inter-Aspect Relations with Graph Convolutional Networks for Aspect Sentiment Analysis (2020.coling-main)

Challenge:	'lottery tickets' can be trained to match the performance of a full model . subnetwork training can also outperform random sampled subnetworks of the same size .
Approach:	They propose to train a subnetwork of 'lottery tickets' to match the full model's performance.
Outcome:	The proposed model outperforms subnetworks of the same size in a phase transition phenomenon . the proposed model improves single task fine-tuning by 0.9 points on BERT-base and 1.0 points on GLUE large .

Copied to clipboard

Bin Liang, Rongdi Yin, Lin Gui, Jiachen Du, Ruifeng Xu

Enhancing Answer Boundary Detection for Multilingual Machine Reading Comprehension (2020.acl-main)

Challenge:	Existing methods for aspect sentiment analysis do not include explicit sentiment expressions.
Approach:	They propose to construct a heterogeneous graph by leveraging aspect-focused and inter-aspect contextual dependencies for the specific aspect.
Outcome:	The proposed model outperforms state-of-the-art methods on four benchmark datasets and significantly boosts performance in comparison with BERT.

Copied to clipboard

Fei Yuan, Linjun Shou, Xuanyu Bai, Ming Gong, Yaobo Liang, Nan Duan, Yan Fu, Daxin Jiang

SAGE : A Top-Down Bottom-Up Knowledge-Grounded User Simulator for Multi-turn Agent Evaluation (2026.findings-eacl)

Challenge:	Existing approaches to improve machine reading comprehension performance on low resource languages are limited due to the lack of sufficient training data.
Approach:	They propose to use a mixed MRC task to translate the question to other languages and build cross-lingual question-passage pairs.
Outcome:	The proposed task improves on two cross-lingual MRC datasets.

Copied to clipboard

Ryan Shea, Yunan Lu, Liang Qiu, Zhou Yu

Challenge:	Existing evaluation methods rely on static benchmarks or narrow task-specific datasets that fail to capture the open-ended nature of real-world interactions.
Approach:	They propose a user Simulation framework for multi-turn AGent Evaluation that integrates top-down knowledge from business contexts and bottom-up knowledge from agent infrastructure.
Outcome:	The proposed framework produces interactions that are more realistic and diverse while identifying up to 33% more agent errors.

Domain Transfer based Data Augmentation for Neural Query Translation (2020.coling-main)

Copied to clipboard

Liang Yao, Baosong Yang, Haibo Zhang, Boxing Chen, Weihua Luo

Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data (2026.acl-long)

Challenge:	Query translation (QT) is a critical factor in successful cross-lingual information retrieval (CLIR).
Approach:	They propose to extend query translation (QT) with a domain transfer procedure to revise synthetic candidates to search-aware examples.
Outcome:	The proposed method outperforms baselines and domain transfer methods on translation quality and retrieval accuracy.

Copied to clipboard

Shiping Yang, Jie Wu, Wenbiao Ding, Ning Wu, Shining Liang, Ming Gong, Hongzhi Li, Hengyuan Zhang, Angel X. Chang, Dongmei Zhang

Out-of-Scope Intent Detection with Self-Supervision and Discriminative Training (2021.acl-long)

Challenge:	Existing studies on robustness to explicit noise (e.g., document semantics) but overlook implicit noise (spurious features).
Approach:	They propose a framework to quantify the robustness of RAGs against spurious features by integrating a data synthesis pipeline and a taxonomy.
Outcome:	The proposed framework quantifies the robustness of RALMs against spurious features.

Copied to clipboard

Li-Ming Zhan, Haowen Liang, Bo Liu, Lu Fan, Xiao-Ming Wu, Albert Y.S. Lam

Hierarchical Curriculum Learning for AMR Parsing (2022.acl-short)

Challenge:	Existing methods for out-of-scope intent detection rely on strong assumptions on data distribution and confidence threshold selection.
Approach:	They propose a method to train an out-of-scope intent classifier in a fully end-to-end manner by simulating the test scenario in training.
Outcome:	The proposed method improves on four benchmark dialogue datasets and improves over state-of-the-art methods.

Copied to clipboard

Peiyi Wang, Liang Chen, Tianyu Liu, Damai Dai, Yunbo Cao, Baobao Chang, Zhifang Sui

Multimodal Transformer for Unaligned Multimodal Language Sequences (P19-1)

Challenge:	Abstract Meaning Representation (AMR) parsing aims to translate sentences to semantic representation with a hierarchical structure, but there is a gap between their flat training objective and the hierarchic structure, which limits the model generalization.
Approach:	They propose a Hierarchical Curriculum Learning framework with Structure-level (SC) and Instance-level curricula (IC) that aims to translate sentences to semantic representation with a hierarchical structure.
Outcome:	Experiments on AMR2.0, AMR3.0, structure-complex and out-of-distribution situations confirm the effectiveness of the proposed framework.

Copied to clipboard

Yao-Hung Hubert Tsai, Shaojie Bai, Paul Pu Liang, J. Zico Kolter, Louis-Philippe Morency, Ruslan Salakhutdinov

LayoutDIT: Layout-Aware End-to-End Document Image Translation with Multi-Step Conductive Decoder (2023.findings-emnlp)

Challenge:	Human language is often multimodal, which comprehends a mixture of natural language, facial gestures, and acoustic behaviors.
Approach:	They propose a multimodal model that extends the standard Transformer network to learn representations directly from unaligned multimodal streams.
Outcome:	The proposed model outperforms state-of-the-art methods on aligned and non-aligned data.

Copied to clipboard

Zhiyang Zhang, Yaping Zhang, Yupu Liang, Lu Xiang, Yang Zhao, Yu Zhou, Chengqing Zong

Cross-Lingual Retrieval Augmented Prompt for Low-Resource Languages (2023.findings-acl)

Challenge:	Existing methods struggle to capture the visual layout in complex document images.
Approach:	They propose to integrate layout knowledge into document image translation by using a layout-aware encoder and a multi-step conductive decoder to achieve the translation step by step.
Outcome:	The proposed model outperforms state-of-the-art methods with better parameter efficiency.

Copied to clipboard

Ercong Nie, Sheng Liang, Helmut Schmid, Hinrich Schütze

MSCTD: A Multimodal Sentiment Chat Translation Dataset (2022.acl-long)

Challenge:	Multilingual pretrained language models (MPLMs) perform strongly in cross-lingual transfer.
Approach:	They propose to augment context with similar sentences retrieved from a high-resource language (HRL) they find a significant correlation between cross-lingual transfer performance and similarity between high- and low-resourced languages .
Outcome:	The proposed model outperforms finetuning by 3.7% on three downstream tasks with multilingual parallel test sets across 10 LRLs covering 6 language families in unlabeled and labeled settings.

Copied to clipboard

Yunlong Liang, Fandong Meng, Jinan Xu, Yufeng Chen, Jie Zhou

Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Tracking (2023.acl-long)

Challenge:	Multimodal machine translation and textual chat translation have received considerable attention . however, little research has been devoted to multimodal machine translator in conversations .
Approach:	They propose a task to generate more accurate translations with the help of dialogue history and visual context.
Outcome:	The proposed task can generate more accurate translations with the help of dialogue history and visual context.

Copied to clipboard

Qingyue Wang, Liang Ding, Yanan Cao, Yibing Zhan, Zheng Lin, Shi Wang, Dacheng Tao, Li Guo

SEMGraph: Incorporating Sentiment Knowledge and Eye Movement into Graph Model for Sentiment Analysis (2022.emnlp-main)

Challenge:	Existing methods to enhance the zeroshot generalization of DST fail to effectively decouple semantics of samples, limiting the zero-shot performance of the system.
Approach:	They propose a new learning schema that explicitly disentangles the semantics of seen data and leverages the performance and robustness with the mixture-of-experts mechanism.
Outcome:	The proposed model achieves state-of-the-art on multiWOZ2.1 with 10M trainable parameters and is robust to the mixture-of experts mechanism.

Copied to clipboard

Bingbing Wang, Bin Liang, Jiachen Du, Min Yang, Ruifeng Xu

Past Meets Present: Creating Historical Analogy with Large Language Models (2025.acl-long)

Challenge:	Existing research on sentiment analysis based on eye movement signals has been attributed importance.
Approach:	They propose a linguistic probing eye movement paradigm to extract eye movement features based on the relationship between linguistic features and human reading behavior.
Outcome:	The proposed graph architecture achieves state-of-the-art performance on two sentiment analysis datasets with eye movement signals and three sentiment analysis data without eye movement signal.

Copied to clipboard

Nianqi Li, Siyu Yuan, Jiangjie Chen, Jiaqing Liang, Feng Wei, Zujie Liang, Deqing Yang, Yanghua Xiao

Simultaneous Translation with Flexible Policy via Restricted Imitation Learning (P19-1)

Challenge:	Historical analogies are important abilities that help people make decisions and understand the world.
Approach:	They propose a historical analogy acquisition task that uses large language models to acquire historical analogies.
Outcome:	The proposed method mitigates hallucinations and stereotypes when LLMs generate historical analogies.

Copied to clipboard

Baigong Zheng, Renjie Zheng, Mingbo Ma, Liang Huang

Edit-Wise Preference Optimization for Grammatical Error Correction (2025.coling-main)

Challenge:	Existing approaches to simultaneous translation have been limited and use fixed-latency policies or a complicated two-staged model.
Approach:	They propose a single model that adds a “delay” token to the target vocabulary and a restricted dynamic oracle to greatly simplify training.
Outcome:	The proposed model achieves better BLEU scores and lower latencies compared to fixed and RL-learned policies on Chinese -> English simultaneous translation.

Copied to clipboard

Jiehao Liang, Haihui Yang, Shiping Gao, Xiaojun Quan

Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding (2024.findings-acl)

Challenge:	Large language models (LLMs) have been successful in grammatical error correction (GEC) but their strengths have yet to be fully demonstrated in GEC .
Approach:	They propose a method to optimize grammatical errors by assigning higher reward weights to edit tokens during preference optimization.
Outcome:	The proposed method outperforms baselines on English and Chinese datasets and achieves state-of-the-art performance.

Copied to clipboard

Xintong Wang, Jingheng Pan, Liang Ding, Chris Biemann

ThinkSwitcher: When to Think Hard, When to Think Fast (2025.findings-emnlp)

Challenge:	Recent research in large vision-language models has shown promising results, but the issue of hallucination remains.
Approach:	They propose an instruction-based method to reduce hallucinations in large vision-language models . they use disturbance instructions to exacerbate hallucinosity in multimodal fusion modules .
Outcome:	The proposed method reduces hallucinations in multimodal fusion modules by reducing alignment uncertainty and subtracting hallucines from the original distribution.

Copied to clipboard

Guosheng Liang, Longguang Zhong, Ziyi Yang, Xiaojun Quan

Leveraging Social Context for Humor Recognition and Sense of Humor Evaluation in Social Media with a New Chinese Humor Corpus - HumorWB (2024.lrec-main)

Challenge:	Large reasoning models excel at solving complex tasks by leveraging long chain-of-thought (CoT) reasoning.
Approach:	They propose a framework that enables a single LRM to dynamically switch between short and long CoT modes based on task complexity.
Outcome:	The proposed framework reduces computational cost by 20-30% while maintaining high accuracy on complex tasks.

Copied to clipboard

Zeyuan Zeng, Zefeng Li, Liang Yang, Hongfei Lin

Diachronic Sense Modeling with Deep Contextualized Word Embeddings: An Ecological View (P19-1)

Challenge:	Existing humor computing research focuses on content while neglecting interaction relationships in social media.
Approach:	They propose a dataset which introduces social context information from social media . they propose 'humor recognition' task and 'horror evaluation task'
Outcome:	The proposed model incorporates social context information from social media . it shows that it is efficient and can be used to evaluate humor in real life .

Copied to clipboard

Renfen Hu, Shen Li, Shichen Liang

Domain Adapted Word Embeddings for Improved Sentiment Classification (P18-2)

Challenge:	Existing word embeddings only assign one vector to a word for a time period, thus they face the meaning conflation deficiency.
Approach:	They propose a sense representation and tracking framework based on deep contextualized embeddings that can be used to answer what and when the word meaning changes.
Outcome:	The proposed framework is effective in representing fine-grained word senses, and brings a significant improvement in word change detection task.

Copied to clipboard

Prathusha K Sarma, Yingyu Liang, Bill Sethares

Think Before You Speak: Cultivating Communication Skills of Large Language Models via Inner Monologue (2024.findings-naacl)

Challenge:	Generic word embeddings are trained on large-scale generic corpora, while domain specific ones are trained only on data from a domain of interest.
Approach:	They propose a method to combine breadth of generic and specific embeddings to form domain-specific embeddables.
Outcome:	The proposed method outperforms generic and domain specific embeddings on sentiment classification tasks.

Copied to clipboard

Junkai Zhou, Liang Pang, Huawei Shen, Xueqi Cheng

Circuit Complexity Bounds for RoPE-based Transformer Architecture (2025.emnlp-main)

Challenge:	emergence of large language models (LLMs) improves capabilities of dialogue systems . but they lack communication skills, which make them more like information seeking tools .
Approach:	They propose to empower LLMs with communication skills through inner monologues . they use a benchmark to evaluate the dialogue generation ability of the model .
Outcome:	The proposed model outperforms the baselines in the evaluation of communication skills.

Copied to clipboard

Bo Chen, Xiaoyu Li, Yingyu Liang, Jiangxuan Long, Zhenmei Shi, Zhao Song, Jiahao Zhang

Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreement (2025.findings-acl)

Challenge:	Recent studies provide the circuit complexity bounds to Transformer-like architectures. position embedding has emerged as a crucial technique in modern large language models.
Approach:	They propose to use position embedding to improve Transformer-like architectures by analyzing their circuits and analyzing the results.
Outcome:	The proposed model is able to solve canonical tasks without embedding positional information.

Copied to clipboard

Junyu Lu, Kai Ma, Kaichun Wang, Kelaiti Xiao, Roy Ka-Wei Lee, Bo Xu, Liang Yang, Hongfei Lin

Towards Better Graph-based Cross-document Relation Extraction via Non-bridge Entity Enhancement and Prediction Debiasing (2024.findings-acl)

Challenge:	Existing studies focus on evaluating large language models' ability to handle disagreement cases.
Approach:	They evaluate the performance of large language models in detecting offensive language at varying levels of agreement.
Outcome:	The proposed model improves detection accuracy and model alignment with human judgment by using disagreement samples in training.

Copied to clipboard

Hao Yue, Shaopeng Lai, Chengyi Yang, Liang Zhang, Junfeng Yao, Jinsong Su

PyraMathBench: Evaluating and Improving Mathematical Capability in Large Language Models (2026.findings-acl)

Challenge:	Existing studies on relation extraction ignore non-bridge entities, leading to bias during inference.
Approach:	They propose a graph-based cross-document Relation Extraction model with non-bridge entity enhancement and prediction debiasing that integrates non-cross entities with target entities and bridge entities.
Outcome:	The proposed model outperforms baseline models on open and closed datasets.

Copied to clipboard

Zetian Ouyang, Linlin Wang, Gerard de Melo, Liang He

Spatial-Agent: Agentic Geo-spatial Reasoning with Scientific Core Concepts (2026.acl-long)

Challenge:	Numerical reasoning is ubiquitous in scientific research and financial analysis, but few benchmarks evaluate them by integrating numerical processing and mathematical reasoning.
Approach:	They propose a numerically-integrated hierarchical benchmark with 27,215 questions derived from 7,404 math word problems that spans 4 key cognitive aspects, 14 subcategories, and 2 modalities.
Outcome:	The proposed model improves Qwen-2.5 score with SOLVE and IRPO training.

Copied to clipboard

Riyang Bao, Cheng Yang, Dazhou Yu, Zhexiang Tang, Gengchen Mai, Liang Zhao

Relation Discovery with Out-of-Relation Knowledge Base as Supervision (N19-1)

Challenge:	Existing LLM-based agents lack inherent spatial awareness, relying on web search or text matching while hallucinating spatial relationships.
Approach:	They propose a spatial-based agent that can perform real-world geospatial computations . they use natural-language questions to parse into executable workflows based on geoFlow Graphs - directed acyclic graphs with nodes corresponding to spatial concepts and edges representing transformations.
Outcome:	The proposed agent outperforms existing baselines on MapEval-API and MapQA benchmarks while producing interpretable and executable geospatial workflows.

Copied to clipboard

Yan Liang, Xin Liu, Jianwen Zhang, Yangqiu Song

Learning to Control Summaries with Score Ranking (2026.findings-acl)

Challenge:	Existing methods to extract relations from text corpus without annotated data are violated by up to 31%.
Approach:	They propose to use out-of-relation knowledge bases to supervise the discovery of unseen relations where relations to discover from the text corpus and those in knowledge bases are not overlapped.
Outcome:	The proposed method improves the state-of-the-art relation discovery performance by a large margin.

Copied to clipboard

Hongye Liu, Liang Ding, Ricardo Henao

Know the Known and the Unknown: Reasonable Answer Generation with Knowledge-Informed Citations (2026.acl-long)

Challenge:	Recent advances in summarization focus on improving summary quality across multiple dimensions, but they overlook the challenge of controlling summary generation with respect to individual dimensions.
Approach:	They propose a loss function that aligns model outputs with fine-grained, model-based evaluation scores to enable both improvement in summary quality and dimension-specific control.
Outcome:	The proposed method improves the overall quality of summaries while maintaining strong control over individual quality dimensions.

Copied to clipboard

Yichi Zhang, Zhuo Chen, Lingbing Guo, Jun Xu, Mengshu Sun, Zhizhen Liu, Lei Liang, Wen Zhang, Huajun Chen

DUAL RM: Beyond Rule-based Preference Reward Modeling via Meta-Reward (2026.acl-long)

Challenge:	Existing approaches focus on generating multi-level citations linked to specific references, making it verifiable and trustworthy.
Approach:	They propose a new data construction pipeline and a benchmark to improve citation granularity and awareness of unknown information.
Outcome:	The proposed model improves on the existing benchmark and data construction pipeline and provides citation granularity and awareness of unknown information.

Copied to clipboard

Xiaobo Liang, Wanfu Wang, Qipeng Huang, Yuyang Ding, Zecheng Tang, Yixin Ji, Qianben Chen, Zhe Zhao, Kehai Chen, Juntao Li, Min Zhang

Challenge:	Existing preference-based reward modeling methods face a recursive dependency where each verifier requires a meta-verifier, leading to continuous and costly dependence on human annotation.
Approach:	They propose a dual RM that couples discriminative and generative reward models under a non-parametric meta-reward.
Outcome:	The proposed model achieves strong performance across major preference benchmarks and even when trained exclusively on language modality, it exhibits robust cross-modal transfer on Omni-RewardBench.

EX-FEVER: A Dataset for Multi-hop Explainable Fact Verification (2024.findings-acl)

Copied to clipboard

Huanhuan Ma, Weizhi Xu, Yifan Wei, Liuji Chen, Liang Wang, Qiang Liu, Shu Wu, Liang Wang

Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch (2025.acl-long)

Challenge:	Existing studies on fact verification lack a high-quality dataset for explainability . existing systems lack evidence retrieval and veracity prediction, limiting the ability to verify a claim .
Approach:	They propose a dataset for multi-hop explainable fact verification that summarises and modifies Wikipedia documents.
Outcome:	The proposed dataset aims to improve the accuracy of multi-hop explainable fact verification systems.

Copied to clipboard

Yuyang Ding, Xinyu Shi, Xiaobo Liang, Juntao Li, Zhaopeng Tu, Qiaoming Zhu, Min Zhang

A Meaning-Based Statistical English Math Word Problem Solver (N18-1)

Challenge:	Existing methods to improve the mathematical reasoning capabilities of Large Language Models (LLMs) are limited due to the proprietary nature of the data.
Approach:	They propose a data synthesis method that generates large-scale mathematical reasoning datasets using lightweight 7B-scale models.
Outcome:	The proposed method outperforms existing open-source datasets in both in-domain and out-of-domain evaluations and shows improvements in code reasoning tasks.

Copied to clipboard

Chao-Chun Liang, Yu-Shiang Wong, Yi-Chung Lin, Keh-Yih Su

Context-aware Embedding for Targeted Aspect-based Sentiment Analysis (P19-1)

Challenge:	Experimental results show that the proposed approach understands the meaning of each quantity in the text more.
Approach:	They propose a meaning-based approach for solving English math word problems . they analyze text, transform body and question parts into corresponding logic forms . Statistical models are proposed to select operator and operands .
Outcome:	The proposed approach outperforms existing systems on benchmark and noisy datasets.

Copied to clipboard

Bin Liang, Jiachen Du, Ruifeng Xu, Binyang Li, Hejiao Huang

SEAL: Interactive Tool for Systematic Error Analysis and Labeling (2022.emnlp-demos)

Challenge:	Existing methods do not specifically pre-train reasonable embeddings for targets and aspects in TABSA.
Approach:	They propose to refine the embeddings of targets and aspects using a sparse coefficient vector . this allows the embeds to be refined from highly correlative words instead of context-independent vectors .
Outcome:	Experiments show that the proposed method improves on two benchmark datasets.

Copied to clipboard

Nazneen Rajani, Weixin Liang, Lingjiao Chen, Margaret Mitchell, James Zou

Learning to Plan by Updating Natural Language (2024.findings-emnlp)

Challenge:	Existing models that fail on tail data or rare groups are difficult to identify due to lack of explicit labels.
Approach:	They propose a systematic error analysis and labeling tool that uses a two-step approach to identify high-error slices of data and then give human-understandable semantics to those underperforming slices.
Outcome:	The proposed tool identifies high-error slices of data and gives human-understandable semantics to those underperforming slices.

Copied to clipboard

Yiduo Guo, Yaobo Liang, Chenfei Wu, Wenshan Wu, Dongyan Zhao, Nan Duan

Adversarial Text Generation using Large Language Models for Dementia Detection (2024.emnlp-main)

Challenge:	Large Language Models (LLMs) have shown remarkable performance in basic natural language tasks.
Approach:	They propose a method that iteratively updates the task plan with new steps and behavioral instructions to guide LLMs to generate the correct solutions step by step.
Outcome:	The proposed method improves performance on five reasoning type tasks and can be directly applied to other LLMs.

Copied to clipboard

Youxiang Zhu, Nana Lin, Kiran Balivada, Daniel Haehn, Xiaohui Liang

Analyzing and Reducing the Performance Gap in Cross-Lingual Transfer with Fine-tuning Slow and Fast (2023.acl-long)

Challenge:	Large language models excel in text classification tasks, but they do not perform well with picture description.
Approach:	They propose an interpretable classification approach by Adversarial Text Generation (ATG) that could relate dementia detection with other tasks.
Outcome:	The proposed approach achieves 85% accuracy, >10% improvement over the previous methods.

Copied to clipboard

Yiduo Guo, Yaobo Liang, Dongyan Zhao, Bing Liu, Nan Duan

Taxonomy-Guided Zero-Shot Recommendations with LLMs (2025.coling-main)

Challenge:	Existing research shows that a multilingual pre-trained language model fine-tuned with one (source) language performs well on downstream tasks for non-source languages . However, there is a clear performance gap between the source and non-sourced languages - this gap can be reduced by reducing forgetting.
Approach:	They propose a method to fine-tune a multilingual pre-trained language model fine- tuned with one (source) language and four training policies to address the performance gap.
Outcome:	The proposed method outperforms baselines on the XNLI dataset by a clear margin.

Copied to clipboard

Yueqing Liang, Liangwei Yang, Chen Wang, Xiongxiao Xu, Philip S. Yu, Kai Shu

EGSS: Entropy-guided Stepwise Scaling for Reliable Software Engineering (2026.acl-long)

Challenge:	Existing approaches to deploy large language models (LLMs) into RecSys have limited prompt length, unstructured item information, and un-constrained generation of recommendations.
Approach:	They propose a taxonomy-guided recommendation framework that empowers LLMs with category information in a systematic approach.
Outcome:	The proposed framework significantly improves recommendation quality compared to zero-shot approaches.

Copied to clipboard

Chenhui Mao, Yuanting Lei, Zhixiang Wei, Ming Liang, Zhixiang Wang, Jingxuan Xu, Dajun Chen, Wei Jiang, Yong Li

M3: A Multi-View Fusion and Multi-Decoding Network for Multi-Document Reading Comprehension (2022.emnlp-main)

Challenge:	Entropy-Guided Stepwise Scaling (EGSS) is a novel TTS framework for software engineering tasks.
Approach:	They propose an entropy-guided stepwise scaling framework that balances efficiency and effectiveness through entropic-guide encoding and robust test-suite augmentation.
Outcome:	EGSS boosts performance by 5–10% across all evaluated models, and reduces inference-time token usage by over 28% . compared to existing methods, EGS reduces token usage and reduce inference time by over 20% .

Copied to clipboard

Liang Wen, Houfeng Wang, Yingwei Luo, Xiaolin Wang

Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RL (2026.findings-acl)

Challenge:	Existing methods for multi-document reading comprehension cannot make full of the advantages of both approaches.
Approach:	They propose a multi-view fusion and multi-decoding method that integrates multiple documents for answering questions.
Outcome:	The proposed method improves on two mainstream multi-document reading comprehension datasets.

Copied to clipboard

Haotian Zhai, Jingcheng Liang, Dongyeop Kang

Challenge:	Existing abstention methods produce generic refusals or encourage follow-up clarifications without verifying whether they identify the key missing information.
Approach:	They propose a clarification-aware RLVR reward that rewards correct answers on unanswerable queries while optimizing explicit abstention and semantically aligned post-refusal clarification on unannounced queries.
Outcome:	The proposed model improves abstention and clarification on unanswerable queries while maintaining strong performance on answerable queries.

BUMP: A Benchmark of Unfaithful Minimal Pairs for Meta-Evaluation of Faithfulness Metrics (2023.acl-long)

Copied to clipboard

Liang Ma, Shuyang Cao, Robert L Logan IV, Di Lu, Shihao Ran, Ke Zhang, Joel Tetreault, Alejandro Jaimes

UMRSpell: Unifying the Detection and Correction Parts of Pre-trained Models towards Chinese Missing, Redundant, and Spelling Correction (2023.acl-long)

Challenge:	Existing benchmarks measure the correlation with human judgements of faithfulness on model-generated summaries, but they are insufficient for diagnosing whether metrics are consistent, effective on human-written texts, and sensitive to different error types.
Approach:	They propose to use unfaithful minimal pairs to measure the consistency of automatic faithfulness metrics by comparing human-written summary pairs with a dataset of 889 human-writing, minimally different summary pairs.
Outcome:	The proposed benchmarks show that the most discriminative metrics tend not to be the most consistent, and that the best performing metrics are sensitive to errors.

Copied to clipboard

Zheyu He, Yujin Zhu, Linlin Wang, Liang Xu

RLHS: Mitigating Misalignment in RLHF with Hindsight Simulation (2026.findings-acl)

Challenge:	Chinese Spelling Correction (CSC) is a task of detecting and correcting misspelled charac- ters in Chinese texts.
Approach:	They propose a model to learn detection and correction parts together from a multi-task learning perspective.
Outcome:	The proposed model can learn detection and correction parts together from a multi-task learning perspective.

Copied to clipboard

Kaiqu Liang, Haimin Hu, Ryan Liu, Thomas L. Griffiths, Jaime Fernández Fisac

From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systems (2025.findings-emnlp)

Challenge:	Reinforcement Learning from Hindsight Simulation (RLHF) can cause severe misalignment in generative AI, but it is not a universal method for fine-tuning large language models.
Approach:	They propose a method that uses evaluator feedback to decouple alignment signal from potentially compromised predictions.
Outcome:	The proposed method significantly outperforms RLHF in comparisons with baselines and human evaluations.

Copied to clipboard

Zekun Zhou, Xiaocheng Feng, Lei Huang, Xiachong Feng, Ziyun Song, Ruihan Chen, Liang Zhao, Weitao Ma, Yuxuan Gu, Baoxin Wang, Dayong Wu, Guoping Hu, Ting Liu, Bing Qin

Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond (2025.acl-industry)

Challenge:	rapid development of artificial intelligence (AI) technologies has inspired researchers to explore how AI can accelerate and enhance research.
Approach:	They organize the relevant studies into three main categories: hypothesis formulation, hypothesis validation, and manuscript publication.
Outcome:	The authors summarize the current state of research in three main areas: hypothesis formulation, hypothesis validation, and manuscript publication.

Copied to clipboard

Liang Wen, Yunke Cai, Fenrui Xiao, Xin He, Qi An, Zhenyu Duan, Yimin Du, Junchen Liu, Tanglifu Tanglifu, Xiaowei Lv, Haosheng Zou, Yongchao Deng, Shousheng Jia, Xiangzheng Zhang

PPTC-R benchmark: Towards Evaluating the Robustness of Large Language Models for PowerPoint Task Completion (2024.findings-emnlp)

Challenge:	Experimental results show that opensource curriculum training is more effective when distinct datasets are available for different training stages.
Approach:	They propose an opensource suite for training long reasoning models using publicdata and models.
Outcome:	The proposed model outperforms DeepSeek-R1-DistillQwen-32B models in math reasoning.

Copied to clipboard

Zekai Zhang, Yiduo Guo, Yaobo Liang, Dongyan Zhao, Nan Duan

Simultaneous Translation (2020.emnlp-tutorials)

Challenge:	Large Language Models (LLMs) are increasingly used for task completion in real-world situations.
Approach:	They propose a PowerPoint Task Completion-Robustness (PPTC-R) benchmark to measure LLMs’ robustness to the user PPT task instruction and software version (Powerpoint).
Outcome:	The proposed benchmark compares 3 closed-source and 4 open-source LLMs to the PowerPoint task instruction and software version (Powerpoint) .

Copied to clipboard

Liang Huang, Colin Cherry, Mingbo Ma, Naveen Arivazhagan, Zhongjun He

Examining False Positives under Inference Scaling for Mathematical Reasoning (2025.emnlp-main)

Challenge:	Simultaneous translation is a problem that has long been considered one of the hardest problems in AI . this tutorial will provide a deep understanding of the history and the recent advances in simultaneous translation.
Approach:	This tutorial will examine the design and evaluation of policies for simultaneous translation . it will provide an overview of the history and recent advances in simultaneous translation.
Outcome:	This tutorial will examine the design and evaluation of policies for simultaneous translation .

Copied to clipboard

Yu Wang, Nan Yang, Liang Wang, Furu Wei, Fuli Feng

POMP: Probability-driven Meta-graph Prompter for LLMs in Low-resource Unsupervised Neural Machine Translation (2024.acl-long)

Challenge:	Recent advances in language models have led to significant improvements in mathematical reasoning across benchmarks.
Approach:	They analyze the prevalence of false positives in language models by using heuristic evaluation methods . they find that false positive models produce correct final answers but with flawed deduction paths .
Outcome:	The proposed model performance improvements are based on the proposed model and its evaluation metrics.

Copied to clipboard

Shilong Pan, Zhiliang Tian, Liang Ding, Haoqi Zheng, Zhen Huang, Zhihua Wen, Dongsheng Li

Learning Easily Updated General Purpose Text Representations with Adaptable Task-Specific Prefix (2023.findings-emnlp)

Challenge:	Low-resource languages (LRLs) face challenges in supervised neural machine translation due to limited parallel data.
Approach:	They propose a method that uses a dynamic graph to organize auxiliary languages in prompts to improve LRL translations.
Outcome:	The proposed method improves translation accuracy in low-resource languages (LRLs) using auxiliary language pairs and synthetic pseudo-parallel data.

Copied to clipboard

Kuan-Hao Huang, Liang Tan, Rui Hou, Sinong Wang, Amjad Almahairi, Ruty Rinott

Musical Score Understanding Benchmark: Evaluating Large Language Models’ Comprehension of Complete Musical Scores (2026.acl-long)

Challenge:	a large pre-trained language model can cause computational burdens in inference time due to multiple forward passes.
Approach:	They propose a method to learn fixed text representations with source tasks . they learn a task-specific prefix for each source task independently and combine them .
Outcome:	The proposed method improves generalizability of representations with source tasks.

Copied to clipboard

Congren Dai, Yue Yang, Krinos Li, Huichi Zhou, Shijie Liang, Zhang Bo, Enyang Liu, Ge Jin, Hongran An, Haosen Zhang, Peiyuan Jing, KinHei Lee, Zhenxuan Zhang, Xiaobing Li, Maosong Sun

Achieving Multi-Hop Calculation and Safe Abstention in Financial Numerical Reasoning by Metric Graph Constrained LLMs (2026.acl-long)

Challenge:	Existing benchmarks for musical score understanding are narrow in scope, focusing on isolated fragments, short excerpts, or multiple-choice formulations, rather than supporting holistic reasoning over entire scores.
Approach:	They propose a benchmark for score-level musical understanding across textual and visual modalities.
Outcome:	The musical score understanding benchmark contains 1,800 question-answer pairs from works by Bach, Beethoven, Chopin, Debussy, and others.

Copied to clipboard

Aoyuan Jiang, Liang Hong, Haoxuan Liu, Rui Wang

Spatial-RAG: Spatial Retrieval Augmented Generation for Real-World Geospatial Reasoning Questions (2026.findings-acl)

Challenge:	Large language models (LLMs) are prone to forced generation when confronting ambiguous evidence or complex recursive dependencies.
Approach:	They propose a framework that imposes semantic and structural constraints via a financial metric knowledge graph.
Outcome:	a neuro-symbolic framework outperforms existing models on financial metric knowledge graphs.

Copied to clipboard

Dazhou Yu, Riyang Bao, Ruiyu Ning, Jinghong Peng, Gengchen Mai, Liang Zhao

STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework (P19-1)

Challenge:	Existing large language models lack spatial computing capabilities and access to up-to-date geospatial data.
Approach:	They propose a Retrieval-Augmented Generation framework for geospatial question answering . it integrates structured spatial databases with LLMs via a hybrid spatial retriever .
Outcome:	Experiments show that Spatial-RAG significantly improves over baselines.

Copied to clipboard

Mingbo Ma, Liang Huang, Hao Xiong, Renjie Zheng, Kaibo Liu, Baigong Zheng, Chuanqiang Zhang, Zhongjun He, Hairong Liu, Xing Li, Hua Wu, Haifeng Wang

EmoS: A High-Fidelity Multimodal Benchmark for Fine-grained Streaming Emotional Understanding (2026.acl-long)

Challenge:	Simultaneous translation is notoriously dif- ficult due to word-order differences.
Approach:	They propose a prefix-to-prefix framework that implicitly learns to anticipate in a single translation model.
Outcome:	The proposed framework achieves low latency and reasonable qual- ity on 4 directions.

Copied to clipboard

Pengze Guo, Jingxi Liang, Zhiwen Xie, Qifeng Wang, Derek F. Wong

A Middle Path for On-Premises LLM Deployment: Preserving Privacy Without Sacrificing Model Confidentiality (2025.emnlp-main)

Challenge:	Existing benchmarks fail to achieve ecological validity, signal clarity, and reliable fine-grained labeling in multimodal Emotion Recognition (MER) Existing datasets lack spontaneity of real-life interactions, resulting in poor quality and inconsistent data quality.
Approach:	They propose a bilingual benchmark to resolve limitations of ecological validity and noise in existing datasets by combining strictly filtered static slices with a dynamic Streaming Monologue subset.
Outcome:	EmoS provides trusted ground truth that captures continuous emotional evolution.

Copied to clipboard

Hanbo Huang, Yihan Li, Bowen Jiang, Bo Jiang, Lin Liu, Zhuotao Liu, Ruoyu Sun, Shiyu Liang

MENTOR: Efficient Autoregressive Image Generation with Balanced Multimodal Control (2026.findings-acl)

Challenge:	Privacy-sensitive users require deploying large language models within their own infrastructure (on-premises) vulnerabilities in local environments can lead to unauthorized access and potential model theft.
Approach:	They propose a framework that secures a few bottom layers in a secure environment . they propose metric to optimize trade-off between protection and customization flexibility .
Outcome:	The proposed framework outperforms baselines on five models with 1.3B to 70B parameters.

Copied to clipboard

Haozhe Zhao, Zefan Cai, Shuzheng Si, Liang Chen, Jiuxiang Gu, Wen Xiao, Minjia Zhang, Junjie Hu

Act-Adaptive Margin: Dynamically Calibrating Reward Models for Subjective Ambiguity (2026.acl-long)

Challenge:	Recent text-to-image models achieve impressive visual quality but still face challenges in precise controllability, balancing multimodal inputs, and high training cost for multimodal image generation.
Approach:	They propose an autoregressive framework with a two-stage training paradigm for controllable multimodal image generation.
Outcome:	Extensive experiments on DreamBench++ and DreamBech show that the proposed framework achieves a strong balance between textual and visual guidance for controllable image generation.

Copied to clipboard

Feiteng Fang, Dingwei Chen, Xiang Huang, Ting-En Lin, Yuchuan Wu, Xiong Liu, Jing Ye, Ziqiang Liu, Haonan Zhang, Liang Zhu, Hamid Alinejad-Rokny, Min Yang, Yongbin Li

Challenge:	Existing approaches to reward modeling in reinforcement learning tasks are limited when dealing with ambiguous preferences.
Approach:	They propose to use AAM to dynamically calibrate preference margins using the Bradley-Terry model's internal parameter knowledge to improve reward modeling in subjective tasks.
Outcome:	The proposed approach improves reward modeling by dynamically calibrating preference margins using the model’s internal parameter knowledge.

MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving (2022.findings-naacl)

Copied to clipboard

Zhenwen Liang, Jipeng Zhang, Lei Wang, Wei Qin, Yunshi Lan, Jie Shao, Xiangliang Zhang

Mind Reader: Latent User Demand-Guided Content Optimization for Generative Search Engine (2026.acl-long)

Challenge:	Existing work on math word problem solvers replace real numbers with symbolic placeholders to focus on logic reasoning.
Approach:	They propose to inject numerical properties into symbolic placeholders with contextualized representation learning schema to solve number representation dilemma.
Outcome:	The proposed model can solve MWP problems on English and Chinese benchmarks.

Copied to clipboard

Tong Chen, JiaWei Guo, Yuxi Li, Baiming Chen, Houxing Ren, Zhang Zhiwei, Yunxiang Zhang, Hanyang Xia, Kun Liang, Zhaoran Fan

Can Language Models Follow Multiple Turns of Entangled Instructions? (2025.findings-emnlp)

Challenge:	Generative Search Engines (GSEs) have reshaped information retrieval and Generating Engine Optimization (GEO) emerges to improve the content visibility in GSEs’ responses.
Approach:	They propose a method to optimize content to cover latent semantic information of GSEs by decomposing query into diverse perspectives and capturing underlying semantic information.
Outcome:	The proposed method outperforms baselines and effectively improves content visibility (with up to 2.44x objective metrics and 1.23x subjective metrics on average).

Copied to clipboard

Chi Han, Xin Liu, Haodong Wang, Shiyang Li, Jingfeng Yang, Haoming Jiang, Zhengyang Wang, Qingyu Yin, Liang Qiu, Changlong Yu, Yifan Gao, Zheng Li, Bing Yin, Jingbo Shang, Heng Ji

Token-Level Self-Evolution Training for Sequence-to-Sequence Learning (2023.acl-short)

Challenge:	Despite of significant achievements in improving instruction-following capabilities of large language models, the ability to process multiple potentially entangled or conflicting instructions remains a considerable challenge.
Approach:	They construct multi-turn instruction with 1.1K high-quality multi-turned conversations using the human-in-the-loop approach and examine their capabilities.
Outcome:	The proposed model shows that it is difficult to integrate multiple turns and balance competing objectives when instructions intersect or conflict.

Copied to clipboard

Keqin Peng, Liang Ding, Qihuang Zhong, Yuanxin Ouyang, Wenge Rong, Zhang Xiong, Dacheng Tao

Multi-Level Cross-Modal Alignment for Speech Relation Extraction (2024.emnlp-main)

Challenge:	Adaptive training approaches do not consider the variation of learning difficulty in different training steps, making the learning deterministic and sub-optimal.
Approach:	They propose a dynamic token-level self-evolution training method that reweighs the training losses of different target tokens based on priors.
Outcome:	Empirically, the proposed method yields significant improvements on three translation tasks.

Copied to clipboard

Liang Zhang, Zhen Yang, Biao Fu, Ziyao Lu, Liangying Shao, Shiyu Liu, Fandong Meng, Jie Zhou, Xiaoli Wang, Jinsong Su

DoTAT: A Domain-oriented Text Annotation Tool (2022.acl-demo)

Challenge:	Existing studies use synthetic speech to train and evaluate SpeechRE models, hindering their development . modality gap issue limits performance of existing models, limiting future researches .
Approach:	They propose to use speech data to train and evaluate SpeechRE models by using real speech . they propose to train a cross-modal alignment model to bridge the modality gap .
Outcome:	The proposed model can train to bridge the modality gap between speech encoder and text decoder . the proposed model is based on two real SpeechRE datasets .

Copied to clipboard

Yupian Lin, Tong Ruan, Ming Liang, Tingting Cai, Wen Du, Yi Wang

Challenge:	DoTAT is a domain-oriented text annotation tool that can reduce the time for event annotation by 19.7% . the tool supports multi-person collaborative process with automatically merging and review .
Approach:	They propose a domain-oriented text annotation tool called DoTAT . it provides multi-person collaborative process with automatic merging and review .
Outcome:	The proposed tool can reduce the time for event annotation by 19.7% compared with existing tools.

RSA-Bench: Benchmarking Audio Large Models in Real-World Acoustic Scenarios (2026.findings-acl)

Copied to clipboard

Yibo Zhang, Kaiwen Luo, Liang Lin, Shilinlu Yan, Jin Wang, Yaoqi Guo, Yitian Chen, Yalan Qin, Zhenhong Zhou, Kun Wang, Li Sun

TRACE: Two-Phase RL for Causal Graph Exploration and Deeper Psychological Intervention in Dynamic Counseling Scenarios (2026.findings-acl)

Challenge:	Existing evaluations rely on synthetic Gaussian noise or simplistic single-source interference, failing to capture the intricate, multi-layered acoustic dynamics that characterize authentic physical environments.
Approach:	They propose a robustness benchmark to stress-test Audio Large Models (ALLMs) using high-fidelity auditory scene simulations.
Outcome:	The proposed model performs well on a wide range of tasks, including automatic speech recognition, speech translation, and audio-based reasoning.

Copied to clipboard

Shilin Tang, Zunyi Yin, Xuefeng Liang, Guanghui Shi, Song Tong, Chen Guangyu

CARL: Constraint-Aware Reinforcement Learning for Planning with LLMs (2026.findings-acl)

Challenge:	Existing models lack the ability to actively explore the underlying causes of psychological distress.
Approach:	They propose a two-phase reinforcement learning framework that implements a causal-graph-driven reward scheme across two phases: an exploration phase that rewards the causal graph reconstruction following a surface-to-deep path, and an intervention phase that supports targeted restructuring of irrational beliefs.
Outcome:	Extensive experiments show that TRACE outperforms existing models, enabling causal-chain-aware psychological intervention beyond surface-level empathy.

Copied to clipboard

Qiuyi Qi, Jinjian Zhang, Mutian Bao, Tian Liang, Guocong Li, Dongnan Liu, Wei Zhou, Jie Liu, Ming Kong, Linjian Mo, Feng Zhang, Qiang Zhu

Memp: Exploring Agent Procedural Memory (2026.findings-acl)

Challenge:	Existing approaches to constraint-aware planning fail to enhance the model’s intrinsic focus on constraints.
Approach:	They propose a constraint-aware reinforcement learning framework that encourages constraint focus and penalizes neglect of LLMs.
Outcome:	The proposed framework outperforms existing frameworks and state-of-the-art reasoning models in a number of real-world applications.

Copied to clipboard

Runnan Fang, Yuan Liang, Xiaobin Wang, Jialong Wu, Shuofei Qiao, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang

Challenge:	Large Language Models (LLMs) based agents suffer from brittle procedural memory that is manually engineered or entangled in static parameters.
Approach:	They propose a procedural-memory repository that distills past agent trajectories into fine-grained, step-by-step instructions and higher-level, script-like abstractions.
Outcome:	The proposed repository can be used to improve agents' performance on travelplanner and Alfworld.

Alleviating Hallucinations from Knowledge Misalignment in Large Language Models via Selective Abstention Learning (2025.acl-long)

Copied to clipboard

Lei Huang, Xiaocheng Feng, Weitao Ma, Yuchun Fan, Xiachong Feng, Yuxuan Gu, Yangfan Ye, Liang Zhao, Weihong Zhong, Baoxin Wang, Dayong Wu, Guoping Hu, Lingpeng Kong, Tong Xiao, Ting Liu, Bing Qin

Asynchronous Deep Interaction Network for Natural Language Inference (D19-1)

Challenge:	Large language models (LLMs) suffer from severe hallucination issues due to the knowledge misalignment between the pre-training stage and the supervised fine-tuning stage.
Approach:	They propose a training objective with an abstention mechanism that selectively rejects tokens that misalign with the desired knowledge distribution via a special [REJ] token.
Outcome:	The proposed model selectively rejects tokens that misalign with the desired knowledge distribution via a special [REJ] token.

Copied to clipboard

Di Liang, Fubao Zhang, Qi Zhang, Xuanjing Huang

MaCSC: Towards Multimodal-augmented Pre-trained Language Models via Conceptual Prototypes and Self-balancing Calibration (2024.naacl-long)

Challenge:	Existing methods have framed the reasoning problem as a semantic matching task.
Approach:	They propose an asynchronous deep interaction network (ADIN) to deconstruct the reasoning process and implement asynchron and multi-step reasoning.
Outcome:	The proposed model outperforms strong baselines on three popular benchmarks: SNLI, MultiNLI, and SciTail.

Copied to clipboard

Xianwei Zhuang, Zhichang Wang, Xuxin Cheng, Yuxin Xie, Liming Liang, Yuexian Zou

Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (2023.emnlp-main)

Challenge:	Existing approaches to training pre-trained language models (PLMs) focus on static image modality; inevitably encounter modality gaps and noise; and treat all modalities.
Approach:	They propose a multimodal-augmented framework that can infuse multimodal semantics into PLMs and facilitate a self-balancing calibration of information allocation.
Outcome:	The proposed framework outperforms baselines on multiple NLP tasks and outperformed existing frameworks.

Copied to clipboard

Shwai He, Run-Ze Fan, Liang Ding, Li Shen, Tianyi Zhou, Dacheng Tao

Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention (2026.acl-long)

Challenge:	Extensive experiments show that MEO significantly improves computational efficiency . compared to dense networks, sparsely activated networks only employ a few parameters for each input .
Approach:	They propose a method that merges multiple experts into one to reduce computation costs . they demonstrate that a sparse Mixture of Experts (MoE) can reduce the cost by activating a small subset of parameters for each input .
Outcome:	The proposed approach reduces the computational cost to that of a single expert by 83.3% compared to 82.6% in vanilla MoE.

Copied to clipboard

Zhen Yang, Mingyang Zhang, Feng Chen, Ganggui Ding, Liang Hou, Xin Tao, Ying-Cong Chen

TS-SQL: Test-driven Self-refinement for Text-to-SQL (2025.findings-emnlp)

Challenge:	Recent advances in large language models (LLMs) have focused on test-time scaling to improve reasoning quality but at the cost of efficiency.
Approach:	They propose a training-free framework that enhances reasoning accuracy and stability with minimal overhead.
Outcome:	The proposed framework yields consistent gains across general, coding, and STEM tasks while remaining highly efficient.

Copied to clipboard

Wenbo Xu, Haifeng Zhu, Liang Yan, Chuanyi Liu, Peiyi Han, Shaoming Duan, Jeff Z. Pan

Uncertainty Aware Learning for Language Model Alignment (2024.acl-long)

Challenge:	null
Approach:	null
Outcome:	null

Copied to clipboard

Yikun Wang, Rui Zheng, Liang Ding, Qi Zhang, Dahua Lin, Dacheng Tao

Low-code LLM: Graphical User Interface over Large Language Models (2024.naacl-demo)

Challenge:	Existing alignment strategies that focus on diverse and high-quality data often overlook the intrinsic uncertainty of tasks, learning all data samples equally.
Approach:	They propose to introduce the sample uncertainty into the alignment of different task scenarios by a simple fashion by setting the label smoothing value of training according to the uncertainty of individual samples.
Outcome:	The proposed model outperforms standard supervised fine-tuning on high-entropy tasks and complex low-entropic tasks.

Copied to clipboard

Yuzhe Cai, Shaoguang Mao, Wenshan Wu, Zehua Wang, Yaobo Liang, Tao Ge, Chenfei Wu, WangYou WangYou, Ting Song, Yan Xia, Nan Duan, Furu Wei

Learning to Contrast the Counterfactual Samples for Robust Visual Question Answering (2020.emnlp-main)

Challenge:	Low-code LLM is a visual programming interface that allows users to incorporate their ideas into the process without writing trivial prompts.
Approach:	They propose a human-LLM interaction framework that incorporates low-code visual programming interactions to achieve more controllable and stable responses.
Outcome:	The proposed framework enables users to incorporate ideas into the process without writing trivial prompts.

Copied to clipboard

Zujie Liang, Weitao Jiang, Haifeng Hu, Jiaying Zhu

SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training (2025.findings-acl)

Challenge:	Existing methods of generating counterfactual samples are not fully utilized in the task of Visual Question Answering (VQA).
Approach:	They propose a self-supervised contrastive learning mechanism to learn the relationship between original samples, factual samples and counterfactual samples.
Outcome:	The proposed method surpasses state-of-the-art models on the VQA-CP dataset, a diagnostic benchmark for assessing the VQ model’s robustness.

Copied to clipboard

Wenxi Chen, Ziyang Ma, Ruiqi Yan, Yuzhe Liang, Xiquan Li, Ruiyang Xu, Zhikang Niu, Yanqiao Zhu, Yifan Yang, Zhanxun Liu, Kai Yu, Yuxuan Hu, Jinyu Li, Yan Lu, Shujie Liu, Xie Chen

Speech & Audio in NLP

Challenge:	a new spoken dialogue system with single-stage training is demonstrating its low latency and high quality . SLAM-Omni achieves zero-shot timbre control by modeling spoken language with semantic tokens .
Approach:	They propose a timbre-controllable, end-to-end voice interaction system with single-stage training.
Outcome:	The proposed system outperforms previous models on 4 GPUs with limited data.

Every Token Counts: Generalizing 16M Ultra-Long Context in Large Language Models (2026.acl-long)

Copied to clipboard

Xiang Hu, Zhanchao Zhou, Ruiqi Liang, Zehuan Li, Wei Wu, Jianguo Li

A Generative Model for End-to-End Argument Mining with Reconstructed Positional Encoding and Constrained Pointer Mechanism (2022.emnlp-main)

Challenge:	a recent study explores efficient ultra-long context modeling.
Approach:	They propose to use Hierarchical Sparse Attention to achieve efficient ultra-long context modeling.
Outcome:	The proposed model performs comparable to full-attention baselines on in-domain and out-of-domain tasks.

Copied to clipboard

Jianzhu Bao, Yuhang He, Yang Sun, Bin Liang, Jiachen Du, Bing Qin, Min Yang, Ruifeng Xu

GeoDRL: A Self-Learning Framework for Geometry Problem Solving using Reinforcement Learning in Deductive Reasoning (2023.findings-acl)

Challenge:	Argument mining (AM) is a challenging task as it requires recognizing complex argumentation structures involving multiple subtasks.
Approach:	They propose a generative framework where expected outputs of AM are framed as a simple target sequence.
Outcome:	The proposed framework achieves state-of-the-art on two AM benchmarks.

Copied to clipboard

Shuai Peng, Di Fu, Yijun Liang, Liangcai Gao, Zhi Tang

Simultaneous Translation Policies: From Fixed to Adaptive (2020.acl-main)

Challenge:	Existing methods for automated geometry problem solving lack labeled data.
Approach:	They propose a framework that integrates logic graph deduction and deep reinforcement learning to optimize geometry reasoning as a Markov Decision Process.
Outcome:	The proposed framework improves accuracy and interpretability in the Geometry3K dataset while maintaining correctness.

Copied to clipboard

Baigong Zheng, Kaibo Liu, Renjie Zheng, Mingbo Ma, Hairong Liu, Liang Huang

SAFARI: Cross-lingual Bias and Factuality Detection in News Media and News Articles (2024.findings-emnlp)

Challenge:	Adaptive policies can balance translation quality and latency based on context information . previous methods on obtaining adaptive policies rely on complicated training process .
Approach:	They propose to obtain adaptive policies by a simple heuristic composition of fixed policies . they propose to use a heurism to obtain policies that can outperform fixed ones .
Outcome:	Experiments on Chinese -> English and German -> english show that adaptive policies outperform fixed policies by up to 4 BLEU points for the same latency.

Copied to clipboard

Dilshod Azizov, Zain Mujahid, Hilal AlQuabeh, Preslav Nakov, Shangsong Liang

Visually-Guided Policy Optimization for Multimodal Reasoning (2026.acl-long)

Challenge:	a new corpus of news media and articles is developed to assess political bias and factuality in cross-lingual contexts . integrity and objectivity of news are crucial in an age of information sharing across cultural and language landscapes - a recent study shows .
Approach:	They propose a corpus of news media and articles for predicting political bias and factuality . they evaluate the cross-lingual ability of the models; however, they evaluate on English data .
Outcome:	The proposed corpus is unprecedented in its collection and evaluates on English data.

Copied to clipboard

Zengbin Wang, Feng Xiong, Liang Lin, Xuecai Hu, Yong Wang, Yanlin Wang, Man Zhang, Xiangxiang Chu

Cross-Lingual Knowledge Editing in Large Language Models (2024.acl-long)

Challenge:	Existing RLVRs lack visual faithfulness due to text-dominated reasoning . a novel framework to reinforce visual focus during policy optimization is proposed .
Approach:	They propose a framework to reinforce visual focus during policy optimization using visual attention compensation mechanism.
Outcome:	The proposed framework exhibits better visual activation and superior performance in multimodal reasoning and visual-dependent tasks.

Copied to clipboard

Jiaan Wang, Yunlong Liang, Zengkui Sun, Yuxuan Cao, Jiarong Xu, Fandong Meng

Learning Invariant Representation Improves Robustness for MRC Models (2022.findings-emnlp)

Challenge:	Knowledge editing is a promising technique to adapt large language models to new knowledge without retraining from scratch.
Approach:	They propose to use a multilingual dataset to translate a large-scale cross-lingual synthetic dataset from English to Chinese and then to evaluate their performance in Chinese.
Outcome:	The proposed method can change model performance on several special cases without retraining from scratch.

Copied to clipboard

Yu Hai, Liang Wen, Haoran Meng, Tianyu Liu, Houfeng Wang

CogEvolve: A Multimodal Benchmark for Evaluating Relational Reasoning in Semantic Extension (2026.acl-long)

Challenge:	Existing approaches to improve machine reading comprehension models are vulnerable and not robust to adversarial examples.
Approach:	They propose to construct positive example pairs which have same answer by augmentation and then introduce stability and contrastive loss to improve invariance of representation.
Outcome:	The proposed approach boosts the robustness of QA models across different tasks and attack sets significantly and consistently.

Copied to clipboard

Jingjie Zeng, Huayang Li, Liang Yang, Yuanyuan Sun, Shaowu Zhang, Hongfei Lin

Argument Pair Extraction with Mutual Guidance and Inter-sentence Relation Graph (2021.emnlp-main)

Challenge:	a gap exists between human embodied logic and machine statistical learning . authors: models internalize statistical patterns or mimic static recognition .
Approach:	They propose a cognitive linguistic benchmark to test whether large language models internalize statistical logic or not . they find that models function as "Super-Associators" expert at static recognition yet fail at causal reasoning .
Outcome:	The proposed model fails at causal reasoning and has a high-fidelity concept representation but lacks transformational operators essential for true relational understanding.

Copied to clipboard

Jianzhu Bao, Bin Liang, Jingyi Sun, Yice Zhang, Min Yang, Ruifeng Xu

Neural Relation Classification with Text Descriptions (C18-1)

Challenge:	Existing studies on argumentation mining focus on monological argumentation and dialogical argumentation.
Approach:	They propose a mutual guidance framework that could guide arguments in one passage . they propose an inter-sentence relation graph to effectively model the inter-relations between two sentences .
Outcome:	The proposed method outperforms the current state-of-the-art model.

Copied to clipboard

Feiliang Ren, Di Zhou, Zhihui Liu, Yongcheng Li, Rongsheng Zhao, Yongkang Liu, Xiaobo Liang

Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs (2023.findings-emnlp)

Challenge:	State-of-the-art methods for relation classification suffer from data sparsity issue greatly.
Approach:	They propose a new neural relation classification method which integrates entities’ text descriptions into deep neural networks models.
Outcome:	The proposed method achieves much better experimental results than other state-of-the-art methods on the SemEval 2010 dataset.

Copied to clipboard

Hongru Wang, Rui Wang, Fei Mi, Yang Deng, Zezhong Wang, Bin Liang, Ruifeng Xu, Kam-Fai Wong

MedQPA-Gen: Medical Question Proposing and Answering for Report Generation (2026.findings-acl)

Challenge:	Existing LLMs generate responses based on the dialogue context, overlooking the underlying linguistic cues about the user status exhibited in the context.
Approach:	They propose a linguistic cue-based chain-of-thoughts method which enhances the LLMs inference with an intermediate reasoning step to find cues exhibited in the dialogue.
Outcome:	The proposed method outperforms standard prompting methods on in-depth dialogue questions and linguistic cues exhibited in the context.

Copied to clipboard

Weijie Liang, Xiyue Zhu, Ruike Zhu, Chenhao Li, Cheng Tang, Zhiyu Liu, Zhihua Gong, Shirui Luo, Yudu Li, Volodymyr Kindratenko

Wasserstein Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains (2020.emnlp-main)

Challenge:	Existing training paradigms fail to explicitly target factual accuracy, resulting in inaccuracies and serious patient safety risks.
Approach:	They propose an automatic and generalizable report evaluation technique that uses question proposing and answering to enable controllable, structured reasoning grounded in medical domain knowledge and the factual correctness of the report.
Outcome:	The proposed method can improve human preference scores and perform better on downstream tasks.

Copied to clipboard

Weijie Yu, Chen Xu, Jun Xu, Liang Pang, Xiaopeng Gao, Xiaozhao Wang, Ji-Rong Wen

Opportunistic Decoding with Timely Correction for Simultaneous Translation (2020.acl-main)

Challenge:	Asymmetrical text matching is a fundamental problem in information retrieval and natural language processing.
Approach:	They propose a method that regularizes features vectors projected from different domains . WD-Match can be used to improve different text matching methods .
Outcome:	The proposed method outperforms existing methods and benchmarks on four datasets.

Copied to clipboard

Renjie Zheng, Mingbo Ma, Baigong Zheng, Kaibo Liu, Liang Huang

LLM Agents for Education: Advances and Applications (2025.findings-emnlp)

Challenge:	Existing approaches to balancing translation quality and latency are either too aggressive or too conservative.
Approach:	They propose an opportunistic decoding technique that always (over-)generates a certain mount of extra words at each step to keep the audience on track with the latest information.
Outcome:	The proposed technique reduces latency and increases BLEU with no over-generating . it also corrects mistakes in the overgenerated words when observing more context .

Copied to clipboard

Zhendong Chu, Shen Wang, Jian Xie, Tinghui Zhu, Yibo Yan, Jingheng Ye, Aoxiao Zhong, Xuming Hu, Jing Liang, Philip S. Yu, Qingsong Wen

Data-Efficient Selection via Grammatical Complexity in Continual Pre-training of Domain-Specific LLMs (2025.emnlp-main)

Challenge:	Large Language Model (LLM) agents are transforming education by automating complex tasks and enhancing both teaching and learning processes.
Approach:	This survey analyzes recent advances in applying Large Language Model agents to educational settings . it highlights ethical issues, hallucination and overreliance, and integration with existing ecosystems .
Outcome:	The authors analyze the technologies enabling LLM agents and highlight key challenges in deploying them in educational settings.

Copied to clipboard

Yizhou Ying, Geng Zhang, Cui Danxin, Chengyu Du, Guanglei Yue, Sihang Jiang, Jiaqing Liang, Yifei Fu, Hailin Hu, Yanghua Xiao

Context-aware Stand-alone Neural Spelling Correction (2020.findings-emnlp)

Challenge:	Existing data selection strategies for continual pre-training of large language models often rely on scarce labeled data or computationally expensive LLMs.
Approach:	They propose an annotation-independent data selection framework for CPT that evaluates grammatical complexity using lexical diversity and syntactic complexity.
Outcome:	The proposed framework outperforms baselines on a financial dataset and surpasses full-data training by 1.7% using only 20% of the data.

Copied to clipboard

Xiangci Li, Hairong Liu, Liang Huang

Challenge:	Existing natural language processing systems are vulnerable to noisy inputs resulting from misspellings.
Approach:	They propose a stand-alone spelling correction problem that corrects the spelling of tokens without additional token insertion or deletion.
Outcome:	The proposed solution outperforms the state-of-the-art spelling correction model by 12.8% absolute F0.5 score.

Think Twice: Perspective-Taking Improves Large Language Models’ Theory-of-Mind Capabilities (2024.acl-long)

Copied to clipboard

Alex Wilf, Sihyun Lee, Paul Pu Liang, Louis-Philippe Morency

Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performance (2025.emnlp-main)

Challenge:	Recent advances to LLMs’ reasoning capabilities from simple yet effective prompting techniques such as Chain-of-Thought have seen limited applicability to ToM.
Approach:	They propose a two-stage prompting framework inspired by Simulation Theory's notion of perspective-taking to elicit Theory-of-Mind capabilities in Large Language Models.
Outcome:	The proposed framework shows that it is much more effective than existing prompts.

Copied to clipboard

Yao Wang, Di Liang, Minlong Peng

Fluent and Low-latency Simultaneous Speech-to-Speech Translation with Self-adaptive Training (2020.findings-emnlp)

Challenge:	Extensive experiments demonstrate that our approach significantly alleviates task interference and forgetting.
Approach:	They propose a framework for supervised fine-tuning for large language models . they first fine-tail the model on each task to identify its core parameter regions .
Outcome:	The proposed framework outperforms vanilla fine-tuning and baselines on multiple public benchmarks on reasoning, dialogue, instruction following, and more.

Copied to clipboard

Renjie Zheng, Mingbo Ma, Baigong Zheng, Kaibo Liu, Jiahong Yuan, Kenneth Church, Liang Huang

Mixup-Transformer: Dynamic Data Augmentation for NLP Tasks (2020.coling-main)

Challenge:	Current approaches to simultaneous speech-to-speech translation accumulate more and more latencies in later sentences when the speaker talks faster.
Approach:	They propose a method which generates more fluent target speech latency than the baseline . they propose to use self-adaptive translation to adjust the length of translations to accommodate different source speech rates.
Outcome:	Xiong et al., 2019) show that the proposed method generates more fluent target speech latency than baseline . authors say it provides more natural communication process than speech-to-text translation . xiong and colleagues say the proposed technique is more efficient than current approaches .

Copied to clipboard

Lichao Sun, Congying Xia, Wenpeng Yin, Tingting Liang, Philip Yu, Lifang He

BERM: Training the Balanced and Extractable Representation for Matching to Improve Generalization Ability of Dense Retrieval (2023.acl-long)

Challenge:	Recent work on data augmentation techniques that interpolate inputs and labels shows strong effectiveness in image classification.
Approach:	They propose to integrate mixup to transformer-based pre-trained architecture for NLP tasks while keeping the whole end-to-end training system.
Outcome:	The proposed framework improves on GLUEbenchmark and transformer-based learning models while keeping the whole end-to-end training system.

Copied to clipboard

Shicheng Xu, Liang Pang, Huawei Shen, Xueqi Cheng

Modeling Bilingual Conversational Characteristics for Neural Chat Translation (2021.acl-long)

Challenge:	Dense retrieval has shown promise in the first-stage retrieval process when trained on in-domain labeled datasets.
Approach:	They propose a method to capture matching signal to improve generalization of dense retrieval by capturing matching signal between two texts.
Outcome:	The proposed method can be combined with different training methods to improve generalization ability without additional inference overhead and target domain data.

Copied to clipboard

Yunlong Liang, Fandong Meng, Yufeng Chen, Jinan Xu, Jie Zhou

Identifying Cellular Niches in Spatial Transcriptomics: An Investigation into the Capabilities of Large Language Models (2025.acl-long)

Challenge:	Neural chat translation aims to translate bilingual conversational text due to its inherent characteristics such as role preference, dialogue coherence, and translation consistency.
Approach:	They propose to model the translation quality of conversational text by learning distributions of bilingual conversational characteristics.
Outcome:	The proposed approach outperforms baseline models and is widely available.

Copied to clipboard

Huanhuan Wei, Xiao Luo, Hongyi Yu, Jinping Liang, Luning Yang, Lixing Lin, Alexandra Popa, Xiting Yan

A Self-Distillation Recipe for Neural Machine Translation (2025.findings-acl)

Challenge:	Spatial transcriptomic technologies allow measuring gene expression profile and spatial information of cells in tissues simultaneously.
Approach:	They propose a spatial transcriptomic approach to identify spatial niches using a zero-shot large language models by transforming spatial transcriptomics data into spatial context prompts.
Outcome:	The proposed model improves performance by leveraging gene expression of neighboring cells/spots, cell type composition, tissue information, and external knowledge.

Copied to clipboard

Hongfei Xu, Zhuofei Liang, Qiuhui Liu, Lingling Mu

Multi-Reference Training with Pseudo-References for Neural Translation and Text Generation (D18-1)

Challenge:	Existing methods for Neural Machine Translation (NMT) have been proven effective in improving the performance of computer vision tasks without pre-training a teacher.
Approach:	They propose a rank-order augmented Pearson correlation loss and an iterative distillation method to prevent the discrepancy of predictions between the student and a stronger teacher from disturbing the training.
Outcome:	The proposed method can lead to significant improvements over the strong Transformer baseline on low/middle/high-resource tasks, obtaining comparable or better performance with fewer layers.

Copied to clipboard

Renjie Zheng, Mingbo Ma, Liang Huang

Semantic Relation-aware Difference Representation Learning for Change Captioning (2021.findings-acl)

Challenge:	Neural text generation has been quite successful recently, but during training time, only one reference is considered for each example, even though there are often multiple references available.
Approach:	They propose an algorithm to generate exponentially many pseudo-references by compressing existing references into lattices and traversing them to generate new pseudo-References.
Outcome:	The proposed model significantly improves on baselines in machine translation and image captioning, and is comparable to existing models.

Copied to clipboard

Yunbin Tu, Tingting Yao, Liang Li, Jiedong Lou, Shengxiang Gao, Zhengtao Yu, Chenggang Yan

VulLibGen: Generating Names of Vulnerability-Affected Packages via a Large Language Model (2024.acl-long)

Challenge:	Existing methods to describe semantic change in images with distractors are difficult to learn .
Approach:	They propose a semantic relation-aware difference representation learning network to explicitly learn the difference representation in the existence of distractors.
Outcome:	The proposed network achieves state-of-the-art performance on CLEVR-Change and Spot-the -Diff datasets.

Copied to clipboard

Tianyu Chen, Lin Li, ZhuLiuchuan ZhuLiuchuan, Zongyang Li, Xueqing Liu, Guangtai Liang, Qianxiang Wang, Tao Xie

Unifying Dual-Space Embedding for Entity Alignment via Contrastive Learning (2025.coling-main)

Challenge:	Existing work on affected package identification is limited by large language models . a recent study shows that 84% third-party packages contain security vulnerabilities .
Approach:	They propose a method to use LLM to generate the affected package . they propose supervised fine-tuning, retrieval augmented generation and a local search algorithm .
Outcome:	The proposed method has an average precision of 0.806 for identifying vulnerable packages in four most popular ecosystems in GitHub Advisory.

Copied to clipboard

Cunda Wang, Weihua Wang, Qiuyu Liang, Feilong Bao, Guanglai Gao

Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis (2022.naacl-main)

Challenge:	Entity alignment (EA) aims to match identical entities across knowledge graphs (KGs) Graph neural network-based entity alignment methods have achieved promising results in Euclidean space, but KGs often contain complex local and hierarchical structures, which are hard to represent in a single space.
Approach:	They propose a method which unifies dual-space embedding to preserve the intrinsic structure of KGs.
Outcome:	The proposed method achieves state-of-the-art in structure-based EA on benchmark datasets.

Copied to clipboard

Yiwei Wang, Muhao Chen, Wenxuan Zhou, Yujun Cai, Yuxuan Liang, Dayiheng Liu, Baosong Yang, Juncheng Liu, Bryan Hooi

Universally Empowering Zeroth-Order Optimization via Adaptive Layer-wise Sampling (2026.findings-acl)

Challenge:	Existing studies rely on entity information for sentence-level relation extraction (RE) but this can leak superficial and spurious clues of relations.
Approach:	They propose to use entity mentions to extract relations from textual context . they use a causal graph to model dependencies between variables in RE models .
Outcome:	The proposed method yields significant gains on both effectiveness and generalization for RE.

Copied to clipboard

Fei Wang, Li Shen, Liang Ding, Chao Xue, Ye Liu, Changxing Ding

Skeletons Matter: Dynamic Data Augmentation for Text-to-Query (2025.emnlp-main)

Challenge:	Existing methods for fine-tuning Large Language Models are slow and lack of performance.
Approach:	They propose a Zeroth-Order optimization framework that uses forward passes to fine-tune Large Language Models.
Outcome:	The proposed framework achieves 1.7 to 3.0 wall-clock acceleration on LLaMA and OPT models.

Copied to clipboard

Yuchen Ji, Bo Xu, Jie Shi, Jiaqing Liang, Deqing Yang, Yu Mao, Hai Chen, Yanghua Xiao

Semantic Parsing

Challenge:	Existing studies focus on a single query language, resulting in limited generalizability . a new task paradigm is proposed to unify semantic parsing tasks across different query languages .
Approach:	They propose a task paradigm that unifies parsing tasks across query languages . they identify query skeletons as a shared optimization target of Text-to-Query tasks .
Outcome:	The proposed method achieves state-of-the-art performance using only a small amount of synthesized data.

From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks (2025.naacl-long)

Copied to clipboard

Xiaofeng Zhang, Yihao Quan, Chen Shen, Xiaosong Yuan, Shaotian Yan, Liang Xie, Wenxiao Wang, Chaochen Gu, Hao Tang, Jieping Ye

Augur: Modeling Covariate Causal Associations in Time Series via Large Language Models (2026.acl-long)

Challenge:	Large visionlanguage models (LVLMs) are a powerful visual-language reasoning tool.
Approach:	They propose to integrate attention analysis with LLaVA-CAM to determine interactions between visual representations.
Outcome:	The proposed approach can be used to determine interactions between visual representations.

Copied to clipboard

Zhiqing Cui, Binwu Wang, Qingxiang Liu, Yeqiang Wang, Zhengyang Zhou, Yuxuan Liang, Yang Wang

CLUE: A Chinese Language Understanding Evaluation Benchmark (2020.coling-main)

Challenge:	Large language models (LLMs) have emerged as a promising avenue for time series forecasting . existing approaches face limitations such as marginalized role in model architectures and lack of interpretability.
Approach:	They propose a framework that exploits LLM causal reasoning to discover and use directed causal associations among covariates.
Outcome:	The proposed model improves predictive accuracy while yielding transparent, traceable reasoning about variable interactions.

Copied to clipboard

Liang Xu, Hai Hu, Xuanwei Zhang, Lu Li, Chenjie Cao, Yudong Li, Yechen Xu, Kai Sun, Dian Yu, Cong Yu, Yin Tian, Qianqian Dong, Weitang Liu, Bo Shi, Yiming Cui, Junyi Li, Jun Zeng, Rongzhao Wang, Weijian Xie, Yanting Li, Yina Patterson, Zuoyu Tian, Yiwen Zhang, He Zhou, Shaoweihua Liu, Zhe Zhao, Qipeng Zhao, Cong Yue, Xinrui Zhang, Zhengliang Yang, Kyle Richardson, Zhenzhong Lan

Challenge:	Existing language evaluation benchmarks for English are limited to English . lack of such benchmarks makes it difficult to replicate success in other languages .
Approach:	They introduce a large-scale Chinese language understanding evaluation benchmark . the benchmark uses a set of current state-of-the-art pre-trained Chinese models .
Outcome:	The first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark is released . the benchmark evaluates models across a wide range of tasks on original Chinese text . existing language evaluation benchmarks are mostly limited to English .

Empirical Study on Data Attributes Insufficiency of Evaluation Benchmarks for LLMs (2025.coling-main)

Copied to clipboard

Chuang Liu, Renren Jin, Zheng Yao, Tianyi Li, Liang Cheng, Mark Steedman, Deyi Xiong

Challenge:	Existing benchmarks for evaluating large language models neglect key qualitative data attributes that can significantly impact the final rankings of LLMs.
Approach:	They propose a framework with three modules designed to assess diversity, redundancy, and difficulty.
Outcome:	The proposed framework systematically incorporates diversity, redundancy, and difficulty attributes and shows that they influence the ranking of LLMs.

Zero-shot Graph Reasoning via Retrieval Augmented Framework with LLMs (2025.findings-emnlp)

Copied to clipboard

Hanqing Li, Sharika Mahadevan, Kiran Jyothi Sheena, Henry Liang, Diego Klabjan

MKT: A Multi-Stage Knowledge Transfer Framework to Mitigate Catastrophic Forgetting in Multi-Domain Chinese Spelling Correction (2025.emnlp-industry)

Challenge:	Existing methods that require extensive finetuning or depend on predefined algorithms are limited by training.
Approach:	a new retrieval-augmented framework is proposed that harnesses retrieval and large language models to address graph reasoning tasks.
Outcome:	The proposed method achieves 100% accuracy on most graph reasoning tasks while maintaining consistent token costs regardless of graph sizes.

Copied to clipboard

Peng Xing, Yinghui Li, Shirong Ma, Xinnian Liang, Haojing Huang, Yangning Li, Shu-Yu Guo, Hai-Tao Zheng, Wenhao Jiang, Ying Shen

FinTextQA: A Dataset for Long-form Financial Question Answering (2024.acl-long)

Challenge:	Chinese Spelling Correction (CSC) is a model that detects and corrects spelling errors in given sentences.
Approach:	They propose a model-agnostic model with an evolving teacher model and dynamic distillation weights for knowledge transfer in each domain rather than focusing solely on new domain knowledge.
Outcome:	The proposed model-agnostic framework is based on an evolving teacher model and dynamic distillation weights for knowledge transfer in each domain, rather than focusing solely on new domain knowledge.

Copied to clipboard

Jian Chen, Peilin Zhou, Yining Hua, Loh Xin, Kehui Chen, Ziyuan Li, Bing Zhu, Junwei Liang

Improve Interpretability of Neural Networks via Sparse Contrastive Coding (2022.findings-emnlp)

Challenge:	Existing financial question answering datasets lack scope diversity and question complexity.
Approach:	They propose to use a dataset for long-form question answering in finance to evaluate QA systems.
Outcome:	The proposed dataset includes 1,262 high-quality, source-attributed QA pairs extracted and selected from finance textbooks and government agency websites.

Copied to clipboard

Junhong Liu, Yijie Lin, Liang Jiang, Jia Liu, Zujie Wen, Xi Peng

Generating Hashtags for Short-form Videos with Guided Signals (2023.acl-long)

Challenge:	XAI has achieved remarkable advances, but few efforts have been devoted to solving the problem.
Approach:	They propose a model-agnostic explanation method termed Sparse Contrastive Coding . they use model-based explanations to explain the black-box in a more model-oriented way .
Outcome:	The proposed method outperforms five state-of-the-art methods in interpretability and classification metrics.

Copied to clipboard

Tiezheng Yu, Hanchao Yu, Davis Liang, Yuning Mao, Shaoliang Nie, Po-Yao Huang, Madian Khabsa, Pascale Fung, Yi-Chia Wang

EducationQ: Evaluating LLMs’ Teaching Capabilities Through Multi-Agent Dialogue Framework (2025.acl-long)

Challenge:	Short-form video hashtag recommendation (SVHR) is a classification or ranking problem that selects hashtags from a set of limited candidates.
Approach:	They propose a short-form video hashtag recommendation task that better represents how hashtags are created naturally by retrieving relevant hashtags from a large-scale hashtag pool as extra guidance signals.
Outcome:	The proposed model outperforms strong classification baselines on two short-form video datasets and the guidance signals boost the performance by 8.11 and 2.17 absolute ROUGE-1 scores on average.

Copied to clipboard

Yao Shi, Rongkeng Liang, Yong Xu

PresentAgent: Multimodal Agent for Presentation Video Generation (2025.emnlp-demos)

Challenge:	Large Language Models (LLMs) are increasingly used as educational tools, yet evaluating their teaching capabilities remains challenging due to the resource-intensive nature of teacher-student interactions.
Approach:	They propose a multi-agent dialogue framework that efficiently assesses teaching capabilities through simulated dynamic educational scenarios.
Outcome:	The proposed framework outperforms open-source models on 1,498 questions across 13 disciplines and 10 difficulty levels on 1,400 questions.

Copied to clipboard

Jingwei Shi, Zeyu Zhang, Biao Wu, Yanjie Liang, Meng Fang, Ling Chen, Yang Zhao

Traffic-R1: Reinforced LLMs Bring Human-Like Reasoning to Traffic Signal Control Systems (2026.acl-long)

Challenge:	Existing methods for generating static slides or text summaries are limited to producing narrated presentations.
Approach:	They propose a multimodal agent that transforms long-form documents into narrated presentations.
Outcome:	The present agent produces fully synchronized visual and spoken content that closely mimics human-style presentations.

Copied to clipboard

Xingchen Zou, Yuhao Yang, Zheng Chen, Xixuan Hao, Yiqi Chen, Chao Huang, Yuxuan Liang

TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models (2023.emnlp-main)

Challenge:	Rapid urbanization and surging vehicle ownership intensify congestion . rapid urbanization drives crash rates, slow emergency response, and burden transit-poor communities .
Approach:	They introduce a 3B-parameter foundation model with human-like reasoning for Traffic signal control (TSC) they use reinforcement learning and network communication to convert LLM into a traffic-control model that operates like a human traffic agent.
Outcome:	The proposed model outperforms baselines and training-intensive RL controllers on a simulated traffic environment and reduces queue lengths by more than 5%.

Copied to clipboard

Jing Xiong, Jianhao Shen, Ye Yuan, Haiming Wang, Yichun Yin, Zhengying Liu, Lin Li, Zhijiang Guo, Qingxing Cao, Yinya Huang, Chuanyang Zheng, Xiaodan Liang, Ming Zhang, Qun Liu

CDS: Data Synthesis Method Guided by Cognitive Diagnosis Theory (2025.findings-acl)

Challenge:	Automated theorem proving (ATP) benchmarks focus on symbolic inference but rarely involve understanding complex number combination reasoning.
Approach:	They propose a benchmark that requires a model to reduce a trigonometric expression with step-by-step proof and evaluates a generative LM’s reasoning ability on formulas and ability to manipulate, group, and factor number terms.
Outcome:	The proposed benchmark evaluates a generative LM’s reasoning ability on formulas and ability to manipulate, group, and factor number terms.

Copied to clipboard

Haokun Zhao, Jinyi Han, Jiaqing Liang, Yanghua Xiao, Xiaojun Meng, Jiansheng Wei

Linguistics & Cognitive NLP

Challenge:	Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse tasks, but the complexity of emerging tasks and higher performance demands highlight the need for continuous improvement.
Approach:	They propose a method that refines evaluation results and characterizes model profiles at the knowledge component level.
Outcome:	The proposed method improves performance across multiple benchmarks and academic exams.

DAGN: Discourse-Aware Graph Network for Logical Reasoning (2021.naacl-main)

Copied to clipboard

Yinya Huang, Meng Fang, Yu Cao, Liwei Wang, Xiaodan Liang

Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators (2023.emnlp-main)

Challenge:	Recent QA with logical reasoning questions requires passage-level relations among the sentences.
Approach:	They propose a discourse-aware graph network that aggregates passage-level clues for QA by using discourse-based information.
Outcome:	The proposed model achieves competitive results on two logical reasoning QA datasets.

Copied to clipboard

Liang Chen, Yang Deng, Yatao Bian, Zeyu Qin, Bingzhe Wu, Tat-Seng Chua, Kam-Fai Wong

Self-Evolution Fine-Tuning for Policy Optimization (2024.findings-emnlp)

Challenge:	Large language models outperform information retrieval techniques for downstream knowledge-intensive tasks when being prompted to generate world knowledge.
Approach:	They propose a COmpreheNsive kNowledge Evaluation framework to evaluate generated knowledge from six important perspectives . they conduct extensive empirical analysis of generated knowledge on two widely studied knowledge-intensive tasks .
Outcome:	The proposed framework evaluates generated knowledge from six important perspectives on two knowledge-intensive tasks.

Copied to clipboard

Ruijun Chen, Jiehao Liang, Shiping Gao, Fanqi Wan, Xiaojun Quan

STATE ToxiCN: A Benchmark for Span-level Target-Aware Toxicity Extraction in Chinese Hate Speech Detection (2025.findings-acl)

Challenge:	Recent years have showcased the remarkable capabilities and performance of large language models (LLMs) across a broad range of tasks.
Approach:	They propose supervised fine-tuning (SEFT) for LLM alignment to eliminate the need for annotated samples while retaining the stability and efficiency of SFT.
Outcome:	The proposed method eliminates the need for annotated samples while maintaining the stability and efficiency of SFT.

Copied to clipboard

Zewen Bai, Liang Yang, Shengdi Yin, Junyu Lu, Jingjie Zeng, Haohao Zhu, Yuanyuan Sun, Hongfei Lin

Ethical NLP

Challenge:	Existing studies on Chinese hate speech detection lack span-level fine-grained annotations.
Approach:	They construct a Span-level target-aware Toxicity Extraction dataset and evaluate existing models for Chinese hateful slang.
Outcome:	The proposed dataset is the first span-level Chinese hate speech dataset and evaluates the ability of existing models to understand hate semantics.

Inducing Argument Facets for Faithful Opinion Summarization (2025.findings-emnlp)

Copied to clipboard

Jian Wang, Yanjie Liang, Yuqing Sun, Bin Gong

Dual-Reasoner: Bridging Interleaved Atomicity and Streaming Latency via Thinking-while-Talking (2026.findings-acl)

Challenge:	Faithful opinion summarization task involves generating a summary that covers the majority and minority opinions in documents.
Approach:	They propose a facets-guided opinion summarization method that induces facets and partitions documents into multiple facet-specific sets.
Outcome:	The proposed method outperforms state-of-the-art methods and multiple LLMs on two representative datasets and shows it can be used in specialty domains.

Copied to clipboard

Yangzhuo Li, Shengpeng Ji, Yifu Chen, Tianle Liang, Haoyu Yang, null Junboli, Jun Fang, Lin Li, Qingyang Hong

Learning How to Remember: A Meta-Cognitive Management Method for Structured and Transferable Agent Memory (2026.findings-acl)

Challenge:	Existing methods to integrate Chain-of-Thought into spoken dialogue models incur prohibitive latency.
Approach:	They propose a Streaming Masking Mechanism to ensure uninterrupted audio streaming . they use a quadruple-constraint system to reconstruct logical atomicity .
Outcome:	Experimental results show that Dual-Reasoner improves speech generation performance with low latency.

Copied to clipboard

Sirui Liang, Pengfei Cao, Jian Zhao, Wenhao Teng, Xiangwen Liao, Jun Zhao, Kang Liu

Challenge:	Existing approaches store memory in fixed representations and reuse it at a single or implicit level of abstraction, which limits generalization and often leads to negative transfer when distribution shift.
Approach:	They propose a Meta-Cognitive Memory Abstraction method which decouples task execution from memory management by combining a frozen task model with a learned memory copilot.
Outcome:	Experiments on ALFWorld, ScienceWorld, and BabyAI show that the proposed method improves performance, out-of-distribution generalization, and cross-task transfer over several baselines.

RGAR: Recurrence Generation-augmented Retrieval for Factual-aware Medical Question Answering (2025.findings-emnlp)

Copied to clipboard

Sichu Liang, Linhai Zhang, Hongyu Zhu, Wenwen Wang, Yulan He, Deyu Zhou

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data (2026.acl-short)

Challenge:	Existing retrieval approaches often overlook patient-specific factual knowledge embedded in EHRs . existing retrieval frameworks often overlook this factual information, limiting its effectiveness in clinical decision-making.
Approach:	They propose a recurrence generation-augmented retrieval framework that synergizes factual and conceptual knowledge from dual sources.
Outcome:	The proposed framework improves on factual-aware medical QA benchmarks.

Copied to clipboard

Zhenwen Liang, Yujun Zhou, Sidi Lu, Xiangliang Zhang, Haitao Mi, Dong Yu

Prefix-Tuning: Optimizing Continuous Prompts for Generation (2021.acl-long)

Challenge:	Strong base models saturate benchmarks, resulting in weaker performance, a paradox . a new approach to Reinforcement Learning (RL) is needed to improve performance .
Approach:	They propose a method that uses constrained uniform top-k sampling to flatten the local optimization landscape by sampling uniformly from constrained high-confidence candidates.
Outcome:	Experiments show that the proposed approach prevents policy degeneration and boosts out-of-domain generalization.

Copied to clipboard

Xiang Lisa Li, Percy Liang

LM-Critic: Language Models for Unsupervised Grammatical Error Correction (2021.emnlp-main)

Challenge:	Fine-tuning is the prevalent paradigm for using large pretrained language models for downstream tasks, but it requires updating and storing all the parameters of the LM.
Approach:	They propose a lightweight alternative to fine-tuning for natural language generation tasks that optimizes a sequence of continuous vectors, which they call the prefix.
Outcome:	The proposed approach outperforms fine-tuning in the full data setting and extrapolates better to examples with topics that are unseen during training.

Copied to clipboard

Michihiro Yasunaga, Jure Leskovec, Percy Liang

PAD-Net: An Efficient Framework for Dynamic Networks (2023.acl-long)

Challenge:	Recent work casts GEC as a translation problem using encoder-decoder models to map bad (ungrammatical) sentences into good (grammatically) sentences.
Approach:	They propose to use a pretrained language model to define an LM-Critic that judges a sentence to be grammatical if the LM assigns it a higher probability than its local perturbations.
Outcome:	The proposed method outperforms existing methods in both the unsupervised and supervised setting.

Copied to clipboard

Shwai He, Liang Ding, Daize Dong, Boan Liu, Fuqiang Yu, Dacheng Tao

Making Pre-trained Language Models Better Continual Few-Shot Relation Extractors (2024.lrec-main)

Challenge:	Dynamic networks can significantly improve the model’s representation power with acceptable computational cost.
Approach:	They propose a partially dynamic network to transform redundant dynamic parameters into static ones and iterative mode partition to partition dynamic and static parameters efficiently.
Outcome:	The proposed network surpasses fully dynamic networks by +0.7% top-1 acc with only 30% dynamic parameters for DY-Conv and +1.9% average score in language understanding with only 50% dynamic parameters.

Copied to clipboard

Shengkun Ma, Jiale Han, Yi Liang, Bo Cheng

Enhancing Input-Label Mapping in In-Context Learning with Contrastive Decoding (2025.acl-short)

Challenge:	Existing methods to learn new relations with limited labeled data are prone to catastrophic forgetting and overfitting.
Approach:	They propose a framework that uses prompts to acquire more generalized knowledge . they propose CFRE to continuously learn new relations while retaining knowledge of old ones .
Outcome:	The proposed method outperforms state-of-the-art methods by a large margin and significantly mitigates catastrophic forgetting and overfitting in low-resource scenarios.

Copied to clipboard

Keqin Peng, Liang Ding, Yuanxin Ouyang, Meng Fang, Yancheng Yuan, Dacheng Tao

Chain-of-History Reasoning for Temporal Knowledge Graph Forecasting (2024.findings-acl)

Challenge:	Prior research has found that large language models overlook input-label mapping information in ICL, relying more on their pre-trained knowledge.
Approach:	They propose a novel method that contrasts input-label mappings between positive and negative in-context examples to improve model performance.
Outcome:	The proposed method improves performance on 7 natural language understanding tasks without additional training.

Copied to clipboard

Yuwei Xia, Ding Wang, Qiang Liu, Liang Wang, Shu Wu, Xiao-Yu Zhang

NarGINA: Towards Accurate and Interpretable Children’s Narrative Ability Assessment via Narrative Graphs (2025.findings-acl)

Challenge:	Existing graph-based models excel at capturing structural information within TKGs but lack semantic comprehension abilities.
Approach:	They propose a plug-and-play module to enhance the performance of graph-based TKG models by exploring high-order histories step-by-step.
Outcome:	Experiments on three datasets and backbones show that CoH is effective in capturing high-order historical information for LLMs.

Copied to clipboard

Jun Zhong, Longwei Xu, Li Kong, Xianzhuo Li, Dandan Liang, Junsheng Zhou

Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction (2026.findings-acl)

Challenge:	Existing methods for assessing children's narrative ability are limited to evaluating completeness of narrative content and the coherence of expression, as well as interpretability of assessment results.
Approach:	They propose a computational framework for assessing narrative ability using a narrative graph to provide a concise and structured summary representation of narrative text.
Outcome:	The proposed framework achieves significant performance improvement over baselines while possessing good interpretability.

Copied to clipboard

Zhenmei Shi, Yifei Ming, Xuan-Phi Nguyen, Yingyu Liang, Shafiq Joty

Challenge:	Large Language Models (LLMs) have demonstrated remarkable capabilities in handling long context inputs, but this comes at the cost of increased computational resources and latency.
Approach:	They propose an algorithm that uses early LLM layers as filters to select and compress input tokens, reducing the context length for subsequent processing.
Outcome:	The proposed method outperforms existing techniques on the Needle in a Haystack task while demonstrating comparable performance on the LongBench challenge.

A New View of Multi-modal Language Analysis: Audio and Video Features as Text “Styles” (2021.eacl-main)

Copied to clipboard

Zhongkai Sun, Prathusha K Sarma, Yingyu Liang, William Sethares

Morpheme Sense Disambiguation: A New Task Aiming for Understanding the Language at Character Level (2024.lrec-main)

Challenge:	Fig. 1 shows how style-transferred multi-modal features can be used in sentiment analysis and emotion recognition.
Approach:	They propose to use adaptive normalization to impose style onto text to learn richer representations for multi-modal utterances.
Outcome:	The proposed model achieves performance on par with state-of-the-art but using less than a third of the model parameters.

Copied to clipboard

Yue Wang, Hua Zheng, Yaqi Yin, Hansi Wang, Qiliang Liang, Yang Liu

Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion (2025.acl-long)

Challenge:	Morphemes are a strong linguistic feature to capture lexical semantics, but lack of morpheme-informed resources and the expense of manual annotations hinder morphme-enhanced methods.
Approach:	They propose a task of Morpheme Sense Disambiguation with two subtasks in-text and in-word to generalize morpheme features on more tasks.
Outcome:	The proposed tasks are based on two morpheme-annotated datasets for Chinese . the best model yields a promising precision of 77.66% on in-text and 88.19% on in word .

Copied to clipboard

Jianqing Zhu, Huang Huang, Zhihang Lin, Juhao Liang, Zhengyang Tang, Khalid Almubarak, Mosen Alharthi, Bang An, Juncai He, Xiangbo Wu, Fei Yu, Junying Chen, Ma Zhuoheng, Yuhao Du, He Zhang, Saied Alshahrani, Emad A. Alghamdi, Lian Zhang, Ruoyu Sun, Haizhou Li, Benyou Wang, Jinchao Xu

CRAFTQA: A Code-Driven Adaptive Framework for Complex Structured Data Reasoning (2026.findings-acl)

Challenge:	In the evolving landscape of large language models, the predominant focus has been on English and Chinese.
Approach:	They propose to utilize Arabic-specific vocabulary in the tokenizer to accelerate decoding.
Outcome:	The proposed model achieves decent performance comparable to the best Arabic LLMs across various Arabic benchmarks.

Copied to clipboard

Chengtao Gan, Zhiqiang Liu, Long Jin, Yushan Zhu, Lei Liang, Wen Zhang

CM-Align: Consistency-based Multilingual Alignment for Large Language Models (2025.findings-emnlp)

Challenge:	Existing unified structured data question answering methods rely on a set of predefined functions, which restricts their ability to perform complex reasoning beyond these predefined operations.
Approach:	They propose a novel adaptive code-driven framework that generates code-based reasoning operations based on a question.
Outcome:	The proposed framework improves on multiple structured datasets on real-world scenarios.

Copied to clipboard

Xue Zhang, Yunlong Liang, Fandong Meng, Songming Zhang, Yufeng Chen, Jinan Xu, Jie Zhou

ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models (2025.acl-long)

Challenge:	Current large language models (LLMs) show a significant performance gap in alignment between English and other languages.
Approach:	They propose a consistency-based method to construct high-quality multilingual preference data for improving multilingual alignment.
Outcome:	The proposed method is based on three LLMs and three common tasks and shows that it performs better than current methods.

Copied to clipboard

Hanxing Ding, Shuchang Tao, Liang Pang, Zihao Wei, Jinyang Gao, Bolin Ding, Huawei Shen, Xueqi Cheng

Student Guides Teacher: Weak-to-Strong Inference via Spectral Orthogonal Exploration (2026.acl-long)

Challenge:	Existing approaches to tool learning rely on hand-crafted prompts and natural language reasoning, making multi-step planning difficult and lacking precise error diagnosis and reflection mechanisms.
Approach:	They propose a framework that reformulates tool learning as a code generation task.
Outcome:	The proposed framework achieves superior performance in task completion accuracy and execution reliability compared to existing approaches.

Copied to clipboard

Dayu Wang, Jiaye Yang, Weikang Li, Jiahui Liang, Yang Li, Deguo Xia, Jizhou Huang

Structured Preference Optimization for Vision-Language Long-Horizon Task Planning (2025.emnlp-main)

Challenge:	Existing Large Language Models suffer from "Reasoning Collapse" on mathematical reasoning tasks where stochastic sampling produces lexical variations of the same erroneous logic rather than genuine semantic exploration.
Approach:	They propose a geometric inference framework that uses a spectral orthogonal probe to introduce semantically heterogeneous reasoning signals into the teacher's orthogonale complement of its dominant subspace.
Outcome:	The proposed framework improves accuracy and sampling efficiency over baseline methods on logic and code generation benchmarks.

Copied to clipboard

Xiwen Liang, Min Lin, Weiqi Ruan, Rongtao Xu, Yuecheng Liu, Jiaqi Chen, Bingqian Lin, Yuzheng Zhuang, Xiaodan Liang

VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs (2025.emnlp-main)

Challenge:	Existing vision-language planning methods struggle with long-horizon reasoning in dynamic environments due to the difficulty of training models to generate high-quality reasoning processes.
Approach:	They propose a framework that enhances reasoning and action selection for long-horizon task planning through structured evaluation and optimized training.
Outcome:	The proposed framework outperforms existing methods on short-horizon tasks but struggles with long-horizon reasoning in dynamic environments.

Copied to clipboard

Keer Lu, Keshi Zhao, Zhuoran Zhang, Zheng Liang, Bin Cui, Tengjiao Wang, Wentao Zhang

XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models (2023.emnlp-main)

Challenge:	Existing work focuses on domain-specific enhancements during fine-tuning, the challenge of which lies in catastrophic forgetting of knowledge across other domains.
Approach:	They propose a data composition framework that allows LLMs to enhance their multi-domain capabilities during supervised fine-tuning.
Outcome:	The proposed framework improves multi-domain fostering performance by 29.77% compared to uniform weights.

Copied to clipboard

Davis Liang, Hila Gonen, Yuning Mao, Rui Hou, Naman Goyal, Marjan Ghazvininejad, Luke Zettlemoyer, Madian Khabsa

Logic-Thinker: Teaching Large Language Models to Think more Logically. (2025.findings-emnlp)

Challenge:	Large multilingual models rely on a single vocabulary shared across 100+ languages . this vocabulary bottleneck limits the representational capabilities of multilingual model XLM-R .
Approach:	They propose a new approach for scaling to large multilingual vocabularies by de-emphasizing token sharing between languages with little lexical overlap and assigning vocabulary capacity to achieve sufficient coverage for each individual language.
Outcome:	The proposed model outperforms XLM-R on all language tasks and is particularly effective on low-resource tasks.

Copied to clipboard

Chengyao Wen, Qiang Cheng, Shaofei Wang, Zhizhen Liu, Deng Zhao, Lei Liang

ADAPT: Benchmarking Commonsense Planning under Unspecified Affordance Constraints (2026.acl-long)

Challenge:	Recent Large Reasoning Models (LRMs) have demonstrated the ability to generate long chains of thought (LongCoT) LongCoT still faces challenges such as redundancy and logical incoherence.
Approach:	They propose a neural-symbolic reasoning framework that generates chains of thought . they propose Logic-Thinker, which transforms symbolic solvers into chains of thoughts .
Outcome:	The proposed framework outperforms models fine-tuned with ThinkerCoT on logic reasoning tasks.

Copied to clipboard

Pei-An Chen, Yongching Liang, Jia-Fong Yeh, Hung-Ting Su, Yi-Ting Chen, Min Sun, Winston H. Hsu

Strength Lies in Differences! Improving Strategy Planning for Non-collaborative Dialogues via Diversified User Simulation (2024.emnlp-main)

Challenge:	Existing methods for embodied agents focus on directly executing instructions without considering whether objects can be manipulated.
Approach:	They propose a benchmark that evaluates embodied agents in dynamic environments . they use plug-and-play module that augments existing planners with explicit affordance reasoning .
Outcome:	The proposed benchmark evaluates embodied agents in dynamic environments with unpredictable affordances . ADAPT significantly improves robustness and task success across seen and unseen environments .

Copied to clipboard

Tong Zhang, Chen Huang, Yang Deng, Hongru Liang, Jia Liu, Zujie Wen, Wenqiang Lei, Tat-Seng Chua

Logical Consistency is Vital: Neural-Symbolic Information Retrieval for Negative-Constraint Queries (2025.findings-acl)

Challenge:	Non-collaborative dialogue agents are expected to engage in strategic conversations with diverse users, and this poses two main challenges for existing dialogue agents: 1) the inability to integrate user-specific characteristics into the strategic planning; 2) the difficulty of training strategic planners that can be generalized to diverse users.
Approach:	They propose to integrate a user-aware strategic planning module and a population-based training paradigm into a non-collaborative dialogue agent for securing a mutual agreement that leans favorably towards the system's objectives.
Outcome:	The proposed model can be used to achieve a mutual agreement that leans favorably towards the system's objectives.

Copied to clipboard

Ganlin Xu, Zhoujia Zhang, Wangyi Mei, Jiaqing Liang, Weijia Lu, Xiaodong Zhang, Zhifei Yang, Xiaofeng Ma, Yanghua Xiao, Deqing Yang

Leveraging Medical Literature for Section Prediction in Electronic Health Records (D19-1)

Challenge:	Current dense retrieval methods compute similarities between dense vectors but overlook the real query intents.
Approach:	They propose a neuro-symbolic information retrieval method that leverages first-order logic to optimize the embeddings of naive natural language by considering the logical consistency between queries and documents.
Outcome:	The proposed method outperforms existing methods on negative-constraint queries under zero-shot and low-resource retrieval tasks.

Copied to clipboard

Sara Rosenthal, Ken Barker, Zhicheng Liang

UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model (2023.findings-emnlp)

Challenge:	Prior approaches to section prediction have only used text data from EHRs and required significant manual annotation.
Approach:	They propose to use sections from medical literature to train models to predict sections in EHRs.
Outcome:	The proposed model uses sections from medical literature that contain similar content to those found in EHR sections.

Copied to clipboard

Jiabo Ye, Anwen Hu, Haiyang Xu, Qinghao Ye, Ming Yan, Guohai Xu, Chenliang Li, Junfeng Tian, Qi Qian, Ji Zhang, Qin Jin, Liang He, Xin Lin, Fei Huang

Social Genome: Grounded Social Reasoning Abilities of Multimodal Models (2025.emnlp-main)

Challenge:	Existing studies for visually-situated language understanding have shown shallow zero-shot visual text recognition ability when fed a low-resolution image with salient text information.
Approach:	They propose a model for universal OCR-free visually-situated language understanding based on the Multimodal Large Language Model (MLLM) their model is jointly finetuned on a wide range of visually situated language understanding tasks via a unified instruction format.
Outcome:	The proposed model achieves state-of-the-art ocr-free performance in 8 out of 10 visually-situated language understanding tasks across 5 domains: documents, tables, charts, natural images, and webpage screenshots.

Copied to clipboard

Leena Mathur, Marian Qian, Paul Pu Liang, Louis-Philippe Morency

ARCH: Efficient Adversarial Regularized Training with Caching (2021.findings-emnlp)

Challenge:	Social reasoning is a core competency of social intelligence and requires specialized neural and cognitive systems to be able to interpret multimodal interactions.
Approach:	They propose to use social reasoning traces to generate fine-grained explanations using external knowledge.
Outcome:	The proposed model is based on 272 videos of human interactions and 1,486 human-annotated reasoning traces related to inferences about these interactions.

Copied to clipboard

Simiao Zuo, Chen Liang, Haoming Jiang, Pengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu Chen, Tuo Zhao

Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation (2024.acl-long)

Challenge:	Existing approaches to regularize models require generating a perturbation for each sample in each epoch.
Approach:	They propose an adversarial regularization method where perturbations are generated and cached once every several epochs.
Outcome:	The proposed method significantly eases the computational burden (saves up to 70% of computational time) it produces a notably better (in most of the tasks) or comparable model generalization.

Copied to clipboard

Shicheng Xu, Liang Pang, Mo Yu, Fandong Meng, Huawei Shen, Xueqi Cheng, Jie Zhou

SLIDE: A Framework Integrating Small and Large Language Models for Open-Domain Dialogues Evaluation (2024.findings-acl)

Challenge:	Existing studies show that LLMs face challenges in effectively using retrieved information . authors propose a method that considers LLM as "Information Refiner"
Approach:	They propose a method that considers LLMs as "Information Refiners" they propose INFO-RAG, which is low-cost and general across various tasks .
Outcome:	The proposed method improves performance of LLaMA2 by 9.39% relative points . it is low-cost and general across various tasks, and is robust and in-context learning is possible .

Copied to clipboard

Kun Zhao, Bohao Yang, Chen Tang, Chenghua Lin, Liang Zhan

A Study of Implicit Ranking Unfairness in Large Language Models (2024.findings-emnlp)

Challenge:	Existing approaches to evaluate open domain dialogues have a one-to-many problem . existing approaches lack commonsense reasoning biases and perform poorly in domain-specific scenarios.
Approach:	They propose a framework that leverages both a small, specialised model and LLMs for the evaluation of open-domain dialogues.
Outcome:	The proposed framework achieves state-of-the-art performance in both classification and evaluation tasks and exhibits better correlation with human judgements.

Copied to clipboard

Chen Xu, Wenjie Wang, Yuxin Li, Liang Pang, Jun Xu, Tat-Seng Chua

PsychEval: A Multi-Session and Multi-Therapy Benchmark for High-Realism AI Psychological Counselor (2026.findings-acl)

Challenge:	Large language models (LLMs) have demonstrated superior ability to serve as ranking models, but they will exhibit discriminatory ranking behaviors based on users’ sensitive attributes (gender).
Approach:	They propose an evaluation method to investigate the severity of implicit ranking unfairness and a pair-wise regression method to conduct fair-aware data augmentation for LLM fine-tuning.
Outcome:	The proposed method outperforms existing methods in ranking fairness, achieving this with only a small reduction in accuracy.

Copied to clipboard

Qianjun Pan, Junyi Wang, Jie Zhou, Yutao Yang, Junsong Li, Kaiyin Xu, Yougen Zhou, Yihan Li, JingYuan Zhao, Qin Chen, Ningning Zhou, Kai Chen, Liang He

Challenge:	Existing models focus on a single therapy, but complex cases require flexible strategies among various therapies.
Approach:	They propose a multi-session, multi-therapy, and highly realistic benchmark . it is designed to address three key challenges: 1) can we train a highly realistic AI counselor? 2) How to systematically evaluate an AI counselor?"
Outcome:	The proposed benchmark is annotated with extensive professional skills and includes over 677 meta-skills and 4577 atomic skills.

Do Question Answering Modeling Improvements Hold Across Benchmarks? (2023.acl-long)

Copied to clipboard

Nelson F. Liu, Tony Lee, Robin Jia, Percy Liang

From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities (2025.findings-acl)

Challenge:	a new study finds that human-constructed and downsampled benchmarks hold more concurrence than downsampled benchmarks.
Approach:	They propose to measure concurrence between two QA benchmarks on a set of 20 models . they find that human-constructed benchmarks have high concurrence amongst themselves .
Outcome:	The proposed models hold broadly across the diverse landscape of question answering (QA) benchmarks.

Copied to clipboard

Shixin Jiang, Jiafeng Liang, Jiyuan Wang, Xuan Dong, Heng Chang, Weijiang Yu, Jinhua Du, Ming Liu, Bing Qin

Don’t Tell the Answer, Truly Guide the Reasoning During RL Rollouts (2026.findings-acl)

Challenge:	MLLMs are able to integrate multiple modalities into a single model to tackle complex tasks in real-world scenarios.
Approach:	They propose a comprehensive survey of Omni-MLLMs to address the challenges and opportunities of multimodal modeling.
Outcome:	The proposed model can integrate multiple modalities into a single model and provide novel perspectives.

Copied to clipboard

Xinyi Wang, Jinyi Han, Zishang Jiang, Tingyun li, Jiaqing Liang, Sihang Jiang, Zhaoqian Dai, Ma Shuguang, Fei Yu, Yanghua Xiao

A Review of Dataset and Labeling Methods for Causality Extraction (2020.coling-main)

Challenge:	Existing methods such as GRPO often break down when task difficulty exceeds the model’s capacity, resulting in sparse rewards and inefficient training.
Approach:	They propose to measure the compatibility between external guidance and a model's intrinsic policy by introducing an adaptive framework to enhance reasoning performance while explicitly preserving high Affinity.
Outcome:	The proposed framework outperforms baseline models while maintaining high Affinity.

Copied to clipboard

Jinghang Xu, Wanli Zuo, Shining Liang, Xianglin Zuo

CQG: A Simple and Effective Controlled Generation Framework for Multi-hop Question Generation (2022.acl-long)

Challenge:	Existing methods for causal relationship extraction are limited and lack of unified methods hinder progress in the field.
Approach:	They propose to summarize existing methods and propose a new causal sequence label method . they propose to use multiple candidate causal label sequences according to label controversy .
Outcome:	The proposed method summarises existing methods and explores their practicability and extensibility from multiple perspectives.

Copied to clipboard

Zichu Fei, Qi Zhang, Tao Gui, Di Liang, Sirui Wang, Wei Wu, Xuanjing Huang

TamEdit: Trajectory-Aware Meta-Learning for Specificity-Preserving Continual Knowledge Editing (2026.acl-long)

Challenge:	Current models can not ensure the complexity of generated questions, so they may generate shallow questions that can be answered without multi-hop reasoning.
Approach:	They propose a controlled framework to generate multi-hop questions that contain key entities in multi- hop reasoning chains and a novel Transformer-based decoder to guarantee that key entities appear in the questions.
Outcome:	The proposed model outperforms the state-of-the-art model 25% on HotpotQA.

Copied to clipboard

Shiqiang Tian, Cheng Ding, Qin Chen, Jie Zhou, Liang He

Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty (2026.findings-acl)

Challenge:	Existing methods for continual knowledge editing focus on single edits or preventing knowledge forgetting.
Approach:	They propose a meta-learning method that preserves specificity for continual knowledge editing by capturing relationships between different single edits within the trajectory.
Outcome:	Experiments show that TamEdit outperforms baselines in continual editing while preserving general capabilities.

Copied to clipboard

Chao Xue, Yao Wang, Mengqiao Liu, Di Liang, Xingsheng Han, Peiyang Liu, Xianjie Wu, Chenyao Lu, Lei Jiang, Yu Lu, Haibo Shi, Shuang Liang, Minlong Peng, Flora D. Salim

Deriving Strategic Market Insights with Large Language Models: A Benchmark for Forward Counterfactual Generation (2025.emnlp-main)

Challenge:	Existing approaches to generating reward models rely on voting-based mechanisms to evaluate CoT outputs.
Approach:	They propose an efficient generative reward modeling framework grounded in model-internal uncertainty.
Outcome:	The proposed framework reduces inference cost while improving answer accuracy.

Copied to clipboard

Keane Ong, Rui Mao, Deeksha Varshney, Paul Pu Liang, Erik Cambria, Gianmarco Mengaldo

MixRED: A Mix-lingual Relation Extraction Dataset (2024.lrec-main)

Challenge:	Existing methods for forward counterfactual generation face limitations . large language models (LLMs) offer promise but remain unexplored for this application .
Approach:	They propose a benchmark to support forward counterfactual generation in finance . they use financial news headlines to curate financial news and provide structured evaluation .
Outcome:	The proposed benchmark aims to provide scalable, automated insights into potential market opportunities and risks for stakeholders.

Copied to clipboard

Lingxing Kong, Yougang Chu, Zheng Ma, Jianbing Zhang, Liang He, Jiajun Chen

Investigating and Mitigating the Multimodal Hallucination Snowballing in Large Vision-Language Models (2024.acl-long)

Challenge:	Existing research focuses on monolingual relation extraction, but there is a significant gap in understanding relation extraction in the mix-lingual scenario.
Approach:	They propose a task of considering relation extraction in the mix-lingual scenario . they construct a human-annotated dataset to support the task .
Outcome:	The proposed task evaluates state-of-the-art supervised models and large language models on the human-annotated dataset MixRED.

Copied to clipboard

Weihong Zhong, Xiaocheng Feng, Liang Zhao, Qiming Li, Lei Huang, Yuxuan Gu, Weitao Ma, Yuan Xu, Bing Qin

Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning (2022.emnlp-main)

Challenge:	Large Vision-Language Models (LVLMs) suffer from multimodal hallucinations . however, the generated hallucines could influence the models’ subsequent generation .
Approach:	They propose a framework to evaluate LVLMs' behaviors when encountering generated hallucinations and a method to revise the output distribution of LVLs with the one derived from the residual visual input.
Outcome:	The proposed framework reduces the performance of open-source LVLMs by 31%, indicating that they are prone to accept the generated hallucinations and make false claims that they would not have supported without distractions.

Copied to clipboard

Yi Cheng, Wenge Liu, Wenjie Li, Jiashuo Wang, Ruihui Zhao, Bang Liu, Xiaodan Liang, Yefeng Zheng

Empathy in Diversity: Personalized Depression and Anxiety Therapy via Dialogue State Tracking and Patient-Aware Planning (2026.acl-long)

Challenge:	Existing research on building ES conversation systems only considered single-turn interactions with users, which is over-simplified and has limited support for multi-turn systems.
Approach:	They propose a multi-turn ES conversation system that uses lookahead heuristics to estimate future user feedback after using particular strategies.
Outcome:	The proposed system significantly outperforms baselines in both dialogue generation and strategy planning.

Copied to clipboard

Xinwei Yang, Junyi Fan, Yuqing Liu, Jiaxuan Wang, Jiashuai Zhang, Hongru Liang, Wenqiang Lei, Yao Song

ReasVQA: Advancing VideoQA with Imperfect Reasoning Process (2025.naacl-long)

Challenge:	Recent efforts have turned to large language models (LLMs) as therapeutic agents for psychological therapy tasks, yet robustness across diverse patients remains underexplored.
Approach:	They propose a realistic role-play protocol for evaluating therapeutic dialogue agents and a de-identified, expert-annotated corpus of therapist–patient dialogues.
Outcome:	The proposed framework outperforms baselines on therapeutic outcomes and dialogue quality while improving conversational efficiency.

Copied to clipboard

Jianxin Liang, Xiaojun Meng, Huishuai Zhang, Yueqian Wang, Jiansheng Wei, Dongyan Zhao

COPR: Continual Human Preference Learning via Optimal Policy Regularization (2025.findings-acl)

Challenge:	Existing approaches to VideoQA often fail when complex reasoning or temporal relationships are involved.
Approach:	They propose a method that leverages reasoning processes generated by Multimodal Large Language Models to improve VideoQA models.
Outcome:	The proposed method improves VideoQA models on three benchmarks.

Copied to clipboard

Han Zhang, Lin Gui, Yu Lei, Yuanzhao Zhai, Yehong Zhang, Zhuo Zhang, Yulan He, Hui Wang, Yue Yu, Kam-Fai Wong, Bin Liang, Ruifeng Xu

Editing Conceptual Knowledge for Large Language Models (2024.findings-emnlp)

Challenge:	Reinforcement Learning from Human Feedback (RLHF) is effective for aligning Large Language Models with human preferences, but its complex process limits its ability to continually learn human feedback.
Approach:	They propose a non-RL offline method to convert historical optimal policies into optimization constraints when continually learning new preferences.
Outcome:	The proposed method outperforms strong CL baselines in terms of reward-based evaluations and human assessment.

Copied to clipboard

Xiaohan Wang, Shengyu Mao, Shumin Deng, Yunzhi Yao, Yue Shen, Lei Liang, Jinjie Gu, Huajun Chen, Ningyu Zhang

KnowVrDU: A Unified Knowledge-aware Prompt-Tuning Framework for Visually-rich Document Understanding (2024.lrec-main)

Challenge:	Existing knowledge editing methods can modify concept-level definitions, but they can distort instantial knowledge in LLMs, leading to poor performance.
Approach:	They construct a benchmark dataset ConceptEdit and establish new metrics for evaluation to investigate the editing capability of LLMs.
Outcome:	The proposed methods can modify concept definitions but can distort instantial knowledge in LLMs, leading to poor performance.

Copied to clipboard

Yunqi Zhang, Yubo Chen, Jingzhe Zhu, Jinyu Xu, Shuai Yang, Zhaoliang Wu, Liang Huang, Yongfeng Huang, Shuai Chen

SEE: Signal Embedding Energy for Quantifying Noise Interference in Large Audio Language Models (2026.acl-long)

Challenge:	Existing methods for integrating layout and image features into pre-training language models are not suitable for few-shot settings.
Approach:	They propose to reformulate VrDU tasks into a single question-answering format with task-specific prompts and train the pre-trained model with the parameter-efficient prompt tuning method.
Outcome:	The proposed framework can be used in few-shot settings and reduces data requirements.

Copied to clipboard

Yuanhe Zhang, Jiayu Tian, Yibo Zhang, Shilinlu Yan, Liang Lin, Zhenhong Zhou, Li Sun, Sen Su

Towards Quantifiable Dialogue Coherence Evaluation (2021.acl-long)

Challenge:	Existing studies on noise lack quantitative analysis and rely on intuition and empirical observation, thus failing to understand practical robustness.
Approach:	They propose a method for quantifying the impact of noise intensity on LALM inputs by using a structured activation subspace derived from the model's internal representations.
Outcome:	The proposed method outperforms existing denoising methods and demonstrates that noise is perceived more accurately than raw audio features.

Copied to clipboard

Zheng Ye, Liucun Lu, Lishan Huang, Liang Lin, Xiaodan Liang

Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis (2022.findings-emnlp)

Challenge:	Existing automatic dialogue coherence evaluation metrics are expensive and high-latency, which cannot meet the requirements of a dialogue system.
Approach:	They propose a framework to train a quantifiable dialogue coherence metric that can reflect actual human rating standards.
Outcome:	Experimental results show that the model trained by QuantiDCE presents stronger correlations with human judgements than the other state-of-the-art metrics.

Copied to clipboard

Yuxin Xiao, Paul Pu Liang, Umang Bhatt, Willie Neiswanger, Ruslan Salakhutdinov, Louis-Philippe Morency

WAFFLE: Fine-tuning Multi-Modal Model for Automated Front-End Development (2025.acl-long)

Challenge:	Pre-trained language models (PLMs) have gained increasing popularity due to compelling prediction performance in diverse natural language processing tasks.
Approach:	They compare three popular options for encoding and Temp Scaling for PLMs . they recommend using Temp Loss as uncertainty quantifier and Focal Loss for fine-tuning .
Outcome:	Using pre-trained language models, we compare three options on NLP classification tasks and domain shift.

Copied to clipboard

Shanchao Liang, Nan Jiang, Shangshu Qian, Lin Tan

Unsupervised Preference-Aware Language Identification (2022.findings-acl)

Challenge:	Large Language Models (LLMs) have shown promise in generating source code, but two major challenges persist in UI-to-HTML code generation: (1) effectively representing HTML’s hierarchical structure for LLMs; and (2) bridging the gap between the visual nature of UI designs and the text-based format of HTML code.
Approach:	They propose a structure-aware attention mechanism that uses a contrastive fine-tuning approach to align LLMs’ understanding of UI images and HTML code.
Outcome:	The proposed model outperforms existing methods on the WebSight-Test and Design2Code benchmarks.

Copied to clipboard

Xingzhang Ren, Baosong Yang, Dayiheng Liu, Haibo Zhang, Xiaoyu Lv, Liang Yao, Jun Xie

Hawkes based Representation Learning for Reasoning over Scale-free Community-structured Temporal Knowledge Graphs (2025.coling-main)

Challenge:	Existing studies do not consider inter-personal variations due to the lack of user annotated training data.
Approach:	They propose to use user preferences to identify ambiguous texts in multilingual applications without user annotated training data to build a preference-aware LID model.
Outcome:	The proposed model significantly outperforms existing LID systems on handling ambiguous texts.

Copied to clipboard

Yuwei Du, Xinyue Liu, Wenxin Liang, Linlin Zong, Xianchao Zhang

CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models (2024.findings-acl)

Challenge:	Temporal knowledge graph reasoning is a useful tool for many practical tasks.
Approach:	They propose a Hawkes process-based Evolutional Representation Learning Network model which learns structural information and evolutional patterns of a TKG simultaneously.
Outcome:	The proposed model learns structural information and evolutional patterns of a TKG simultaneously, considering the characteristics of real-world networks: community structure, scale-free and temporal decaying.

Copied to clipboard

Yizhi Li, Ge Zhang, Xingwei Qu, Jiali Li, Zhaoqun Li, Noah Wang, Hao Li, Ruibin Yuan, Yinghao Ma, Kai Zhang, Wangchunshu Zhou, Yiming Liang, Lei Zhang, Lei Ma, Jiajun Zhang, Zuowen Li, Wenhao Huang, Chenghua Lin, Jie Fu

Beyond WER: Probing Whisper’s Sub‐token Decoder Across Diverse Language Resource Levels (2025.emnlp-main)

Challenge:	a recent study shows that large language models have limited generalization in low-resource languages like Chinese.
Approach:	They propose to evaluate the zero-shot generalizability of large language models to the Chinese language . they release only half of the dataset publicly, with the remainder kept private .
Outcome:	The Chinese Instruction-Following Benchmark evaluates the generalizability of LLMs to the Chinese language.

Copied to clipboard

Siyu Liang, Nicolas Ballier, Gina-Anne Levow, Richard Wright

What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time (2026.acl-long)

Challenge:	Large multilingual automatic speech recognition models achieve remarkable performance, but the internal mechanisms of the end-to-end pipeline remain underexplored.
Approach:	They propose to analyze Whisper's multilingual decoder to uncover systematic decoding disparities masked by aggregate error rates.
Outcome:	The proposed model performs better on higher resource languages, but lower resource languages fare worse on these metrics.

Copied to clipboard

Dong Yan, Jian Liang, Yanbo Wang, Shuo Lu, Ran He, Tieniu Tan

Generation-Distillation for Efficient Natural Language Understanding in Low-Data Settings (D19-61)

Challenge:	Existing TTRL methods rely on positive pseudo-labeling strategies to enhance reasoning capabilities.
Approach:	They propose a test-time reinforcement learning framework that mitigates label noise amplification by deriving pseudo-rewards from majority voting consensus.
Outcome:	The proposed framework mitigates label noise amplification by implementing selective positive pseudo-labeling and entropy-gated negative p-labeled pruning.

Copied to clipboard

Luke Melas-Kyriazi, George Han, Celine Liang

Original Content Is All You Need! an Empirical Study on Leveraging Answer Summary for WikiHowQA Answer Selection Task (2022.coling-1)

Challenge:	Recent research points to knowledge distillation as a potential solution for NLU tasks.
Approach:	They propose a training approach that distills large finetuned LMs into a small network using unlabeled training examples.
Outcome:	The proposed approach outperforms BERT training approaches while using 300 times fewer parameters.

Copied to clipboard

Liang Wen, Juan Li, Houfeng Wang, Yingwei Luo, Xiaolin Wang, Xiaodong Zhang, Zhicong Cheng, Dawei Yin

MoDULA: Mixture of Domain-Specific and Universal LoRA for Multi-Task Learning (2024.emnlp-main)

Challenge:	Existing answer selection approaches for community question answering lack additional answer summaries due to redundancy and lengthiness issues of crowdsourced answers.
Approach:	They constructed a dataset which contains a corresponding reference summary for each original lengthy answer.
Outcome:	The proposed model improves the performance of a question and candidate answer on a WikiHowQA dataset.

Copied to clipboard

Yufei Ma, Zihan Liang, Huangyu Dai, Ben Chen, Dehong Gao, Zhuoran Ran, Wang Zihan, Linbo Jin, Wen Jiang, Guannan Zhang, Xiaoyan Cai, Libin Yang

Beyond Rejection Sampling: Trajectory Fusion for Scaling Mathematical Reasoning (2026.findings-acl)

Challenge:	Recent advances in open-source Large Language Models (LLMs) have achieved notable successes in natural language processing.
Approach:	They propose a Parameter Efficient Fine-Tuning paradigm for improved fine-tuning and parameter efficiency in multi-task learning.
Outcome:	The proposed model outperforms existing methods on multi-task learning while reducing training costs by over 80% without losing general capability.

Copied to clipboard

Jie Deng, Hanshuang Tong, Jun Li, Shining Liang, Ning Wu, Hongzhi Li, Yutao Xie

Selection Bias Explorations and Debias Methods for Natural Language Sentence Matching Datasets (P19-1)

Challenge:	Large language models (LLMs) fine-tuned using rejection sampling retain only correct reasoning trajectories . however, this paradigm treats supervision as a binary filter that systematically excludes teacher-generated errors, leaving a gap in how reasoning failures are modeled during training.
Approach:	They propose a fine-tuning strategy that reframes rejection sampling as a structured supervision construction process.
Outcome:	The proposed approach outperforms RFT on multiple math benchmarks while retaining only correct reasoning trajectories.

Copied to clipboard

Guanhua Zhang, Bing Bai, Jian Liang, Kun Bai, Shiyu Chang, Mo Yu, Conghui Zhu, Tiejun Zhao

Is There a One-Model-Fits-All Approach to Information Extraction? Revisiting Task Definition Biases (2024.findings-emnlp)

Challenge:	Natural Language Sentence Matching (NLSM) is a popular NLP task.
Approach:	They propose to use QuoraQP to train and evaluate NLSM models using a selection bias framework.
Outcome:	The proposed framework can improve generalization ability of trained models and give more trustworthy evaluation results for real-world adoptions.

Copied to clipboard

Wenhao Huang, Qianyu He, Zhixu Li, Jiaqing Liang, Yanghua Xiao

Know What You Don’t Know: Unanswerable Questions for SQuAD (P18-2)

Challenge:	Definition bias is a negative phenomenon that can mislead models.
Approach:	They propose a framework that measures definition bias, bias-aware fine-tuning and task-specific bias mitigation to mitigate definition bias in information extraction.
Outcome:	The proposed framework mitigates definition bias in information extraction tasks by measuring definition bias, bias-aware fine-tuning, and task-specific bias mitigation.

Copied to clipboard

Pranav Rajpurkar, Robin Jia, Percy Liang

Tracing the Light of Thought: A Probabilistic Self- and Cross-Consistency Verification Mechanism Improving Mathematical Reasoning in LLMs (2026.findings-acl)

Challenge:	Existing datasets focus on answerable questions or use automatically generated unanswerable questions that are easy to identify.
Approach:	They propose a dataset that combines the Stanford Question Answering Dataset with 50,000 unanswerable questions written by crowdworkers to look similar to answerable ones.
Outcome:	The proposed dataset looks similar to answerable questions on crowd-written questions . strong neural system that gets 86% F1 on SQuAD achieves only 66% F1.

Copied to clipboard

Xiaoyang Liu, Dawei Wang, Tian Li, Huizhi Liang, Gary Ushaw, Richard Davison

VizoMem: A Visual-Textual Memory Framework for Efficient Long-Horizon Reasoning (2026.findings-acl)

Challenge:	Existing methods for evaluating reasoning paths are not efficient, but they are prone to errors.
Approach:	They propose a probabilistic self- and cross-consistency framework for mathematical reasoning that employs an accept-reject mechanism to encourage high-quality reasoning paths.
Outcome:	The proposed framework improves on 9 LLMs across 4 challenging benchmarks.

Copied to clipboard

Weijie Liang, Yuanfeng Song, Xing Chen, Caleb Chen Cao, Sirui Han, Yike Guo

Qsnail: A Questionnaire Dataset for Sequential Question Generation (2024.lrec-main)

Challenge:	Existing systems that use long-context modeling incur computational and memory overhead.
Approach:	They propose a visual memory framework that pre-rendered text into structured images and stored as visual notes for agentic systems.
Outcome:	The proposed system reduces token consumption while preserving effective long-term memory recall.

Copied to clipboard

Yan Lei, Liang Pang, Yuanzhuo Wang, Huawei Shen, Xueqi Cheng

Towards Unifying Multi-Lingual and Cross-Lingual Summarization (2023.acl-long)

Challenge:	Questionnaires are a professional research methodology used for qualitative and quantitative analysis of human opinions, preferences, and behaviors.
Approach:	They propose a questionnaire-based dataset that consists of 13,168 human-written questionnaires.
Outcome:	The proposed dataset contains 13,168 human-written questionnaires gathered from online platforms.

Copied to clipboard

Jiaan Wang, Fandong Meng, Duo Zheng, Yunlong Liang, Zhixu Li, Jianfeng Qu, Jie Zhou

Contrastive Decoding: Open-ended Text Generation as Optimization (2023.acl-long)

Challenge:	Existing work on multilingual summarization and cross-lingual summmarization has been limited due to their different definitions.
Approach:	They propose to unify MLS and CLS into a more general setting, i.e. many-to-many summarization.
Outcome:	The proposed model outperforms the state-of-the-art models in the zero-shot directions.

Copied to clipboard

Xiang Lisa Li, Ari Holtzman, Daniel Fried, Percy Liang, Jason Eisner, Tatsunori Hashimoto, Luke Zettlemoyer, Mike Lewis

Transferring from Formal Newswire Domain with Hypernet for Twitter POS Tagging (D18-1)

Challenge:	Using a language model, maximum probability is a poor decoding objective because it produces short and repetitive text.
Approach:	They propose a reliable decoding approach that optimizes a contrastive objective subject to a plausibility constraint.
Outcome:	The proposed approach outperforms four strong decoding algorithms in automatic and human evaluations across wikipedia, news and story domains.

Copied to clipboard

Tao Gui, Qi Zhang, Jingjing Gong, Minlong Peng, Di Liang, Keyu Ding, Xuanjing Huang

COCOGEC: Counterfactual Generation for Robust Grammatical Error Correction (2026.findings-acl)

Challenge:	Existing POS tagging methods for Twitter use labeled newswire text . however, Twitter users tend to mimic formal media expressions and develop linguistically informal styles.
Approach:	They propose to use newswire text to learn POS tagging for Twitter while twitter users are developing linguistically informal styles.
Outcome:	The proposed method achieves better performance than state-of-the-art methods on three different datasets.

Copied to clipboard

Qianyu Wang, Xiaoman Wang, Yuanyuan Liang, Xinyuan Li, Yunshi Lan

Localizing Malicious Outputs from CodeLLM (2025.findings-emnlp)

Challenge:	Existing GEC models fail to understand error patterns in varying contexts . a framework that generates copies of training instances with error-irrelevant contexts altered is proposed .
Approach:	They propose a framework that generates copies of training instances with error-irrelevant contexts altered.
Outcome:	The proposed framework outperforms baselines on the simulated tasks and outperformed existing models.

Copied to clipboard

Mayukh Borana, Junyi Liang, Sai Sathiesh Rajan, Sudipta Chattopadhyay

iAgent: LLM Agent as a Shield between User and Recommender Systems (2025.findings-acl)

Challenge:	Using FreqRank, we localize malicious components in outputs for triggered inputs and their corresponding backdoor triggers.
Approach:	They propose a mutation-based defense to localize malicious components in LLM outputs and their corresponding backdoor triggers.
Outcome:	The proposed defense has an average attack success rate (ASR) of 86.6% and can localize the backdoor triggers in 98% of cases.

Copied to clipboard

Wujiang Xu, Yunxiao Shi, Zujie Liang, Xuying Ning, Kai Mei, Kun Wang, Xi Zhu, Min Xu, Yongfeng Zhang

Challenge:	Traditional recommender systems focus on the user-platform paradigm, where users are directly exposed under the control of the platform's recommendation algorithms.
Approach:	They propose a user-agent-platform paradigm where agent serves as the protective shield between user and recommender system that enables indirect exposure.
Outcome:	The proposed model improves 16.6% over baselines on four datasets and mitigates echo chamber effects and reduces model bias in disadvantaged users.

Causal Intervention for Abstractive Related Work Generation (2023.findings-emnlp)

Copied to clipboard

Jiachang Liu, Qi Zhang, Chongyang Shi, Usman Naseem, Shoujin Wang, Liang Hu, Ivor Tsang

Challenge:	Existing models ignore the inherent causality during related work generation, leading to spurious correlations which downgrade the models’ generation quality and generalizability.
Approach:	They propose a Causal Intervention Module for Related Work Generation (CaM) that captures causal relationships in related work generation and implements causal interventions to mitigate the negative impact of spurious correlations.
Outcome:	The proposed framework improves the quality and coherence of generated related work by capturing causalities in the generation process.

The price of debiasing automatic metrics in natural language evalaution (P18-1)

Copied to clipboard

Arun Chaganty, Stephen Mussmann, Percy Liang

ELAD: Explanation-Guided Large Language Models Active Distillation (2024.findings-acl)

Challenge:	Existing methods to evaluate natural language systems are expensive and expensive.
Approach:	They propose to combine automatic metrics with human judgment to obtain an unbiased estimator at lower cost than human evaluation alone.
Outcome:	The proposed estimator reduces the cost of evaluating summarization and open-response questions by 7-13%.

Copied to clipboard

Yifei Zhang, Bo Pan, Chen Ling, Yuntong Hu, Liang Zhao

Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs (2024.findings-acl)

Challenge:	Large Language Models (LLMs) are hindered by their memory inefficiency, computational demands, and the high costs of API inferences.
Approach:	They propose an Explanation-Guided LLMs Active Distillation framework that employs an active learning strategy to optimize the balance between annotation costs and model performance.
Outcome:	The proposed framework significantly improves the efficiency of LLMs knowledge distillation.

Copied to clipboard

Xun Liang, Hanyu Wang, Shichao Song, Mengting Hu, Xunzhi Wang, Zhiyu Li, Feiyu Xiong, Bo Tang

Wish I Can Feel What You Feel: A Neural Approach for Empathetic Response Generation (2022.findings-emnlp)

Challenge:	Controlled Text Generation (CTG) aims to produce texts that exhibit specific desired attributes.
Approach:	They propose a pluggable CTG framework for Large Language Models to control text . they use attribute scorers to evaluate attributes of sentences and construct dynamic attribute graphs .
Outcome:	The proposed framework achieves a peak improvement of 19.29% over baseline methods in two tasks.

Copied to clipboard

Yangbin Chen, Chunfeng Liang

Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning (2021.acl-long)

Challenge:	Existing approaches focus on a single factor that affects empathy but in practice it is complex and dynamic.
Approach:	They propose a method which integrates emotion cause, knowledge graph, and communication mechanism for empathetic response generation.
Outcome:	The proposed method generates more informative and empathetic responses on a large-scale dataset.

Copied to clipboard

Pan Lu, Ran Gong, Shibiao Jiang, Liang Qiu, Siyuan Huang, Xiaodan Liang, Song-Chun Zhu

Revisiting the Negative Data of Distantly Supervised Relation Extraction (2021.acl-long)

Challenge:	Existing methods for solving geometric problems are either small in scale or not publicly available.
Approach:	They propose a large-scale benchmark for geometric problem solving using formal language and symbolic reasoning.
Outcome:	The proposed approach parses geometry problems into formal language and performs symbolic reasoning step by step.

Copied to clipboard

Chenhao Xie, Jiaqing Liang, Jingping Liu, Chengsong Huang, Wenhao Huang, Yanghua Xiao

Change Entity-guided Heterogeneous Representation Disentangling for Change Captioning (2025.findings-acl)

Challenge:	Existing methods for relation extraction with distant supervision generate plenty of training samples but noisy labels and imbalanced training data cause problems.
Approach:	They propose a method that automatically labels a sentence with relational triples from a knowledge base.
Outcome:	The proposed method outperforms existing methods even with false positive samples.

Copied to clipboard

Yi Li, Yunbin Tu, Liang Li, Li Su, Qingming Huang

RulE: Knowledge Graph Reasoning with Rule Embedding (2024.findings-acl)

Challenge:	Existing approaches to describe differences between two images are highly challenging due to distractors such as illumination and viewpoint changes.
Approach:	They propose a change-entity-guided disentanglement network that explicitly learns difference representations while mitigating the impact of distractors.
Outcome:	The proposed method outperforms existing methods on CLEVR-Change, CLE VR-DC and Spot-the-Diff datasets and achieves state-of-the art performance.

Copied to clipboard

Xiaojuan Tang, Song-Chun Zhu, Yitao Liang, Muhan Zhang

ReCoSa: Detecting the Relevant Contexts with Self-Attention for Multi-turn Dialogue Generation (P19-1)

Challenge:	Knowledge graph reasoning is an important problem for knowledge graphs.
Approach:	They propose a framework that leverages logical rules to enhance KG reasoning by learning rule embeddings from existing triplets and first-order rules.
Outcome:	The proposed framework outperforms existing embedding-based and rule-based methods on multiple benchmarks.

Copied to clipboard

Hainan Zhang, Yanyan Lan, Liang Pang, Jiafeng Guo, Xueqi Cheng

OCNLI: Original Chinese Natural Language Inference (2020.findings-emnlp)

Challenge:	Existing hierarchical recurrent encoder-decoder models treat all contexts indiscriminately, which may hurt the following response generation process.
Approach:	They propose a hierarchical recurrent encoder-decoder model that treats all contexts indiscriminately and uses a word level LSTM encoder to obtain the initial representation of each context.
Outcome:	The proposed model outperforms baseline models on Chinese customer services and English Ubuntu dialogue datasets in terms of both metric-based and human evaluations.

Copied to clipboard

Hai Hu, Kyle Richardson, Liang Xu, Lu Li, Sandra Kübler, Lawrence Moss

DCT-Centered Temporal Relation Extraction (2022.coling-1)

Challenge:	Recent efforts to extend natural language understanding to other languages have focused on (automatically) translating existing English datasets.
Approach:	They propose to use a Chinese dataset to generate annotated sentences from native speakers specializing in linguistics to elicit annotations.
Outcome:	The proposed dataset does not rely on automatic translation or non-expert annotation. instead, it elicits annotations from native speakers specializing in linguistics.

Copied to clipboard

Liang Wang, Peifeng Li, Sheng Xu

Prompt-fused Framework for Inductive Logical Query Answering (2024.lrec-main)

Challenge:	Existing work on temporal relation extraction focuses on extracting temporal relations between events . previous work on relation extraction focused on focusing on event-centered tasks .
Approach:	They propose a temporal relation extraction model that unifies events, timexes and DCT . they propose combining event mentions, time expressions and document creation time into a sentence-style model .
Outcome:	The proposed model outperforms baselines on E-E, E-T and E-D significantly.

Copied to clipboard

Zezhong Xu, Wen Zhang, Peng Ye, Lei Liang, Huajun Chen

“Yes, My LoRD.” Guiding Language Model Extraction with Locality Reinforced Distillation (2025.acl-long)

Challenge:	Existing methods for addressing logical queries on knowledge graphs neglect missing edges in KGs . Existing approaches focus on addressing missing edges, thereby neglecting the emergence of new entities .
Approach:	They propose a query-aware prompt-fused framework that addresses embedding of emerging entities . they propose to use a symbolic query to gather information relevant to the query .
Outcome:	The proposed framework addresses embedding of emerging entities through contextual information aggregation.

Copied to clipboard

Zi Liang, Qingqing Ye, Yanyun Wang, Sen Zhang, Yaxin Xiao, RongHua Li, Jianliang Xu, Haibo Hu

LLM-OREF: An Open Relation Extraction Framework Based on Large Language Models (2025.emnlp-main)

Challenge:	Existing methods for model extraction attacks on large language models are inadequate . existing methods neglect the inconsistency between training tasks and LLM alignment .
Approach:	They propose a model extraction algorithm that uses a policy-gradient-style training task to guide the crafting of preference for the local model.
Outcome:	The proposed algorithm reduces query complexity while mitigating watermark protection . it can extract various state-of-the-art commercial LLMs while minimizing query complexity .

Copied to clipboard

Hongyao Tu, Liang Zhang, Yujie Lin, Xin Lin, Haibo Zhang, Long Zhang, Jinsong Su

Boundary-Driven Table-Filling for Aspect Sentiment Triplet Extraction (2022.emnlp-main)

Challenge:	Existing studies focus on building models that can only handle predefined relations . however, their reliance on human annotation limits their practicality .
Approach:	They propose an open relation extraction framework that can generalize to new relations not encountered during training.
Outcome:	The proposed framework can generalize to new relations not encountered during training.

Copied to clipboard

Yice Zhang, Yifan Yang, Yihui Li, Bin Liang, Shiwei Chen, Yixue Dang, Min Yang, Ruifeng Xu

Low-Cost Generation and Evaluation of Dictionary Example Sentences (2024.naacl-long)

Challenge:	Existing work focuses on extracting aspect terms and opinion terms without considering the relations between aspect terms .
Approach:	They propose a task to extract aspect terms, opinion terms, and expressed sentiments from a two-dimensional (2D) table.
Outcome:	The proposed method achieves state-of-the-art on several public benchmarks and is well-suited to the ASTE task.

Copied to clipboard

Bill Cai, Ng Clarence, Daniel Liang, Shelvia Hotama

“Barking up the Right Tree”, a GAN-Based Pun Generation Model through Semantic Pruning (2024.lrec-main)

Challenge:	Prior studies have shown that language models can be trained to generate example sentences, but they relied on costly customized models and word sense datasets for generation and evaluation.
Approach:	They propose a new automatic evaluation metric called OxfordEval that measures the win-rate of generated sentences against existing Oxford Dictionary sentences.
Outcome:	The proposed model achieves over 85.1% win rate against baseline sentences compared to 39.8% win rate for prior model-generated sentences.

Copied to clipboard

JingJie Zeng, Liang Yang, Jiahao Kang, Yufeng Diao, Zhihao Yang, Hongfei Lin

Landmark-Guided Cross-Speaker Lip Reading with Mutual Information Regularization (2024.lrec-main)

Challenge:	Existing methods for generating humorous puns are limited and require a broad spectrum of commonsense and worldly skills.
Approach:	They propose a GAN-based approach that employs semantic pruning and contrastive learning to generate humorous puns using a model that captures the semantic nuances of puns.
Outcome:	The proposed model produces semantically coherent and humorous puns while ensuring both correctness and humor.

Copied to clipboard

Linzhi Wu, Xingyu Zhang, Yakun Zhang, Changyan Zheng, Tiejun Liu, Liang Xie, Ye Yan, Erwei Yin

Improving Deep Embedded Clustering via Learning Cluster-level Representations (2022.coling-1)

Challenge:	Lip reading is a process of interpreting silent speech from visual lip movements . but lip reading in cross-speaker scenarios poses a challenging problem due to inter-speech variability .
Approach:	They propose to exploit lip landmark-guided visual clues instead of mouth-cropped images as input features.
Outcome:	Experimental results show that the proposed approach reduces speaker-specific appearance characteristics in cross-speaker scenarios.

Copied to clipboard

Qing Yin, Zhihua Wang, Yunya Song, Yida Xu, Shuai Niu, Liang Bai, Yike Guo, Xian Yang

MisinfoEval: Generative AI in the Era of “Alternative Facts” (2024.emnlp-main)

Challenge:	Existing efforts to learn meaningful representations at the instance level are limited.
Approach:	They propose a deep embedded clustering model with cluster-level representation learning to jointly learn cluster and instance level representations.
Outcome:	The proposed model produces meaningful clusters on real-world short text datasets.

Copied to clipboard

Saadia Gabriel, Liang Lyu, James Siderius, Marzyeh Ghassemi, Jacob Andreas, Asuman Ozdaglar

Your Reasoning Model is Secretly a Reward Model - Optimization-Free Verification from Experience (2026.acl-long)

Challenge:	Existing efforts to address misinformation on social media platforms are hampered by user biases and scalability challenges.
Approach:	They propose a framework for generating and comprehensively evaluating large language model based misinformation interventions using a simulated social media environment and personalized explanations tailored to users' beliefs.
Outcome:	The proposed framework improves accuracy at reliability labeling by up to 41.72% and personalized explanations appeal to users' pre-existing values.

Copied to clipboard

Zhenwen Liang, Ruosen Li, Yujun Zhou, Linfeng Song, Dian Yu, Xinya Du, Haitao Mi, Dong Yu

CLAMBER: A Benchmark of Identifying and Clarifying Ambiguous Information Needs in Large Language Models (2024.acl-long)

Challenge:	Existing verifiers operate on the surface text or on confidence proxies derived from token probabilities, which can be brittle.
Approach:	They propose a training-free, non-parametric verifier that summarizes each reasoning trace by an activation delta and compares it to two class centroids computed from labeled experience.
Outcome:	The proposed model improves selection and reranking on large and less-calibrated models.

Copied to clipboard

Tong Zhang, Peixin Qin, Yang Deng, Chen Huang, Wenqiang Lei, Junhong Liu, Dingnan Jin, Hongru Liang, Tat-Seng Chua

Subjective Topic meets LLMs: Unleashing Comprehensive, Reflective and Creative Thinking through the Negation of Negation (2024.emnlp-main)

Challenge:	Large language models are used to meet user information needs, but their effectiveness in dealing with user queries that contain various types of ambiguity remains unknown.
Approach:	They propose a benchmark for evaluating large language models using a well-organized taxonomy.
Outcome:	The proposed model is based on a well-organized taxonomy and compares it with other models.

Copied to clipboard

Fangrui Lv, Kaixiong Gong, Jian Liang, Xinyu Pang, Changshui Zhang

TransGEC: Improving Grammatical Error Correction with Translationese (2023.findings-acl)

Challenge:	Large language models (LLMs) exhibit powerful reasoning capacity, but their evaluation still lacks comprehensiveness.
Approach:	They propose a framework grounded in the principle of the Negation of Negation (NeoN) to unleash the potential comprehensive, reflective, and creative thinking abilities of LLMs.
Outcome:	The proposed framework unleashes the potential comprehensive, reflective, and creative thinking abilities of large language models.

Copied to clipboard

Tao Fang, Xuebo Liu, Derek F. Wong, Runzhe Zhan, Liang Ding, Lidia S. Chao, Dacheng Tao, Min Zhang

PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering (2026.acl-long)

Challenge:	Experimental results show that data augmentation improves accuracy over strong baselines.
Approach:	They propose to use translationese as input for GEC data augmentation to overcome stylistic discrepancies . they propose to obtain human-translated texts with a more similar style to non-native texts .
Outcome:	The proposed method improves correction accuracy over strong baselines on four GEC benchmarks.

Copied to clipboard

Xiangfeng Wang, Hangyu Guo, Yanlin Lai, Mitt Huang, Liang Zhao, Chengyuan Yao, Yinmin Zhang, Qi Han, null Xiaoxiaoren, Chun Yuan, Tong Xu, Zheng Ge, Xiangyu Zhang, Daxin Jiang

M2PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning (2024.emnlp-main)

Challenge:	Current outcome-centric verification paradigms neglect potential errors in the derivation process.
Approach:	They propose a process-aware RLVR training paradigm utilizing verifiers selected via PRIME.
Outcome:	The proposed approach outperforms the baseline verification paradigm on AIME24, AIME25, and Beyond-AIME models.

Copied to clipboard

Taowen Wang, Yiyang Liu, James Liang, Junhan Zhao, Yiming Cui, Yuning Mao, Shaoliang Nie, Jiahao Liu, Fuli Feng, Zenglin Xu, Cheng Han, Lifu Huang, Qifan Wang, Dongfang Liu

C2PO: Diagnosing and Disentangling Bias Shortcuts in LLMs (2026.findings-acl)

Challenge:	Multimodal Large Language Models (MLLMs) exhibit remarkable performance across a wide range of domains.
Approach:	They propose a multimodal prompt tuning approach for efficient instruction tuning of MLLMs.
Outcome:	The proposed approach shows superior performance on multimodal evaluation datasets compared to state-of-the-art methods.

Copied to clipboard

Xuan Feng, Bo An, Tianlong Gu, Liang Chang, Fengrui Hao, Peipeng Yu, Shuai Zhao

emrQA: A Large Corpus for Question Answering on Electronic Medical Records (D18-1)

Challenge:	Existing approaches to solve large language models address stereotypical and structural biases in isolation . however, prior paradigms address these in isolation, often at the expense of exacerbating the other .
Approach:	They propose a framework to tackle latent spurious feature correlations within input that drive erroneous reasoning shortcuts.
Outcome:	The proposed framework mitigates stereotypical and structural biases while preserving robust general reasoning capabilities.

Copied to clipboard

Anusri Pampari, Preethi Raghavan, Jennifer Liang, Jian Peng

Structured Attention for Unsupervised Dialogue Structure Induction (2020.emnlp-main)

Challenge:	Existing annotations for other NLP tasks are used to generate domain-specific large-scale question answering (QA) datasets.
Approach:	They propose to re-purpose existing annotations for other NLP tasks by generating a large-scale question answering corpus using 1 million questions-logical form and 400,000+ question-answer evidence pairs.
Outcome:	The proposed model can be trained to learn domain-specific large-scale question answering (QA) datasets.

Copied to clipboard

Liang Qiu, Yizhou Zhao, Weiyan Shi, Yuan Liang, Feng Shi, Tao Yuan, Zhou Yu, Song-Chun Zhu

KaFT: Knowledge-aware Fine-tuning for Boosting LLMs’ Domain-specific Question-Answering Performance (2025.findings-acl)

Challenge:	Using structured attention, a model can learn dialogue structure in unsupervised fashion.
Approach:	They propose to incorporate structured attention layers into a Variational Recurrent Neural Network model with discrete latent states to learn dialogue structure in an unsupervised fashion.
Outcome:	The proposed model learns semantic structures similar to templates used to generate a dialogue corpus on two-party datasets and on multi-party dialogues, disentangling dialogues without human annotation.

Copied to clipboard

Qihuang Zhong, Liang Ding, Xiantao Cai, Juhua Liu, Bo Du, Dacheng Tao

A Training-Free Debiasing Framework with Counterfactual Reasoning for Conversational Emotion Detection (2023.emnlp-main)

Challenge:	Recent literature reveals that supervised fine-tuning (SFT) is suboptimal for domain-specific question-answering tasks.
Approach:	They propose a query diversification strategy for robust conflict detection and a knowledge-aware fine-tuning approach to effectively boost LLMs’ performance.
Outcome:	The proposed approach improves the model generalization and alleviates the hallucination.

Copied to clipboard

Geng Tu, Ran Jing, Bin Liang, Min Yang, Kam-Fai Wong, Ruifeng Xu

P-React: Synthesizing Topic-Adaptive Reactions of Personality Traits via Mixture of Specialized LoRA Experts (2025.findings-acl)

Challenge:	Existing studies in Emotion Recognition in Conversations (ERC) focus on capturing context-sensitive and speaker-sensitive dependencies, ignoring the unintended dataset biases of data.
Approach:	They propose a training-free debiasing framework that extracts biases from the model by generating counterfactual utterances and contexts and mitigates them using simple yet empirically robust element-wise subtraction operations.
Outcome:	Experiments on three public datasets show that the proposed framework improves generalization ability and fairness across different ERC models.

Copied to clipboard

Yuhao Dan, Jie Zhou, Qin Chen, Junfeng Tian, Liang He

Challenge:	Existing studies on personalized large language models focus on modeling explicit character profiles, while ignoring the underlying personality traits that truly shape behaviors and decision-making.
Approach:	They propose a personalized large language model (LLM) that captures implicit Big Five personality traits and integrates a Personality Specialization Loss to capture individual trait expressions.
Outcome:	The proposed model improves on Big Five personality traits and integrates a Personality Specialization Loss (PSL) to capture individual trait expressions.

RGR-KBQA: Generating Logical Forms for Question Answering Using Knowledge-Graph-Enhanced Large Language Model (2025.coling-main)

Copied to clipboard

Tengfei Feng, Liang He

Towards Modeling Role-Aware Centrality for Dialogue Summarization (2022.aacl-short)

Challenge:	Existing methods for Knowledge Base Question Answering (KBQA) face hallucination problems, resulting in low accuracy.
Approach:	They propose a retrieval-generate-retrieve framework that uses a Retrieve-Generate framework to retrieve factual knowledge from a knowledge graph.
Outcome:	Experimental results show that RGR-KBQA improves on CWQ and WebQSP datasets.

Copied to clipboard

Xinnian Liang, Chao Bian, Shuangzhi Wu, Zhoujun Li

S2LPP: Small-to-Large Prompt Prediction across LLMs (2025.findings-emnlp)

Challenge:	Existing methods for dialogue summarization consider roles separately where interactions among different roles are not fully explored.
Approach:	They propose a novel role-aware centrality model to capture role interactions by involving role prompts to control what kind of summary to generate.
Outcome:	The proposed model achieves state-of-the-art on two public benchmark datasets, CSDS and MC.

Copied to clipboard

Liang Cheng, Tianyi Li, Zhaowei Wang, Mark Steedman

DialogSum: A Real-Life Scenario Dialogue Summarization Dataset (2021.findings-acl)

Challenge:	a small model can be used to select effective prompt templates for a larger model.
Approach:	They propose a method to use a smaller model to select effective prompt templates for a larger model.
Outcome:	The proposed method significantly reduces the cost of prompt engineering while matching performance with optimal prompts among candidates.

Copied to clipboard

Yulong Chen, Yang Liu, Liang Chen, Yue Zhang

Eureka: Neural Insight Learning for Knowledge Graph Reasoning (2022.coling-1)

Challenge:	Experimental results show unique challenges in dialogue summarization such as spoken terms, special discourse structures, coreferences and ellipsis, pragmatics and social common sense.
Approach:	They propose a large-scale labeled dialogue summarization dataset . they use state-of-the-art neural models to analyze spoken dialogue summaries .
Outcome:	The proposed dataset can be used to analyze spoken dialogue summarization challenges.

Copied to clipboard

Alex X. Zhang, Xun Liang, Bo Wu, Xiangping Zheng, Sensen Zhang, Yuhui Guo, Jun Wang, Xinyao Liu

Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modeling (2025.emnlp-industry)

Challenge:	Existing knowledge embedding methods have limited performance on knowledge graph reasoning tasks . eureka is empowered to learn seen relations with sufficient training triples .
Approach:	They propose a neural insight learning framework called Eureka to bridge the “seen” to “unsea” gap . Eureca is empowered to learn seen relations with sufficient training triples while providing flexibility to learn unseen relations given only one trigger .
Outcome:	The proposed framework outperforms state-of-the-art models on seen and unseen relations . it can learn seen and unseen relationships with sufficient training triples .

Copied to clipboard

Xiaoyu Liu, Di Liang, Hongyu Shan, Peiyang Liu, Yonghao Liu, Muling Wu, Yuntao Li, Xianjie Wu, Li Miao, Jiangrong Shen, Minlong Peng

AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations (2024.findings-emnlp)

Challenge:	Generative RMs (GRMs) lack contextual and background information during inference, leading to incomplete evaluations.
Approach:	They propose a modular and interpretable framework that integrates side-branch models as auxiliary feature generators.
Outcome:	The proposed framework outperforms scalar and saline reward models in robustness and alignment with human preferences.

Copied to clipboard

Zhicheng Yang, Yinya Huang, Jing Xiong, Liang Feng, Xiaodan Liang, Yiwei Wang, Jing Tang

Agent Trading Arena: A Study on Numerical Understanding in LLM-Based Agents (2025.findings-emnlp)

Challenge:	Existing LLMs are delicate and elusive in prompt words and styles.
Approach:	They propose an LLM-acquainted prompting technique that includes proficient "native-speaking" they propose to use in-context learning to prompt LLMs to perform high-performance reasoning .
Outcome:	The proposed technique achieves step-wise prompts in zero-shot scenarios while maintaining the prompt quality.

Copied to clipboard

Tianmi Ma, Jiawei Du, Wenxin Huang, Wenjie Wang, Liang Xie, Xian Zhong, Joey Tianyi Zhou

Shallow Domain Adaptive Embeddings for Sentiment Analysis (D19-1)

Challenge:	Existing approaches to large language models are limited to historical backtesting and static data.
Approach:	a new large-language model is developed to simulate real-time trading in a virtual stock market . the agent trading arena simulates real-world bid-ask interactions and provides real-life trading scenarios .
Outcome:	The Agent Trading Arena simulates real-world market conditions and directly impacts price dynamics.

Copied to clipboard

Prathusha K Sarma, Yingyu Liang, William Sethares

MultiMET: A Multimodal Dataset for Metaphor Understanding (2021.acl-long)

Challenge:	Existing domain adaptation algorithms for text classification are limited by lack of training data and exploiting domain idiosyncrasies to improve performance.
Approach:	They propose a domain adaptation layer that learns weights to combine a generic and a specific word embedding into a DA embeddable.
Outcome:	The proposed approach improves on binary and multi-class classification tasks using popular encoder architectures.

Copied to clipboard

Dongyu Zhang, Minghao Zhang, Heting Zhang, Liang Yang, Hongfei Lin

From Mimesis to Metamorphosis: Evolving VLM Judges via In-Context Comparing and Knowledge Internalization (2026.findings-acl)

Challenge:	Metaphor is a linguistic phenomenon and a cognitive phenomenon structuring human thought, authors say . previous studies focused on texts, partly due to the unavailability of ground truth labels of multimodal metaphor .
Approach:	They propose a multimodal metaphor dataset that integrates multimodal text and image . it contains 10,437 text-image pairs with multimodal annotations of occurrences .
Outcome:	The proposed dataset examines multimodal cues and their interplay.

Copied to clipboard

Juntuo Wang, Yuming Qiao, Yifan Yang, Lunxi Yuan, Liang Luo, Dan Meng

s1: Simple test-time scaling (2025.emnlp-main)

Challenge:	Existing approaches to subjective assessment are inconsistent and inconsistent due to inconsistent scales and inherent preference biases.
Approach:	They propose a framework that operationalizes subjective assessment as comparative analysis and internalizes it via Language Buttons.
Outcome:	The proposed framework achieves state-of-the-art performance across multiple benchmarks and is scale-steerable.

Copied to clipboard

Niklas Muennighoff, Zitong Yang, Weijia Shi, Xiang Lisa Li, Li Fei-Fei, Hannaneh Hajishirzi, Luke Zettlemoyer, Percy Liang, Emmanuel Candes, Tatsunori Hashimoto

ADaPT: Token-Level Decoupling for Efficient Large Reasoning Models (2026.findings-acl)

Challenge:	OpenAI’s o1 model showed this capability but did not publicly share its methodology, leading to many replication efforts.
Approach:	They curate a small dataset s1K with 1,000 reasoning questions based on three criteria we validate through ablations: difficulty, diversity, and quality.
Outcome:	The proposed model exceeds o1-preview on competition math questions by up to 27% (MATH and AIME24).

Copied to clipboard

Tingyun li, Zishang Jiang, Jinyi Han, Xinyi Wang, Sihang Jiang, Han Xia, Zhaoqian Dai, Ma Shuguang, Fei Yu, Jiaqing Liang, Yanghua Xiao

Exploiting Noisy Data in Distant Supervision Relation Classification (N19-1)

Challenge:	Existing efficiency-oriented methods attempt to shorten or mix reasoning strategies, yet often degrade reasoning capability.
Approach:	They propose a token-level dual-process framework that explicitly decouples efficiency and correctness signals during training.
Outcome:	The proposed framework reduces inference cost while maintaining strong reasoning ability across multiple benchmarks.

Copied to clipboard

Kaijia Yang, Liang He, Xin-yu Dai, Shujian Huang, Jiajun Chen

Text Classification

Challenge:	Existing approaches to relation classification are noisy and time-consuming . RCEND uses noisy data to split noisy data into correctly and incorrectly labeled data .
Approach:	They propose a framework to enhance relation classification by exploiting noisy data . they use an instance discriminator with reinforcement learning to split noisy data into correctly and incorrectly labeled data based on the noisy data.
Outcome:	The proposed method outperforms the state-of-the-art models on relation classification . the proposed method is based on a semi-supervised learning method .

HyCoRec: Hypergraph-Enhanced Multi-Preference Learning for Alleviating Matthew Effect in Conversational Recommendation (2024.acl-long)

Copied to clipboard

Yongsen Zheng, Ruilin Xu, Ziliang Chen, Guohua Wang, Mingjie Qian, Jinghui Qin, Liang Lin

UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression (2022.emnlp-main)

Challenge:	Existing methods to study the Matthew effect in Recommender Systems (RSs) however, it is amplified when the user interacts with the system over time.
Approach:	They propose a paradigm to alleviate the Matthew effect in conversational recommendation by learning multi-aspect preferences.
Outcome:	The proposed paradigm achieves state-of-the-art performance and superior of alleviating Matthew effect in conversational recommendation tasks.

Copied to clipboard

Jiaqi Chen, Tong Li, Jinghui Qin, Pan Lu, Liang Lin, Chongyu Chen, Xiaodan Liang

AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents (2025.findings-acl)

Challenge:	Existing work on geometry problem solving treats calculation and proving as two specific tasks hindering a deep model to unify reasoning ability on multiple math tasks.
Approach:	They propose a large-scale Unified Geometry problem benchmark to unify geometry on multiple math tasks.
Outcome:	The proposed framework outperforms the existing model with 5.6% and 3.2% accuracies on calculation and proving problems.

Copied to clipboard

Yuxiang Chai, Siyuan Huang, Yazhe Niu, Han Xiao, Liang Liu, Guozhi Wang, Dingyu Zhang, Shuai Ren, Hongsheng Li

Challenge:	a new dataset is being developed to improve the capabilities of mobile GUI-control agents.
Approach:	They propose a dataset designed for generalist mobile GUI-control agents . they use screenshots from popular mobile applications to create a detailed GUI-annotated dataset .
Outcome:	The Android Multi-annotation EXpo (AMEX) is a large-scale dataset for generalist mobile GUI-control agents . it includes screenshots from popular mobile applications, which are annotated at multiple levels .

Iterative Nearest Neighbour Machine Translation for Unsupervised Domain Adaptation (2023.findings-acl)

Copied to clipboard

Hui Huang, Shuangzhi Wu, Xinnian Liang, Zefan Zhou, Muyun Yang, Tiejun Zhao

Conditional Semantic Textual Similarity via Conditional Contrastive Learning (2025.coling-main)

Challenge:	Existing methods for supervised domain adaptation of machine translation focus on fine-tuning, which is non-extensible.
Approach:	They propose to perform unsupervised domain adaptation in a non-parametric manner by using in-domain monolingual data and performing nearest neighbour inference on both forward and backward directions.
Outcome:	The proposed method significantly improves the in-domain translation performance and achieves state-of-the-art results among non-parametric methods.

Copied to clipboard

Xinyue Liu, Zeyang Qin, Zeyu Wang, Wenxin Liang, Linlin Zong, Bo Xu

The ManDi Corpus: A Spoken Corpus of Mandarin Regional Dialects (2022.lrec-1)

Challenge:	Existing methods to assess similarity between sentences encounter over-estimation problem . compared to fuzzy representations, similarity is comparatively lower in terms of "The person's age".
Approach:	They propose a conditional contrastive learning framework that constructs positive and negative samples from two perspectives.
Outcome:	The proposed method achieves state-of-the-art performance with five models based on bi-encoder and tri-encoding architectures.

Copied to clipboard

Liang Zhao, Eleanor Chodroff

Diagnosing and Remedying Representation Deficiencies for Deterministic Reasoning in KGQA (2026.acl-long)

Challenge:	Existing methods of remote speech data collection were limited by the telephone bandwidth and were therefore of low quality for phonetic research.
Approach:	They introduce a spoken corpus of regional Mandarin dialects and Standard Mandarin.
Outcome:	The proposed corpus contains 357 recordings (about 9.6 hours) of monosyllabic words, disyllable words, short sentences, a short passage and a poem, produced in standard Mandarin and in one of six regional Mandarin dialects.

Copied to clipboard

Gewen Liang, Mufan Xu, Kehai Chen, Wei Wang, Yuwei Wang, Muyun Yang, Tiejun Zhao, Min Zhang

TinyChart: Efficient Chart Understanding with Program-of-Thoughts Learning and Visual Token Merging (2024.emnlp-main)

Challenge:	Existing approaches to solve non-deterministic reasoning problems in large language models are limited by their complexity and lack of a clear understanding of the problem.
Approach:	They propose a method to diagnose and correct non-deterministic reasoning behaviors in large language models.
Outcome:	The proposed method outperforms baselines and WebQSP benchmarks on the widely used WebQ SP and CWQ benchmarks.

Copied to clipboard

Liang Zhang, Anwen Hu, Haiyang Xu, Ming Yan, Yichen Xu, Qin Jin, Ji Zhang, Fei Huang

EMTIR-GRPO: Efficient Multi-Tool Augmented Large Language Models via Reinforcement Learning (2026.findings-acl)

Challenge:	Recent studies have shown that multimodal large language models can be useful for chart understanding, but their size limits their use in resource-constrained environments.
Approach:	They propose an efficient multimodal large language model with only 3B parameters for chart understanding.
Outcome:	The proposed model outperforms several chart-understanding MLLMs with up to 13B parameters on ChartQA, Chart-to-Text, Chart to Table, OpenCQA, and ChartX.

Copied to clipboard

Shixin Jiang, Zhihao Zhu, Jiafeng Liang, Yang Wu, Ming Liu, Bing Qin

Improving Recall of Large Language Models: A Model Collaboration Approach for Relational Triple Extraction (2024.lrec-main)

Challenge:	Tool-integrated reasoning (TIR) enables large language models to invoke external tools for tasks beyond their internal capacity but often suffers from tool overuse.
Approach:	They propose an algorithm that uses a composite reward to model tool costs and tool efficiency.
Outcome:	The proposed algorithm models heterogeneous tool costs and encourages more cost-effective tool-use strategies.

Copied to clipboard

Zepeng Ding, Wenhao Huang, Jiaqing Liang, Yanghua Xiao, Deqing Yang

Bayesian Active Learning with Gaussian Processes Guided by LLM Relevance Scoring for Dense Passage Retrieval (2026.findings-acl)

Challenge:	Existing large language models can extract triples from simple sentences with few-shot learning or fine-tuning, but they often miss out when extracting from complex sentences.
Approach:	They propose an evaluation-filtering framework that integrates large language models with small models for relational triple extraction tasks.
Outcome:	The proposed framework integrates large language models with small models for relational triple extraction tasks.

Copied to clipboard

Junyoung Kim, Anton Korikov, Jiazhou Liang, Justin Cui, Yifan Simon Liu, Qianfeng Wen, Mark Zhao, Scott Sanner

FedMABench: Benchmarking Mobile GUI Agents on Decentralized Heterogeneous User Data (2025.emnlp-main)

Challenge:	Existing approaches passively rely on first-stage dense retrievers, which leads to two limitations: failing to retrieve relevant passages in semantically distinct clusters and failing to propagate relevance signals to the broader corpus.
Approach:	They propose a framework that propagates sparse LLM relevance signals across the embedding space to guide global exploration.
Outcome:	Experiments show that the proposed framework outperforms existing approaches under the same budget on all four datasets.

Copied to clipboard

WenHao Wang, Zijie Yu, Rui Ye, Jianqing Zhang, Guangyi Liu, Liang Liu, Siheng Chen, Yanfeng Wang

Challenge:	Mobile GUI agents have attracted tremendous research participation recently. traditional approaches to mobile agent training rely on centralized data collection.
Approach:	They propose a benchmark for federated training and evaluation of mobile GUI agents . they find that federation algorithms consistently outperform local training .
Outcome:	The first benchmark for federated training and evaluation of mobile GUI agents is released . it features 6 datasets with 30+ subsets, 8 federation algorithms, 10+ base models, and over 800 apps across 5 categories .

LLM-Driven Multi-Perspective Location Completion for Next Location Prediction (2026.findings-acl)

Copied to clipboard

Pengxiang Lan, Enneng Yang, Yuliang Liang, Jianzhe Zhao, Linying Jiang, Guibing Guo

Challenge:	Existing methods assume that check-in data is complete, overlooking the subjective nature of user behavior, leading to inaccurate capture of user preferences.
Approach:	They propose a framework that uses spatial coordinates to augment location completion by transforming geographic coordinates into text.
Outcome:	The proposed framework outperforms state-of-the-art methods on three real-world datasets.

ACROSS: An Alignment-based Framework for Low-Resource Many-to-One Cross-Lingual Summarization (2023.findings-acl)

Copied to clipboard

Peiyao Li, Zhengkun Zhang, Jun Wang, Liang Li, Adam Jatowt, Zhenglu Yang

Improving Simultaneous Translation by Incorporating Pseudo-References with Fewer Reorderings (2021.emnlp-main)

Challenge:	Existing studies ignore data imbalance in multilingual settings and do not utilize monolingual data.
Approach:	They propose a cross-lingual summarization model that aligns cross-linguistic data with high-resource monolingual data via contrastive and consistency loss.
Outcome:	The proposed model outperforms baseline models and consistently dominates on 45 language pairs.

Copied to clipboard

Junkun Chen, Renjie Zheng, Atsuhito Kita, Mingbo Ma, Liang Huang

Colloquial Singaporean English Style Transfer with Fine-Grained Explainable Control (2025.acl-long)

Challenge:	Existing systems for simultaneous translation are still trained on full-sentence bitexts due to the abundance of unnecessary long-distance reorderings.
Approach:	They propose to rewrite target side of existing full-sentence corpora into simultaneous-style translation by adding generated pseudo-references to the target side.
Outcome:	Experiments on ZhEn and JaEn simultaneous translation show that the proposed method improves on existing full-sentence corpora.

Copied to clipboard

Jinggui Liang, Dung Vo, Yap Hong Xian, Hai Leong Chieu, Kian Ming A. Chai, Jing Jiang, Lizi Liao

Explicit Inductive Inference using Large Language Models (2024.findings-emnlp)

Challenge:	Existing methods for style transfer between Singlish and Standard English lack explainability and fine-grained control.
Approach:	They propose a multi-agent framework where large language models act as expert agents for each linguistic aspect.
Outcome:	The proposed model enables precise, interpretable transformations, advancing explainability in NLP for Singlish.

Copied to clipboard

Tianyang Liu, Tianyi Li, Liang Cheng, Mark Steedman

ZhuJiu-Knowledge: A Fairer Platform for Evaluating Multiple Knowledge Types in Large Language Models (2024.naacl-demo)

Challenge:	Large Language Models (LLMs) suffer a signifi- cant performance drop when entailment labels disagree with the attestation label of hypothesis H.
Approach:	They propose a pipeline that exploits an LLM's attestation bias to do explicit inductive inference . they transform a premise into attested alternatives and aggregate the results .
Outcome:	The proposed pipeline improves the performance of large language models on inference tasks and alleviates the attestation bias.

Copied to clipboard

Pengfan Du, Sirui Liang, Baoli Zhang, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

UIOrchestra: Generating High-Fidelity Code from UI Designs with a Multi-agent System (2025.findings-emnlp)

Challenge:	evaluating the knowledge of large language models (LLMs) is crucial, and rapid advancement in large language modeling has heightened the importance of model evaluations.
Approach:	They propose a fairer benchmark for evaluating multiple knowledge types of LLMs by focusing on commonsense knowledge, world knowledge, and language knowledge.
Outcome:	The proposed framework evaluates 14 current mainstream LLMs and provides a detailed discussion and analysis of their results.

Copied to clipboard

Chuhuai Yue, Jiajun Chai, Yufei Zhang, Zixiang Ding, Xihao Liang, Peixin Wang, Shihai Chen, Wang Yixuan, null Wangyanping, Guojun Yin, Wei Lin

Multilingual Knowledge Editing with Language-Agnostic Factual Neurons (2025.coling-main)

Challenge:	Recent advances in large language models have significantly improved automated code generation . however, the translation of complex mobile UI designs into high-fidelity front-end code remains a challenge .
Approach:	They propose a collaborative multi-agent system to reconstruct static single-page apps from mockups.
Outcome:	The proposed system outperforms existing methods in reconstructing complex app pages . the code and data will be released upon paper acceptance .

Copied to clipboard

Xue Zhang, Yunlong Liang, Fandong Meng, Songming Zhang, Yufeng Chen, Jinan Xu, Jie Zhou

Efficient and Effective Prompt Tuning via Prompt Decomposition and Compressed Outer Product (2025.naacl-long)

Challenge:	Existing methods to update factual knowledge overlook connections of same knowledge between different languages, resulting in knowledge conflicts and limited edit performance.
Approach:	They propose a method to edit multilingual knowledge simultaneously that avoids knowledge conflicts and improves edit performance.
Outcome:	The proposed method avoids knowledge conflicts and improves edit performance on bi-ZsRE and MzsRE benchmarks.

Copied to clipboard

Pengxiang Lan, Haoyu Xu, Enneng Yang, Yuliang Liang, Guibing Guo, Jianzhe Zhao, Xingwei Wang

Dual Debiasing for Noisy In-Context Learning for Text Generation (2025.findings-acl)

Challenge:	Existing methods for fine-tuning pre-trained language models overlook intrinsic semantic associations between soft prompt tokens, leading to high discreteness and limited interactions.
Approach:	They propose a low-parameters Prompt Tuning method which leverages prompt decomposition and compressed outer product to facilitate multiple interactions among prompt tokens.
Outcome:	Experiments on six architectures and eight datasets show that the proposed method outperforms state-of-the-art methods in performance and efficiency.

Copied to clipboard

Siqi Liang, Sumyeong Ahn, Paramveer Dhillon, Jiayu Zhou

From Implicit to Explicit: Token-Efficient Logical Supervision for Mathematical Reasoning in LLMs (2026.findings-acl)

Challenge:	Existing methods detect noisy annotations by ranking local perplexities, but this assumption breaks down when the noise ratio is high and many demonstrations are flawed.
Approach:	They propose a method that uses synthesized neighbors to explicitly correct perplexity estimates, yielding a robust Sample Cleanliness Score.
Outcome:	The proposed method is comparable to a fully clean demonstration corpus and performs well even with noise ratios as high as 0.8.

Copied to clipboard

Shaojie Wang, Liang Zhang

EduBench: A Comprehensive Benchmarking Dataset for Evaluating Large Language Models in Diverse Educational Scenarios (2026.acl-long)

Challenge:	Recent studies reveal large language models lack logical reasoning abilities . logical relationship understanding is a core capability underlying genuine logical thinking .
Approach:	They propose a lightweight training framework targeting logical relationship understanding . they propose logical relation understanding framework that provides explicit supervision .
Outcome:	The proposed framework outperforms CoT-SFT training frameworks in logical relationship understanding tasks.

Copied to clipboard

Bin Xu, Yu Bai, Huashan Sun, Yiguan Lin, Siming Liu, Xinyue Liang, Yaolin Li, Zhuangzhi Dong, Jingren Zhang, Yufan Deng, Xinyu Zou, Yang Gao, Heyan Huang

Read Extensively, Focus Smartly: A Cross-document Semantic Enhancement Method for Visual Documents NER (2022.coling-1)

Challenge:	Existing benchmarks that focus on knowledge-intensive tasks do not reflect diverse educational scenarios.
Approach:	They propose a benchmark that incorporates 9 major scenarios and 4,000 educational contexts.
Outcome:	The proposed model performs comparable to state-of-the-art large models on the test set.

Copied to clipboard

Jun Zhao, Xin Zhao, WenYu Zhan, Tao Gui, Qi Zhang, Liang Qiao, Zhanzhan Cheng, Shiliang Pu

Truncation Sampling as Language Model Desmoothing (2022.findings-emnlp)

Challenge:	Existing methods to extract entities from visually-rich documents ignore the inherent multimodality of VRDs and thus the suboptimal results are achieved.
Approach:	They propose a multimodal semantic enhancement method that filters redundant information in the current document and a cross-document information awareness technique to enrich the entity-related context.
Outcome:	The proposed method outperforms existing methods on two documents understanding benchmarks covering eight languages.

Copied to clipboard

John Hewitt, Christopher Manning, Percy Liang

Lˆ2GC:Lorentzian Linear Graph Convolutional Networks for Node Classification (2024.lrec-main)

Challenge:	Long samples of text from neural language models can be of poor quality.
Approach:	They propose to think of a neural language model as a mixture of k and a true distribution that avoids infinite perplexity.
Outcome:	The proposed methods generate more plausible long documents according to humans and break out of repetition.

Copied to clipboard

Qiuyu Liang, Weihua Wang, Feilong Bao, Guanglai Gao

MapGPT: Map-Guided Prompting with Adaptive Path Planning for Vision-and-Language Navigation (2024.acl-long)

Challenge:	Existing linear GCNs perform neural network operations in Euclidean space, which do not capture tree-like hierarchical structure of graphs.
Approach:	They propose a Lorentzian linear GCN framework that maps features into hyperbolic space and performs a feature transformation to capture the underlying tree-like structure of data.
Outcome:	The proposed framework achieves state-of-the-art accuracy on standard citation networks datasets and 81.3% on PubMed datasets.

Copied to clipboard

Jiaqi Chen, Bingqian Lin, Ran Xu, Zhenhua Chai, Xiaodan Liang, Kwan-Yee Wong

Construction of a Chinese Corpus for the Analysis of the Emotionality of Metaphorical Expressions (P18-2)

Challenge:	Embodied agents equipped with GPT as their brains have extraordinary decision-making and generalization abilities across various tasks.
Approach:	They propose a map-based agent that introduces an online linguistic-formed map to encourage global exploration.
Outcome:	The proposed agent achieves state-of-the-art zero-shot performance on R2R and REVERIE simultaneously.

Copied to clipboard

Dongyu Zhang, Hongfei Lin, Liang Yang, Shaowu Zhang, Bo Xu

Let GPT be a Math Tutor: Teaching Math Word Problem Solvers with Customized Exercise Generation (2023.emnlp-main)

Challenge:	a corpus of 5,605 manually annotated sentences in Chinese is described . emotion is an abstract and vague conception, which is often described by metaphor .
Approach:	They propose to construct a corpus of metaphors annotated with emotion in Chinese . they use an annotation scheme to include linguistic metaphors, emotional categories and intensity .
Outcome:	The proposed corpus contains 5,605 manually annotated sentences in Chinese . the authors show that the corpus is large enough to analyze emotions .

Copied to clipboard

Zhenwen Liang, Wenhao Yu, Tanmay Rajpurohit, Peter Clark, Xiangliang Zhang, Ashwin Kalyan

A Quality-based Syntactic Template Retriever for Syntactically-Controlled Paraphrase Generation (2023.emnlp-main)

Challenge:	Existing approaches for distilling large language models into smaller, more efficient student models are based on educational science principles such as knowledge tracing and personalized learning.
Approach:	They propose a method for distilling large language models into smaller, more efficient student models that are aligned with educational science principles such as knowledge tracing and personalized learning.
Outcome:	The proposed approach outperforms LLMs on three benchmarks while employing significantly fewer parameters.

Copied to clipboard

Xue Zhang, Songming Zhang, Yunlong Liang, Yufeng Chen, Jian Liu, Wenjuan Han, Jinan Xu

Robust Neural Machine Translation with Joint Textual and Phonetic Embedding (P19-1)

Challenge:	Existing syntactically-controlled paraphrase generation models perform well with human-annotated or well-chosen syntaktic templates.
Approach:	They propose a quality-based Syntactic Template Retriever to retrieve templates based on the quality of the to-be-generated paraphrases.
Outcome:	The proposed algorithm can generate high-quality paraphrases without sacrificing quality.

Copied to clipboard

Hairong Liu, Mingbo Ma, Liang Huang, Hao Xiong, Zhongjun He

From Remembering to Metacognition: Do Existing Benchmarks Accurately Evaluate LLMs? (2025.findings-emnlp)

Challenge:	Neural machine translation models are sensitive to noises in input sentences . one special kind of noise is the homophone noise, where words are replaced by other words with similar pronunciations.
Approach:	They propose to embed phonetic and textual information into neural machine translation datasets to improve robustness to homophone noises.
Outcome:	The proposed method improves the robustness of neural machine translation to homophone noises on clean test sets.

Copied to clipboard

Geng Zhang, Yizhou Ying, Sihang Jiang, Jiaqing Liang, Guanglei Yue, Yifei Fu, Hailin Hu, Yanghua Xiao

Generative Reward Modeling via Synthetic Criteria Preference Learning (2025.acl-long)

Challenge:	Existing benchmark datasets focus on low-level cognitive tasks while providing limited coverage of higher-level reasoning skills.
Approach:	They analyze the cognitive depth of popular LLM benchmarks using Bloom’s Taxonomy to evaluate both the cognitive and knowledge dimensions.
Outcome:	The results show that incorporating higher-level cognitive instructions into the current instruction fine-tuning process improves model performance.

Copied to clipboard

Xiaobo Liang, Haoke Zhang, Juntao Li, Kehai Chen, Qiaoming Zhu, Min Zhang

Learning Intrinsic Dimension via Information Bottleneck for Explainable Aspect-based Sentiment Analysis (2024.lrec-main)

Challenge:	Generative Reward Models (GenRMs) leverage synthesized Chains of Thought (CoT) but this approach introduces risks of overoptimization due to the inability to guarantee the correctness of the CoTs.
Approach:	They propose a criteria-based preference tree for GenRMs that uses chain of thought to generate reasoning . they show that synthesized data can be learned using a long CoT format .
Outcome:	The proposed model shows significant improvements over baselines on multiple human preference benchmarks.

Copied to clipboard

Zhenxiao Cheng, Jie Zhou, Wen Wu, Qin Chen, Liang He

BlendSQL: A Scalable Dialect for Unifying Hybrid Question Answering in Relational Algebra (2024.findings-acl)

Challenge:	Gradient-based explanation methods are increasingly used to interpret neural models in natural language processing (NLP) however, in the context of Aspect-based Sentiment Analysis, only specific dimensions are pertinent.
Approach:	They propose a Gradient-based explanation framework that leverages an information bottleneck to refine word embeddings into a concise intrinsic dimension, maintaining essential features and omitting unrelated information.
Outcome:	The proposed framework improves both the models’ performance and explanations’ clarity by identifying sentiment-aware features.

Copied to clipboard

Parker Glenn, Parag Dakle, Liang Wang, Preethi Raghavan

MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning (2026.findings-acl)

Challenge:	Existing hybrid question answering systems use a "prompt-and-pray" paradigm . context size limitations limit ability of many transformer-based LLMs to fit into a given prompt .
Approach:	They propose a superset of SQLite to act as a unified dialect for orchestrating reasoning across unstructured and structured data.
Outcome:	The proposed framework scales to massive datasets and improves performance while using 35% fewer tokens.

Copied to clipboard

Xukai Wang, Xuanbo Liu, Mingrui Chen, Haitian Zhong, Xuanlin Yang, Bohan Zeng, Jinbo Hu, Hao Liang, Junbo Niu, Xuchen Li, Ruitao Wu, Ruichuan An, Yang Shi, Liu Liu, Qiang Liu, Zhouchen Lin, Xu-Yao Zhang, Wentao Zhang, Bin Dong

Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuning (2025.findings-acl)

Challenge:	Existing benchmarks designed to evaluate the reasoning capabilities of large models are limited in scope and lack flexibility to adapt difficulty according to evolving reasoning capacities of models.
Approach:	They propose a benchmark that incorporates multidisciplinary questions to evaluate the reasoning capabilities of large models and can adjust and update question difficulty based on the reasoning abilities of advanced models.
Outcome:	The proposed benchmark incorporates multidisciplinary questions to evaluate the reasoning capabilities of large models and can adjust and update question difficulty based on the reasoning abilities of advanced models.

Copied to clipboard

Ming Li, Pei Chen, Chenguang Wang, Hongyu Zhao, Yijun Liang, YuPeng Hou, Fuxiao Liu, Tianyi Zhou

Dynamic Generation of Multi LLM Agents Communication Topologies with Graph Diffusion Models (2026.acl-long)

Challenge:	Current instruction tuning relies on teacher models or human intervention to generate and refine the instructions and responses for training, which are costly, non-sustainable, and may lack diversity.
Approach:	They propose a human/model-free compositional data synthesis method that can create rich and diverse augmentations from existing instruction tuning data to enhance large language models.
Outcome:	The proposed method improves performance over benchmarks and reduces training costs by 80% compared with original instruction tuning.

Copied to clipboard

Eric Hanchen Jiang, Levina Li, Frank Wan, Xiao Liang, Sophia Yin, Yuchen Wu, Xinfeng Li, Yizhou Sun, Wei Wang, Kai-Wei Chang, Ying Nian Wu

Length-Adaptive Distillation: Customizing Small Language Model for Dynamic Token Pruning (2023.findings-emnlp)

Challenge:	Existing frameworks rely on static or rule-based topologies that fail to adapt to task requirements.
Approach:	They propose a generative framework that generates highly task-adaptive topologies . they validated the framework on multiple benchmarks and validated it on multiple platforms .
Outcome:	The proposed framework outperforms existing frameworks in task-adaptive communication topologies.

Copied to clipboard

Chang Liu, Chongyang Tao, Jianxin Liang, Jiazhan Feng, Tao Shen, Quzhe Huang, Dongyan Zhao

Data-Efficient Language Shaped Few-shot Image Classification (2021.findings-emnlp)

Challenge:	Existing methods to accelerate inference speed are model compression and dynamic computation (e.g., dynamic token pruning).
Approach:	They propose a two-stage knowledge distillation framework that produces a customized small language model for dynamic token pruning.
Outcome:	The proposed framework can make the small language model more customized for dynamic token pruning and achieve better speed-performance trade-off.

Copied to clipboard

Zhenwen Liang, Xiangliang Zhang

Extracting and Combining Abilities For Building Multi-lingual Ability-enhanced Large Language Models (2025.emnlp-main)

Challenge:	Existing studies have shown that language is helpful guider for image understanding by neural networks.
Approach:	They propose a language-shaped learning method that makes the best use of the few-shot images and the language available only in training.
Outcome:	The proposed method outperforms state-of-the-art methods on a few-shot dataset with limited training data.

Copied to clipboard

Zhipeng Chen, Kun Zhou, Liang Song, Xin Zhao, Bingning Wang, Weipeng Chen, Ji-Rong Wen

LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration Benchmark (2026.findings-acl)

Challenge:	Existing work relies on training with multi-lingual ability-related data, which may not be available for low-resource languages.
Approach:	They propose a multi-lingual ability-enhanced LLM that extracts language-agnostic ability-related weights from LLMs and combine them across different languages by simple addition and subtraction operations without training.
Outcome:	The proposed approach extracts language-agnostic ability-related weights from LLMs and combine them across different languages without training.

Copied to clipboard

Guangyi Liu, Pengxiang Zhao, Liang Liu, Zhiming Chen, Yuxiang Chai, Yaozhen Liang, WenHao Wang, Siheng Chen, Zhengxi Lu, Shuai Ren, Hao Wang, Shibo He, Yong Liu, Wenchao Meng

CNNs for NLP in the Browser: Client-Side Deployment and Visualization Opportunities (N18-5)

Challenge:	Mobile GUI agents show promise in automating tasks but face significant generalization challenges in long-tail scenarios.
Approach:	They propose a benchmark framework for mobile GUI agents that measures the performance of GUI agents by analyzing their performance.
Outcome:	The LearnGUI benchmark outperforms existing methods in offline and online evaluations and demonstrates consistent gains across model architectures.

Copied to clipboard

Yiyun Liang, Zhucheng Tu, Laetitia Huang, Jimmy Lin

Self-Evolution Knowledge Distillation for LLM-based Machine Translation (2025.coling-main)

Challenge:	a JavaScript implementation of a convolutional neural network performs feedforward inference completely in the browser.
Approach:	They propose a JavaScript implementation that performs feedforward inference completely in the browser.
Outcome:	The proposed model performs feedforward inference completely in the browser without server requests . the proposed model is useful for applications with stringent latency requirements or low connectivity .

Copied to clipboard

Yuncheng Song, Liang Ding, Changtong Zan, Shujian Huang

Distributionally Robust Language Modeling (D19-1)

Challenge:	Existing knowledge distillation strategies for large language models minimize output distributions between student and teacher models indiscriminately for each token.
Approach:	They propose a distillation strategy that integrates teacher and one-hot distribution of ground truth into the student distribution as prior knowledge, which promotes the distillation process.
Outcome:	The proposed method brings an average improvement of approximately 1.4 SacreBLEU points across four translation directions in the WMT22 test sets.

Copied to clipboard

Yonatan Oren, Shiori Sagawa, Tatsunori B. Hashimoto, Percy Liang

Hi-ArG: Exploring the Integration of Hierarchical Argumentation Graphs in Language Pretraining (2023.emnlp-main)

Challenge:	Language models are generally trained on data spanning a wide range of topics but might be applied to an unknown target distribution.
Approach:	They propose a distributionally robust optimization procedure which minimizes the loss of the model over the worst-case mixture of topics with sufficient overlap with the training distribution.
Outcome:	The proposed method reduces the loss of the model over the worst-case mixture of topics with sufficient overlap with the training distribution.

Copied to clipboard

Jingcong Liang, Rong Ye, Meng Han, Qi Zhang, Ruofei Lai, Xinyu Zhang, Zhao Cao, Xuanjing Huang, Zhongyu Wei

Robust Knowledge Editing via Explicit Reasoning Chains for Distractor-Resilient Multi-Hop QA (2025.findings-emnlp)

Challenge:	Recent studies have discussed its capability to assist language models for various applications.
Approach:	They propose a structure to organize arguments using the Hierarchical Argumentation Graph (Hi-ArG) and propose two approaches to exploit Hi-AarG, including a text-graph multi-modal model GreaseArR and a framework augmented with graph information.
Outcome:	The proposed structure supersedes existing language models on two argumentation tasks while incorporating graph information during further training improves vanilla language models.

Copied to clipboard

Yuchen Wu, Liang Ding, Li Shen, Dacheng Tao

Fine-tuning Pre-trained Language Models for Few-shot Intent Detection: Supervised Pre-training and Isotropization (2022.naacl-main)

Challenge:	Large language models encode vast amounts of knowledge but remain static once trained, making timely integration of emerging facts prohibitively expensive via full retraining.
Approach:	They introduce a reasoning-chain-based editing framework that steers a pretrained LLM through four structured stages to filter distractors in a single pass.
Outcome:	The proposed framework steers a pretrained LLM through four structured stages to filter distractors in a single pass.

Copied to clipboard

Haode Zhang, Haowen Liang, Yuwei Zhang, Li-Ming Zhan, Xiao-Ming Wu, Xiaolei Lu, Albert Lam

DeepPlanner: Scaling Planning Capability for Deep Research Agents via Advantage Shaping (2026.findings-acl)

Challenge:	Recent studies show that fine-tuning pre-trained language models with a small set of labeled utterances in a supervised manner is helpful, but it yields an anisotropic feature space, which may suppress the expressive power of the semantic representations.
Approach:	They propose to regularize supervised pre-training towards isotropy by contrastive learning and correlation matrix regularizers.
Outcome:	The proposed methods improve supervised pre-training by regularizing the feature space towards isotropy.

Copied to clipboard

Wei Fan, Wenlin Yao, Zheng Li, Feng Yao, Xin Liu, Liang Qiu, Qingyu Yin, Yangqiu Song, Bing Yin

Enabling Language Models to Fill in the Blanks (2020.acl-main)

Challenge:	Existing approaches to planning involve implicit planning or introduce explicit planners without systematically optimizing the planning stage.
Approach:	They propose an end-to-end RL framework that enhances the planning capabilities of deep research agents.
Outcome:	Experiments show that DeepPlanner improves planning quality and achieves state-of-the-art results under a lower training budget.

Copied to clipboard

Chris Donahue, Mina Lee, Percy Liang

A Contrastive Cross-Channel Data Augmentation Framework for Aspect-Based Sentiment Analysis (2022.coling-1)

Challenge:	Infilling is the task of predicting missing spans of text at any position in a document.
Approach:	They propose a framework which can be used to infill entire sentences . they train off-the-shelf LMs on sequences containing concatenation of masked text .
Outcome:	The proposed approach can infill entire sentences on short stories, scientific abstracts, and lyrics.

Copied to clipboard

Bing Wang, Liang Ding, Qihuang Zhong, Ximing Li, Dacheng Tao

MGM: Global Understanding of Audience Overlap Graphs for Predicting the Factuality and the Bias of News Media (2025.naacl-long)

Challenge:	Aspect-based sentiment analysis is sensitive to multi-aspect challenges, resulting in multiple aspects in a sentence.
Approach:	They propose a framework that leverages an in-domain generator to construct more multi-aspect samples . they then boost the robustness of ABSA models via contrastive learning on these generated samples ."
Outcome:	The proposed framework outperforms baselines without any augmentations on accuracy and Macro- F1 . the proposed framework can generate more multi-aspect samples and boost the robustness of ABSA models .

Copied to clipboard

Muhammad Arslan Manzoor, Ruihong Zeng, Dilshod Azizov, Preslav Nakov, Shangsong Liang

A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors (P18-1)

Challenge:	Existing methods for profiling news media focus on textual features, causing them to overlook complex relationships between entities.
Approach:	They propose a framework for profiling news media from the lens of political bias and factuality.
Outcome:	The proposed framework improves existing models and improves them by integrating structural information from similar nodes.

Copied to clipboard

Mikhail Khodak, Nikunj Saunshi, Yingyu Liang, Tengyu Ma, Brandon Stewart, Sanjeev Arora

Beyond Positive Scaling: How Negation Impacts Scaling Trends of Language Models (2023.findings-acl)

Challenge:	Existing word2vec-based methods for learning rare or unseen words have been criticized for degrading performance in small corpus settings.
Approach:	They propose a la carte embedding method that relies on a linear transformation that is efficiently learnable using pretrained word vectors and linear regression.
Outcome:	The proposed method is based on a new dataset showing that it can be used when a word is encountered even if only a single usage example is available.

Copied to clipboard

Yuhui Zhang, Michihiro Yasunaga, Zhengping Zhou, Jeff Z. HaoChen, James Zou, Percy Liang, Serena Yeung

Improving Semantic Matching through Dependency-Enhanced Pre-trained Model with Adaptive Fusion (2022.findings-emnlp)

Challenge:	Recent studies show that some tasks exhibit inverse scaling, or U-shaped scaling, where the performance degrades as models are scaled up.
Approach:	They propose a task that asks questions with negation to show positive scaling . they hypothesize that solving NeQA depends on question answering and negation understanding .
Outcome:	The proposed task can exhibit inverse scaling, U-shaped scaling, or positive scaling, and the scaling trends shift as the task is more powerful.

Copied to clipboard

Jian Song, Di Liang, Rumei Li, Yuntao Li, Sirui Wang, Minlong Peng, Wei Wu, Yongxin Yu

C-LLM: Learn to Check Chinese Spelling Errors Character by Character (2024.emnlp-main)

Challenge:	Existing work on dependency prior structure integration into pre-trained models is still unclear.
Approach:	They propose a dependency-based fusion attention paradigm which explicitly introduces dependency prior structure into pre-trained models and adaptively fuses it with semantic information.
Outcome:	The proposed model achieves state-of-the-art or competitive performance on 10 public datasets, demonstrating the benefits of adaptively fusing dependency structure in semantic matching task.

Copied to clipboard

Kunting Li, Yong Hu, Liang He, Fandong Meng, Jie Zhou

Have We Designed Generalizable Structural Knowledge Promptings? Systematic Evaluation and Rethinking (2025.acl-long)

Challenge:	Chinese Spell Checking (CSC) aims to detect and correct spelling errors in sentences.
Approach:	They propose a Chinese Spell Checking method that learns to check errors Character by Character.
Outcome:	The proposed method achieves a 2.1% enhancement in general scenarios and a significant improvement in vertical domain scenarios compared to existing methods.

Copied to clipboard

Yichi Zhang, Zhuo Chen, Lingbing Guo, Yajing Xu, Shaokai Chen, Mengshu Sun, Binbin Hu, Zhiqiang Zhang, Lei Liang, Wen Zhang, Huajun Chen

The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants (2024.acl-long)

Challenge:	Existing methods to integrate external knowledge into LLMs focus on specific problems, lacking a comprehensive exploration of the generalization and capability boundaries of SKP.
Approach:	They propose a new paradigm for structural knowledge prompting to integrate external structural knowledge into LLMs by incorporating structural representations.
Outcome:	The proposed benchmark SUBARU enables the evaluation of the generalization capabilities of SKP from four perspectives.

Copied to clipboard

Lucas Bandarkar, Davis Liang, Benjamin Muller, Mikel Artetxe, Satya Narayan Shukla, Donald Husa, Naman Goyal, Abhinandan Krishnan, Luke Zettlemoyer, Madian Khabsa

ChatMusician: Understanding and Generating Music Intrinsically with LLM (2024.findings-acl)

Challenge:	Existing benchmarks for text comprehension only cover 30 languages, but lack of labeled data is a major obstacle to building functional systems in most languages.
Approach:	They present a multiple-choice machine reading comprehension dataset spanning 122 languages . they use it to evaluate the capabilities of multilingual masked language models and large language models .
Outcome:	The proposed dataset enables the evaluation of text models in high-, medium- and low-resource languages.

Copied to clipboard

Ruibin Yuan, Hanfeng Lin, Yi Wang, Zeyue Tian, Shangda Wu, Tianhao Shen, Ge Zhang, Yuhang Wu, Cong Liu, Ziya Zhou, Liumeng Xue, Ziyang Ma, Qin Liu, Tianyu Zheng, Yizhi Li, Yinghao Ma, Yiming Liang, Xiaowei Chi, Ruibo Liu, Zili Wang, Chenghua Lin, Qifeng Liu, Tao Jiang, Wenhao Huang, Wenhu Chen, Jie Fu, Emmanouil Benetos, Gus Xia, Roger Dannenberg, Wei Xue, Shiyin Kang, Yike Guo

Improving Unsupervised Extractive Summarization with Facet-Aware Modeling (2021.findings-acl)

Challenge:	Despite LLMs' impressive capabilities in musical knowledge, music reasoning remains an unsolved task.
Approach:	They propose an open-source large language model (LLM) that integrates intrinsic musical abilities into LLaMA2 and GPT-3.5.
Outcome:	The proposed model can understand and generate music with a pure text tokenizer without external multi-modal neural structures or tokenizers.

Copied to clipboard

Xinnian Liang, Shuangzhi Wu, Mu Li, Zhoujun Li

SlotRefine: A Fast Non-Autoregressive Model for Joint Intent Detection and Slot Filling (2020.emnlp-main)

Challenge:	Existing extractive summarization methods tend to select sentences within the same facet, which leads to facet bias.
Approach:	They propose a facet-aware centrality-based ranking model that gives a weight to the sentence centrality score.
Outcome:	The proposed method outperforms baseline models on a wide range of summarization tasks and performs comparably to other models.

Copied to clipboard

Di Wu, Liang Ding, Fan Lu, Jian Xie

Capturing Minds, Not Just Words: Enhancing Role-Playing Language Models with Personality-Indicative Data (2024.findings-emnlp)

Challenge:	Slot filling and intent detection are two main tasks in spoken language understanding systems.
Approach:	They propose a non-autoregressive slot filling model with two-pass iteration mechanism to handle uncoordinated slots problem.
Outcome:	The proposed model significantly outperforms previous models in slot filling task while speeding up decoding.

Copied to clipboard

Yiting Ran, Xintao Wang, Rui Xu, Xinfeng Yuan, Jiaqing Liang, Yanghua Xiao, Deqing Yang

Label-aware Multi-level Contrastive Learning for Cross-lingual Spoken Language Understanding (2022.emnlp-main)

Challenge:	Existing role-playing models focus on character knowledge and tones, but lack personality-indicative data to capture characters' minds.
Approach:	They propose to enhance role-playing agents (RPAs) via personality-indicative data by asking psychological scales to capture broad aspects of personality traits in individuals.
Outcome:	The proposed model exhibits advanced role-playing capabilities for both general and personality-related evaluations.

Copied to clipboard

Shining Liang, Linjun Shou, Jian Pei, Ming Gong, Wanli Zuo, Xianglin Zuo, Daxin Jiang

A3: Android Agent Arena for Mobile GUI Agents with Essential-State Procedural Evaluation (2026.findings-acl)

Challenge:	Existing approaches to translate spoken language understanding into low-resource languages are limited to implicit alignment and disregard the inherent semantic structure in SLU.
Approach:	They propose to model utterance-slot-word structure by a multi-level contrastive learning framework . they also propose a label-aware joint model leveraging label semantics to enhance alignment .
Outcome:	The proposed model improves performance on two zero-shot cross-lingual datasets.

Copied to clipboard

Yuxiang Chai, Shunye Tang, Han Xiao, Weifeng Lin, Hanhao Li, Jiayu Zhang, Liang Liu, Pengxiang Zhao, Guangyi Liu, Guozhi Wang, Shuai Ren, Rongduo Han, Haining Zhang, Siyuan Huang, Hongsheng Li

Chain-of-Talkers (CoTalk): Fast Human Annotation of Dense Image Captions (2025.emnlp-main)

Challenge:	Existing evaluation methods for mobile GUI agents rely on static frame assessments or offline static apps.
Approach:	They propose an evaluation system that leverages large language models as reward models to verify task completion and process achievement.
Outcome:	The proposed system addresses the limitations of traditional function based evaluation methods on online dynamic apps.

Copied to clipboard

Yijun Shen, Delong Chen, Fan Liu, Xingyu Wang, Chuanyi Zhang, Liang Yao, Yuhui Zheng

MIND Your Reasoning: A Meta-Cognitive Intuitive-Reflective Network for Dual-Reasoning in Multimodal Stance Detection (2026.acl-long)

Challenge:	Existing approaches for optimizing human annotation efforts are limited . et al., 2015) suggest that densely annotated image captions improve vision-language alignment .
Approach:	They propose an AI-in-the-loop methodology to maximize the number of annotated samples and improve their comprehensiveness under fixed budget constraints.
Outcome:	The proposed method improves annotation speed and retrieval performance over the parallel method.

Copied to clipboard

Bingbing Wang, Zhengda Jin, Bin Liang, Wenjie Li, Jing Li, Ruifeng Xu, Min Zhang

HERALD: An Annotation Efficient Method to Detect User Disengagement in Social Conversations (2021.acl-long)

Challenge:	Existing methods operate by learning to fuse modalities, leading to frequent misjudgments.
Approach:	They propose a paradigm shift from learning to fuse to *learning the reason's process' inspired by the dual-process theory of human cognition, MIND operationalizes a self-improving loop.
Outcome:	The proposed model significantly outperforms baseline models and exhibits strong generalization.

Copied to clipboard

Weixin Liang, Kai-Hui Liang, Zhou Yu

WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning (2025.emnlp-main)

Challenge:	Existing work on detecting user disengagement requires hand-labeling many dialog samples . Currently, self-reported user ratings are constrained to a static corpus .
Approach:	They propose an efficient annotation framework that denoises dialog samples instead of manually labeling them.
Outcome:	The proposed framework improves annotation efficiency significantly and detects user disengagement in two dialog corpora.

Copied to clipboard

Zhepei Wei, Wenlin Yao, Yao Liu, Weizhi Zhang, Qin Lu, Liang Qiu, Changlong Yu, Puyang Xu, Chao Zhang, Bing Yin, Hyokun Yun, Lihong Li

Challenge:	Existing work on reinforcement learning has focused on single-turn tasks such as solving math problems.
Approach:	They propose a framework that learns directly from online interactions by asynchronously generating diverse trajectories, guided by binary rewards depending on task success.
Outcome:	Experiments on the WebArena-Lite benchmark show that the framework outperforms state-of-the-art methods and strong proprietary models.

AssoCiAm: A Benchmark for Evaluating Association Thinking while Circumventing Ambiguity (2025.emnlp-main)

Copied to clipboard

Yifan Liu, Wenkuan Zhao, Shanshan Zhong, Jinghui Qin, Mingfu Liang, Zhongzhan Huang, Wushao Wen

Challenge:	Recent advances in multimodal large language models (MLLMs) have garnered significant attention, offering a promising pathway toward artificial general intelligence (AGI).
Approach:	They propose a benchmark to evaluate associative ability while circumventing the inherent ambiguity in association tasks by decomposing ambiguities into two types and propose 'assoCiAm' they conduct extensive experiments on MLLMs, revealing a strong positive correlation between cognition and association.
Outcome:	The proposed method shows that ambiguity in association evaluations makes MLLMs more random-like and the model's behavior more random.

VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format (2025.findings-emnlp)

Copied to clipboard

Yueqian Wang, Xiaojun Meng, Yuxuan Wang, Jianxin Liang, Jiansheng Wei, Huishuai Zhang, Dongyan Zhao

A Study on Knowledge Distillation from Weak Teacher for Scaling Up Pre-trained Language Models (2023.findings-acl)

Challenge:	Recent studies on video large language models focus on model architectures and training datasets . interaction format between user and model is unsatisfactory for time-sensitive tasks .
Approach:	They propose a video-text duet interaction format that allows for continuous playback of the video . when a text message ends, the video continues to play, similar to the alternative of two performers in a duet.
Outcome:	The proposed format improves performance on time-sensitive tasks with minimal training efforts.

Copied to clipboard

Hayeon Lee, Rui Hou, Jongpil Kim, Davis Liang, Sung Ju Hwang, Alexander Min

Plot2Code: A Comprehensive Benchmark for Evaluating Multi-modal Large Language Models in Code Generation from Scientific Plots (2025.findings-naacl)

Challenge:	a study shows that DWT can be effective in the vision domain and natural language processing pre-training stages.
Approach:	They examine three key factors to optimize Distillation from Weak Teacher (DWT) DWT is a method of transferring knowledge from a weaker teacher model to a larger student model to improve its performance.
Outcome:	a new study examines three key factors to optimize DWT in NLP pre-training scenarios . the impact of teacher model quality and guidelines for adjusting the weighting value for DW T loss are examined .

Copied to clipboard

Chengyue Wu, Zhixuan Liang, Yixiao Ge, Qiushan Guo, Zeyu Lu, Jiahao Wang, Ying Shan, Ping Luo

On the Complementarity between Pre-Training and Random-Initialization for Resource-Rich Machine Translation (2022.coling-1)

Challenge:	Multi-modal Large Language Models have shown remarkable progress in visual contexts, yet their ability to convert visual figures into executable code remains underexplored.
Approach:	They propose to use a set of visual coding metrics to assess MLLMs' visual . pass rate, text-match ratio, and GPT-4V rating judgement to assess the quality of generated code and rendered images.
Outcome:	The proposed benchmark includes 132 high-quality matplotlib plots across six plot types, as well as 150 and 86 plots from Python’s and R’s plotly libraries respectively, totaling 368 plots.

Copied to clipboard

Changtong Zan, Liang Ding, Li Shen, Yu Cao, Weifeng Liu, Dacheng Tao

Data-Centric Perspectives on Agentic Retrieval-Augmented Generation: A Survey (2026.findings-acl)

Challenge:	Pre-Training (PT) of text representations has been successfully applied to low-resource Neural Machine Translation (NMT) however, it often fails to achieve notable gains on resource-rich NMT on par with its Random-Initialization (RI) counterpart.
Approach:	They propose to combine pre-training and random-initialization techniques to achieve significant improvements in NMT.
Outcome:	The proposed model fusion algorithm can achieve significant improvements on two resource-rich translation benchmarks.

Copied to clipboard

Jingwen Deng, Jihao Huang, Zhen Hao Wong, Hao Liang, Quanqing Xu, Bin Cui, Wentao Zhang

Revisiting Demonstration Selection Strategies in In-Context Learning (2024.acl-long)

Challenge:	Large Language Models (LLMs) excel at natural language understanding and generation, yet rely on static pre-training data.
Approach:	They propose to augment Large Language Models with external retrieval to ground model outputs . traditional RAG is constrained by a fixed retrieve-then-generate routine . authors aim to guide creation of high-quality datasets for next generation of adaptive LLM agents .
Outcome:	The proposed model can decompose tasks, issue exploratory queries, and refine evidence through iterative retrieval.

Copied to clipboard

Keqin Peng, Liang Ding, Yancheng Yuan, Xuebo Liu, Min Zhang, Yuanxin Ouyang, Dacheng Tao

Vanessa: Visual Connotation and Aesthetic Attributes Understanding Network for Multimodal Aspect-based Sentiment Analysis (2024.findings-emnlp)

Challenge:	Large language models (LLMs) have shown an impressive ability to perform a wide range of tasks using in-context learning (ICL).
Approach:	They propose a data- and model-dependent method to select models using in-context learning, TopK + ConE, and propose unified explanations for the effectiveness of previous methods.
Outcome:	The proposed method improves language understanding and generation tasks with different model scales.

Copied to clipboard

Luwei Xiao, Rui Mao, Xulang Zhang, Liang He, Erik Cambria

Question Tells You Where the Answer Is: Intention-aware Long-Context KV Cache Compression (2026.acl-long)

Challenge:	Existing methods to analyze images focus on superficial features or descriptions, omitting subtle contextual information.
Approach:	They propose a Visual Connotation and Aesthetic Attributes Understanding Network (Vanessa) for Multimodal Aspect-based Sentiment Analysis.
Outcome:	The proposed network captures both implicit and explicit sentimental cues and can be used to enrich textual sentiment analysis.

Copied to clipboard

Liang Zhao, Xiaocheng Feng, Weihong Zhong, Lei Huang, Kun Zhu, Baoxin Wang, Dayong Wu, Guoping Hu, Ting Liu, Bing Qin

Challenge:	Recent methods to reduce the KV cache size fail to identify crucial KVs for generation while excluding others accurately, resulting in severe information loss.
Approach:	They propose an intention-aware KV cache eviction method that identifies and retains crucial KVs according to the attention distribution of intention, which semantically reflects the user’s goal and determines which part of the context is relevant.
Outcome:	The proposed method can maintain the model performance while reducing the KV cache size from 128K to 2K, leading to a 6.3x increase in decoding speed and 7.8x enhancement in memory efficiency compared to the default setting.

Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data (N19-1)

Copied to clipboard

Wei Zhao, Liang Wang, Kewei Shen, Ruoyu Jia, Jingming Liu

EMPATH: An Ensemble Method for Automatic Fine-Grained Turn-Level Dialogue Empathy Evaluation with a Novel Emotional Distance Metric (2026.findings-acl)

Challenge:	Neural machine translation systems have become state-of-the-art approaches for Grammatical Error Correction (GEC) task.
Approach:	They propose a copy-augmented architecture for the Grammatical Error Correction task by copying unchanged words from the source sentence to the target sentence.
Outcome:	The proposed architecture outperforms all recently published state-of-the-art results by a large margin.

Copied to clipboard

Dongning Rao, Zhihua Liang, Zhihua Jiang

Learning First-Order Logic Rules for Argumentation Mining (2025.acl-long)

Challenge:	Empathy evaluation metrics are lacking in the competitions, and classical dialogue evaluation metrics require further investigation.
Approach:	They propose a framework which combines fine-tuned models, large language models, classical dialogue evaluation metrics, and a novel metric.
Outcome:	The proposed framework improves on the WASSA 2024 benchmark and shows a statistically significant 8% improvement on the EX dataset.

Copied to clipboard

Yang Sun, Guanrong Chen, Hamid Alinejad-Rokny, Jianzhu Bao, Yuqi Huang, Bin Liang, Kam-Fai Wong, Min Yang, Ruifeng Xu

Neural-Symbolic Solver for Math Word Problems with Auxiliary Tasks (2021.acl-long)

Challenge:	Argumentation Mining (AM) aims to extract argumentative structures from texts by identifying argumentation components (ACs) and their argumentative relations (ARs).
Approach:	They propose a First- Order Logic reasoning framework for AM to capture logical reasoning paths within argumentative texts.
Outcome:	The proposed framework outperforms strong baselines while significantly improving explainability.

Copied to clipboard

Jinghui Qin, Xiaodan Liang, Yining Hong, Jianheng Tang, Liang Lin

Controllable Contamination Detection for Reliable LLM Evaluation with Statistical Guarantees (2026.acl-long)

Challenge:	Existing solutions for math word problems lack explicit integration of math symbolic constraints, leading to unexplainable and unreasonable predictions.
Approach:	They propose a novel mathematical model that explicitly incorporates symbolic constraints by auxiliary tasks to enforce different symbolic reasoning.
Outcome:	The proposed solver incorporates symbolic constraints by auxiliary tasks to enforce different symbolic reasoning.

Copied to clipboard

Zheng Zhang, Qi Liu, Siyuan Liang, Ning Li, Zirui Hu, Weibo Gao, Rui Li, Zhenya Huang, Leszek Rutkowski, Baosheng Yu, Dacheng Tao

RelCLIP: Adapting Language-Image Pretraining for Visual Relationship Detection via Relational Contrastive Learning (2022.emnlp-main)

Challenge:	Existing training data detectors fail to detect clean samples from contaminated test sets . existing methods fail to identify clean samples due to black-box nature of LLMs .
Approach:	They propose a framework that detects and filters contaminated evaluation data . they propose 'failure detection' to reduce the proportion of contaminated samples mistakenly retained .
Outcome:	The proposed framework reduces false discovery rate (FDR) under valid FDR control while maintaining evaluation consistency.

Copied to clipboard

Yi Zhu, Zhaoqing Zhu, Bingqian Lin, Xiaodan Liang, Feng Zhao, Jianzhuang Liu

Stable Language Guidance for Vision–Language–Action Models (2026.acl-long)

Challenge:	Existing visual relationship detection models only use numeric ids of relation labels for training, but ignore semantic correlation between labels.
Approach:	They propose a visual Relationship prediction framework that transfers natural language knowledge from Contrastive Language-Image Pre-training models to enhance the relationship prediction.
Outcome:	The proposed framework improves visual relationship prediction by matching semantic correlations with relation triplets.

Copied to clipboard

Zhihao Zhan, Yuhao Chen, Jiaying Zhou, Qinhan Lyu, Hao Liu, Keze Wang, Liang Lin, Guangrun Wang

Toward Human-Like Evaluation for Natural Language Generation with Error Analysis (2023.acl-long)

Challenge:	Existing vision-Language-Action models are notoriously brittle to linguistic perturbations.
Approach:	They propose a probabilistic framework that disentangles physical affordance from semantic execution.
Outcome:	The proposed framework disentangles physical affordance from semantic execution.

Copied to clipboard

Qingyu Lu, Liang Ding, Liping Xie, Kanjian Zhang, Derek F. Wong, Dacheng Tao

SEEK: Segmented Embedding of Knowledge Graphs (2020.acl-main)

Challenge:	Pre-trained language models (PLMs) have been used to evaluate language generation tasks . pretrained error analysis can be used to refine the generated sentence toward higher confidence .
Approach:	They propose to combine pretrained language model based metrics with human-like error analysis to improve sentence confidence.
Outcome:	The proposed method outperforms top-scoring metrics in 19/25 settings.

Copied to clipboard

Wentao Xu, Shun Zheng, Liang He, Bin Shao, Jian Yin, Tie-Yan Liu

G-Cap: A Game Character Caption Generator (2026.acl-long)

Challenge:	Existing methods for knowledge graph embedding can not make a proper trade-off between the model complexity and the model expressiveness, which makes them far from satisfactory.
Approach:	They propose a lightweight modeling framework that can achieve highly competitive relational expressiveness without increasing the model complexity.
Outcome:	The proposed framework can achieve highly competitive relational expressiveness without increasing model complexity.

Copied to clipboard

Yang Yang, Feng Hu, Haiming Zhang, XU Cheng, Gui Zheng, Liang Yao, Wenqi Ren

ToNER: Type-oriented Named Entity Recognition with Generative Language Model (2024.lrec-main)

Challenge:	Existing studies on Large Vision-Language Models (LVLMs) primarily focus on real-world scenarios, leaving surreal, highly stylized, and semantically hybrid virtual-world situations significantly underexplored.
Approach:	They propose to use a manually annotated benchmark to evaluate LVLMs' ability to perceive and describe game character from the virtual-world.
Outcome:	The proposed task evaluates LVLMs’ ability to perceive and describe game character from the virtual-world.

Copied to clipboard

Guochao Jiang, Ziqin Luo, Yuchen Shi, Dixuan Wang, Jiaqing Liang, Deqing Yang

On the Copying Behaviors of Pre-Training for Neural Machine Translation (2021.findings-acl)

Challenge:	Input too many potential entity types would distract the model inevitably.
Approach:	They propose to use a generative model to exploit entity types' merit on promoting NER task by appending a type matching model to identify the entity types most likely to appear in the sentence.
Outcome:	The proposed framework exploits entity types' merit on promoting NER task by adding auxiliary task to the model to discover the entity types.

Copied to clipboard

Xuebo Liu, Longyue Wang, Derek F. Wong, Liang Ding, Lidia S. Chao, Shuming Shi, Zhaopeng Tu

DSQG-Syn: Synthesizing High-quality Data for Text-to-SQL Parsing by Domain Specific Question Generation (2025.findings-naacl)

Challenge:	Existing studies show that initializing NMT models with pre-trained language models (LM) can speed up the model training and boost the model performance.
Approach:	They propose a method to control copying behaviors in NMT models by initializing them with pre-trained language models (LM) they propose to use a metric called copy ratio to control the copying behavior in decoding.
Outcome:	The proposed method improves translation performance by controlling copying behaviors for pre-training based models.

Copied to clipboard

Shaoming Duan, Youxuan Wu, Chuanyi Liu, Yuhao Zhang, Zirui Wang, Peiyi Han, Shengyuan Yu, Liang Yan, Yingwei Liang

Multi-View Document Representation Learning for Open-Domain Dense Retrieval (2022.acl-long)

Challenge:	Existing methods for generating SQL queries using natural language questions produce inconsistent NLQ-SQL pairs.
Approach:	They propose a text-to-SQL data synthesis framework that generates domain-relevant questions . they synthesize NLQ-SqL pairs that are domain-specific and intent-consistent .
Outcome:	The proposed method outperforms closed-source LLMs on the Text-to-SQL task.

Copied to clipboard

Shunyu Zhang, Yaobo Liang, Ming Gong, Daxin Jiang, Nan Duan

Decomposing Argumentative Essay Generation via Dialectical Planning of Complex Reasoning (2024.findings-acl)

Challenge:	Existing methods for dense retrieval are hard to match with multiple views.
Approach:	They propose a multi-view document representation learning framework to generate multiple embeddings through viewers to represent documents and enforce them to align with different queries.
Outcome:	The proposed method outperforms recent works and achieves state-of-the-art results.

Copied to clipboard

Yuhang He, Jianzhu Bao, Yang Sun, Bin Liang, Min Yang, Bing Qin, Ruifeng Xu

Modeling Multi-Granularity Hierarchical Features for Relation Extraction (2022.naacl-main)

Challenge:	Argumentative Essay Generation (AEG) is a challenging task in computational argumentation, where detailed logical reasoning and effective rhetorical skills are essential.
Approach:	They propose an argumentative planning strategy for prompting large language models to generate high-quality essays by sketch planning and dialectical planning.
Outcome:	The proposed method generates more dialectical and persuasive essays with higher diversity compared to baselines.

Copied to clipboard

Xinnian Liang, Shuangzhi Wu, Mu Li, Zhoujun Li

NL ⇒ Schedule: Evaluate Multitask Scheduling Capability of Large Language Models (2026.acl-long)

Challenge:	Existing work on relation extraction focuses on constructing explicit structured features using knowledge graph and dependency tree.
Approach:	They propose a method to extract multi-granularity features based solely on the original input sentences.
Outcome:	The proposed method outperforms state-of-the-art models that even use external knowledge on three public benchmarks: SemEval 2010 Task 8, Tacred, and Tacred Revisited.

Copied to clipboard

Wenrui Liao, Weihong Du, Yi Li, Hongru Liang, Wenqiang Lei

ChemAmp: Amplified Chemistry Tools via Composable Agents (2026.findings-acl)

Challenge:	Existing methods for scheduling from natural language descriptions rely on experts with limited scheduling skills and domain knowledge.
Approach:	They propose a model to generate a feasible schedule from natural language descriptions.
Outcome:	The proposed framework achieves more robust performance than six state-of-the-art LLM+solver methods.

Copied to clipboard

Zhucong Li, Powei Chang, Jin Xiao, Zhijian Zhou, Qianyu He, Jiaqing Liang, Fenglei Cao, Xu Yinghui, Yuan Qi

Challenge:	LLM-based agents are powerful tools for automating complex scientific workflows, especially in chemistry, but their single-task performance is limited by tool constraints.
Approach:	They propose a framework that optimizes the collective capabilities of specialized tools by dynamic coordination within individual tasks.
Outcome:	The proposed framework outperforms chemistry-specialized models, generalist LLMs, and agent systems with tool orchestration.

Don’t Take It Literally: An Edit-Invariant Sequence Loss for Text Generation (2022.naacl-main)

Copied to clipboard

Guangyi Liu, Zichao Yang, Tianhua Tao, Xiaodan Liang, Junwei Bao, Zhen Li, Xiaodong He, Shuguang Cui, Zhiting Hu

A Query-Response Framework for Whole-Page Complex-Layout Document Image Translation with Relevant Regional Concentration (2025.findings-acl)

Challenge:	Neural text generation models are typically trained by maximizing log-likelihood with the sequence cross entropy (CE) loss.
Approach:	They propose an Edit-Invariant Sequence Loss method which computes the matching loss of a target sequence with all n-grams in the generated sequence.
Outcome:	The proposed method outperforms the common CE loss and strong baselines on a wide range of tasks.

Copied to clipboard

Zhiyang Zhang, Yaping Zhang, Yupu Liang, Zhiyuan Chen, Lu Xiang, Yang Zhao, Yu Zhou, Chengqing Zong

BAR: A Backward Reasoning based Agent for Complex Minecraft Tasks (2025.findings-acl)

Challenge:	Existing methods for document image translation rely on the vanilla encoder-decoder paradigm . a novel dynamic aggregation mechanism is designed to enhance the text semantics in query features toward translation.
Approach:	They propose a Query-Response DIT framework that reformulates the DIT task into a parallel response/translation process of multiple queries.
Outcome:	The proposed framework improves translation quality on four translation directions on three benchmarks.

Copied to clipboard

Weihong Du, Wenrui Liao, Binyu Yan, Hongru Liang, Anthony G Cohn, Wenqiang Lei

MAVIS: Multi-Agent Video Retrieval via Structured Video Understanding (2026.findings-acl)

Challenge:	Existing studies focus on forward reasoning based planning, but this paradigm doesn't work well for complex tasks.
Approach:	They propose to decompose a task into easily executed steps by planning and use a backward reasoning based agent to make the planning starting from the terminal state.
Outcome:	The proposed model outperforms existing methods and the proposed modules in a virtual environment that simulates complex tasks based on real-world scenarios.

Copied to clipboard

Jie Zhang, Qilang Ye, Hao Zhou, Haochen Liang, Fei Luo

Redistributing Low-Frequency Words: Making the Most of Monolingual Data in Non-Autoregressive Translation (2022.acl-long)

Challenge:	Existing methods for video retrieval rely on embedding-based full-corpus scanning, but there is a bottleneck in semantic asymmetry and computational redundancy.
Approach:	They propose a multi-agent framework that rethinks retrieval as cooperative reasoning . they parse raw videos into a structured semantic library, enabling explicit attribute-level indexing .
Outcome:	The proposed framework bridges the granularity mismatch gap by parsing raw videos into a structured semantic library . it employs a Logic-aware Debate mechanism with a strict veto protocol . the proposed framework achieves competitive performance without task-specific fine-tuning .

Copied to clipboard

Liang Ding, Longyue Wang, Shuming Shi, Dacheng Tao, Zhaopeng Tu

GLA: Grounding Large Language Models in Molecular Hierarchy for Chemical Understanding (2026.findings-acl)

Challenge:	Knowledge distillation (KD) is the preliminary step for training non-autoregressive translation models, but it can lose important information for translating low-frequency words.
Approach:	They propose a knowledge distillation method which trains NAT student on external monolingual data with AT teacher trained on the original bilingual data.
Outcome:	Extensive experiments on eight WMT benchmarks show that monolingual KD outperforms the standard KD by improving low-frequency word translation without introducing any computational cost.

Copied to clipboard

Yingxu Li, Jingjie Zeng, Zekun Wang, Hongfei Lin, Liang Yang

Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration (2024.emnlp-main)

Challenge:	Existing molecule-language models obscure the hierarchical organization of chemical semantics . Existing models rely on linear or uniform encodings, causing structural distortion .
Approach:	They propose a framework that integrates intrinsic molecular topology into large language models.
Outcome:	The proposed framework improves on cross-modal retrieval, captioning, and property prediction benchmarks.

Copied to clipboard

Kangxi Wu, Liang Pang, Huawei Shen, Xueqi Cheng

StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer (2021.naacl-main)

Challenge:	Large language models (LLMs) are difficult to interpret due to their black-box nature and randomness.
Approach:	They propose a new method which enhances influence functions by addressing fitting errors by eliminating knowledge bias present in the base model before fine-tuning.
Outcome:	The proposed method outperforms existing methods and achieves an average AUC of 91.64%.

Copied to clipboard

Yiwei Lyu, Paul Pu Liang, Hai Pham, Eduard Hovy, Barnabás Póczos, Ruslan Salakhutdinov, Louis-Philippe Morency

TAG : Type Auxiliary Guiding for Code Comment Generation (2020.acl-main)

Challenge:	Existing methods for text style transfer focus on individual high-level semantic changes but do not offer fine-grained control of sentence structure, emphasis, and content.
Approach:	They propose a large-scale text style transfer benchmark with 21 fine-grained stylistic changes across atomic lexical, syntactic, semantic, and thematic transfers.
Outcome:	The proposed method allows modeling fine-grained changes as building blocks for more complex, high-level transfers.

Copied to clipboard

Ruichu Cai, Zhihao Liang, Boyan Xu, Zijian Li, Yuexing Hao, Yao Chen

DORM: Preference Data Weights Optimization for Reward Modeling in LLM Alignment (2025.findings-emnlp)

Challenge:	Existing code comment generation approaches ignore type information of interpretation of the code, e.g., operator, string, etc. Existing approaches ignore the type information due to the hierarchical dependence among the type.
Approach:	They propose an encoder-decoder framework which considers the source code as an N-ary tree with type information associated with each node.
Outcome:	The proposed framework is based on a Type Auxiliary Guiding encoder-decoder framework and a type-restricted Decoder to resolve training difficulties.

Copied to clipboard

Rongzhi Zhang, Chenwei Zhang, Xinyang Zhang, Liang Qiu, Haoming Jiang, Yuchen Zhuang, Qingru Zhang, Hyokun Yun, Xian Li, Bing Yin, Tuo Zhao, Chao Zhang

Challenge:	Existing approaches to align large language models with human preferences are noisy and varying in importance of preference samples.
Approach:	a new method enhances reward modeling by learning to dynamically weigh preference data.
Outcome:	a new method improves the performance of large language models with human preferences . it initializes data importance and iteratively refines them to maximize validation performance.

Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning (2026.findings-acl)

Copied to clipboard

Haolin Liu, Dian Yu, Sidi Lu, Yujun Zhou, Rui Liu, Zhenwen Liang, Haitao Mi, Chen-Yu Wei, Dong Yu

Listening to Patients: Detecting and Mitigating Patient Misreport in Medical Dialogue System (2025.findings-acl)

Challenge:	Existing reinforcement learning methods rely on sparse outcome rewards, which fail to credit correct intermediate steps in partially successful solutions.
Approach:	They propose a process reward model that rewards correct steps only when they detect errors . they propose VPPO, which rewards the correct prefix and an erroneous suffix .
Outcome:	a new approach outperforms sparse-reward RL and prior PRM-guided baselines on Pass@1 and Pass@K . a process reward model (PRM) outperformed sparser-rebound RL on multiple reasoning benchmarks .

Copied to clipboard

Lang Qin, Yao Zhang, Hongru Liang, Adam Jatowt, Zhenglu Yang

ATG: Benchmarking Automated Theorem Generation for Generative Language Models (2024.findings-naacl)

Challenge:	Medical Dialogue Systems (MDSs) aim to provide automated healthcare support through natural language interactions between patients and system agents.
Approach:	They propose a framework that detects misreports and mitigates them by generating controlled clarifying questions.
Outcome:	The proposed framework can detect misreports and mitigate them through generating controlled clarifying questions.

Copied to clipboard

Xiaohan Lin, Qingxing Cao, Yinya Huang, Zhicheng Yang, Zhengying Liu, Zhenguo Li, Xiaodan Liang

VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Search (2025.acl-long)

Challenge:	Existing generative language models (LMs) can generate new or reusable theorems, but their ability to generate new theorels is under-explored.
Approach:	They propose to use Metamath library to generate new theorems that can be saved as reusable knowledge for future theoretical proving.
Outcome:	The proposed benchmark evaluates whether an agent can generate valuable (and possibly brand new) theorems that are applicable for downstream theoretic proving as reusable knowledge.

Copied to clipboard

Yikun Wang, Siyin Wang, Qinyuan Cheng, Zhaoye Fei, Liang Ding, Qipeng Guo, Dacheng Tao, Xipeng Qiu

KERS: A Knowledge-Enhanced Framework for Recommendation Dialog Systems with Multiple Subgoals (2021.findings-emnlp)

Challenge:	Existing approaches to large vision-language models fail to capture interleaved nature of human visual-verbal reasoning processes.
Approach:	They propose a framework that integrates visuospatial and linguistic domains to facilitate multimodal slow thinking by enabling progressive visual-textual reasoning.
Outcome:	Experiments show that VisuoThink significantly improves reasoning capabilities even without fine-tuning.

Copied to clipboard

Jun Zhang, Yan Yang, Chencai Chen, Liang He, Zhou Yu

Unilaw-R1: A Large Language Model for Legal Reasoning with Reinforcement Learning and Iterative Inference (2025.emnlp-main)

Challenge:	Existing frameworks for multi-subgoal dialogs require a system to build a social bond with users to gain trust and develop affinity.
Approach:	They propose a framework for common knowledge-based multi-subgoal dialogs that divides up conversations with multiple subgoals and propose mechanisms to filter noisy knowledge and to include cleaned knowledge in the dialog response generation process.
Outcome:	The proposed framework obtains state-of-the-art results on a DuRecDial dataset in both automatic and human evaluation.

Copied to clipboard

Hua Cai, Shuang Zhao, Liang Zhang, Xuli Shen, Qing Xu, Weilin Shen, Zihao Wen, Tianke Ban

Type-enriched Hierarchical Contrastive Strategy for Fine-Grained Entity Typing (2022.coling-1)

Challenge:	Reasoning-focused large language models (LLMs) are rapidly evolving across various domains, yet their capabilities in handling complex legal problems remain underexplored.
Approach:	They propose a large language model tailored for legal reasoning with a 7-billion parameter scale and a two-stage training strategy combining Supervised Fine-Tuning and Reinforcement Learning.
Outcome:	The proposed model outperforms all models of similar scale on authoritative benchmarks and outperformed Qwen-2.5-7B-Instruct (46.6%) by an average margin of 6.6%.

Copied to clipboard

Xinyu Zuo, Haijin Liang, Ning Jing, Shuang Zeng, Zhou Fang, Yu Luo

MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts (2024.emnlp-main)

Challenge:	Experimental results show that fine-grained entity typing (FET) can be used to deduce specific semantic types of entities.
Approach:	They propose a type-enriched hierarchical contrastive strategy to model type differences . their method can make type information directly perceptible and improve distinguishability .
Outcome:	The proposed method can model the differences between hierarchical types and distinguish multi-grained similar types at different granularities.

Copied to clipboard

Haofei Yu, Zhengyang Qi, Lawrence Jang, Russ Salakhutdinov, Louis-Philippe Morency, Paul Pu Liang

RECAL: Sample-Relation Guided Confidence Calibration over Tabular Data (2023.findings-emnlp)

Challenge:	Multimodal models focus on the correspondence between images and text, but this only covers a subset of real-world interactions.
Approach:	They propose an approach to enhance multimodal models by training separate expert models for each type of interaction, such as redundancy present in both modalities, uniqueness in one modality, or synergy that emerges when both . modality is used to capture overlaps in semantic content between images and text, making a strong multi-view redundancies assumption.
Outcome:	The proposed approach improves on a sarcasm detection and humor detection task.

Copied to clipboard

Wang HaoTian, Zhen Zhang, Mengting Hu, Qichao Wang, Liang Chen, Yatao Bian, Bingzhe Wu

RNNs can generate bounded hierarchical languages with optimal memory (2020.emnlp-main)

Challenge:	Various machine learning methods for tabular data lack accurate confidence estimation, which is needed for high-risk sensitive applications such as credit modeling and financial fraud detection.
Approach:	They propose a general post-training confidence calibration framework to calibrate the confidence of current machine learning models by employing graph neural networks to model the relationships between different samples.
Outcome:	The proposed framework improves the confidence estimation on tabular datasets by using graph neural networks to model the relationships between different samples.

Copied to clipboard

John Hewitt, Michael Hahn, Surya Ganguli, Percy Liang, Christopher D. Manning

EventWeave: A Dynamic Framework for Capturing Core and Supporting Events in Dialogue Systems (2026.acl-long)

Challenge:	Existing studies have shown that RNNs can efficiently generate bounded hierarchical languages with high syntactic fidelity, but their success is not well-understood theoretically.
Approach:	They propose a language of well-nested brackets and m-bounded nesting depth . they prove that an RNN with O(m log k) hidden units suffices, an exponential reduction in memory, by an explicit construction.
Outcome:	The proposed language is well-nested brackets and has m-bounded nesting depth . it shows that an RNN with O(m log k) hidden units suffices, an exponential reduction in memory, by an explicit construction.

Copied to clipboard

Zhengyi Zhao, Shubo Zhang, Yiming Du, Bin Liang, Baojun Wang, Zhongyang Li, Binyang Li, Kam-Fai Wong

Self-Evolution Learning for Mixup: Enhance Data Augmentation on Few-Shot Text Classification Tasks (2023.emnlp-main)

Challenge:	Existing dialogue systems process conversational turns in isolation, overlooking event structures that guide natural interactions.
Approach:	They propose a framework that explicitly models relationships between conversational events to generate more contextually appropriate dialogue responses.
Outcome:	Experiments on three dialogue datasets show that the proposed approach produces more natural responses while requiring less computational overhead.

Copied to clipboard

Haoqi Zheng, Qihuang Zhong, Liang Ding, Zhiliang Tian, Xin Niu, Changjian Wang, Dongsheng Li, Dacheng Tao

Evaluating Scene-based In-Situ Item Labeling for Immersive Conversational Recommendation (2026.findings-acl)

Challenge:	Text classification tasks often encounter few-shot scenarios with limited labeled data, and addressing data scarcity is crucial.
Approach:	They propose a self-evolution learning (SE) based mixup approach for data augmentation in text classification which generates more adaptive and model-friendly pseudo samples for the model training.
Outcome:	The proposed approach can generate more adaptive and model-friendly pseudo samples for the model training.

Copied to clipboard

Jiazhou Liang, Yifan Simon Liu, David Guo, Yilun Jiang, Minqi Sun, Scott Sanner

ROSE Doesn’t Do That: Boosting the Safety of Instruction-Tuned Large Language Models with Reverse Prompt Contrastive Decoding (2024.findings-acl)

Challenge:	Existing methods for evaluating item labels fail to leverage scenario-specific information modalities, present redundant information that is visually inferable, and lack latent awareness of users' information needs.
Approach:	They propose a principled categorization of information needs into explicit intent satisfaction and proactive information needs and define evaluation metrics for item label selection.
Outcome:	The proposed evaluation framework is based on IR-, LLM-, and VLM-based methods across fashion, movie recommendation, and retail shopping scenarios.

Copied to clipboard

Qihuang Zhong, Liang Ding, Juhua Liu, Bo Du, Dacheng Tao

FTibSuite: A Comprehensive Resource Suite for Tibetan Vision–Language Modeling (2026.findings-acl)

Challenge:	Existing methods for aligning LLMs output with expected safety require substantial training efforts and expensive computational resources.
Approach:	They propose a method to directly boost the safety of existing instruction-tuned large language models without additional training.
Outcome:	The proposed method improves safety of instruction-tuned large language models without training and requires expensive computational resources.

Copied to clipboard

Guixian Xu, Yide Liang, Zeli Su, Xuexian Song, Ziyin Zhang, Yushuang Dong, Ting Zhang, Xu Han

REVEALER: Reinforcement-Guided Visual Reasoning for Element-Level Text-Image Alignment Evaluation (2026.acl-long)

Challenge:	FTibSuite provides an end-to-end training-and-evaluation workflow for vision–language models . Tibetan is underserved due to the lack of infrastructure for reproducible training and evaluation.
Approach:	They propose a resource-centric workflow for Tibetan VLMs that provides an end-to-end training-and-evaluation workflow and human-verified multimodal annotations.
Outcome:	FTibSuite provides an end-to-end training-and-evaluation workflow and human-verified multimodal annotations.

Copied to clipboard

FuLin Shi, Wenyi Xiao, Leilei Gan, Liang Ding, null Binchen

Best Practices for Distilling Large Language Models into BERT for Web Search Ranking (2025.coling-industry)

Challenge:	Existing methods for text-to-image alignment evaluation rely on coarse-grained metrics or static Question Answering pipelines that lack fine-grounded interpretability and struggle to reflect human preferences.
Approach:	They propose a reinforcement-guided visual reasoning framework for element-level text-to-image alignment evaluation.
Outcome:	The proposed framework achieves state-of-the-art results on four benchmarks and surpasses the strong proprietary Gemini 3 Pro and Training-based baselines.

Copied to clipboard

Dezhi Ye, Junwei Hu, Jiabin Fan, Bowen Tian, Jie Liu, Haijin Liang, Jin Ma

On the Complementarity between Pre-Training and Back-Translation for Neural Machine Translation (2021.findings-emnlp)

Challenge:	Recent studies have highlighted the potential of Large Language Models (LLMs) as zero-shot relevance rankers.
Approach:	They propose to use a ranking loss to transfer ranking knowledge from LLMs to smaller models like BERT.
Outcome:	The proposed model has been successfully integrated into a commercial web search engine as of February 2024.

Copied to clipboard

Xuebo Liu, Longyue Wang, Derek F. Wong, Liang Ding, Lidia S. Chao, Shuming Shi, Zhaopeng Tu

GEMv2: Multilingual NLG Benchmarking in a Single Line of Code (2022.emnlp-demos)

Challenge:	Experimental results show that PT and BT are nicely complementary to each other.
Approach:	They introduce two probing tasks for PT and BT respectively and investigate their complementarity.
Outcome:	The proposed methods establish state-of-the-art on the WMT16 English-Romanian and English-Russian benchmarks.

Copied to clipboard

Sebastian Gehrmann, Abhik Bhattacharjee, Abinaya Mahendiran, Alex Wang, Alexandros Papangelis, Aman Madaan, Angelina Mcmillan-major, Anna Shvets, Ashish Upadhyay, Bernd Bohnet, Bingsheng Yao, Bryan Wilie, Chandra Bhagavatula, Chaobin You, Craig Thomson, Cristina Garbacea, Dakuo Wang, Daniel Deutsch, Deyi Xiong, Di Jin, Dimitra Gkatzia, Dragomir Radev, Elizabeth Clark, Esin Durmus, Faisal Ladhak, Filip Ginter, Genta Indra Winata, Hendrik Strobelt, Hiroaki Hayashi, Jekaterina Novikova, Jenna Kanerva, Jenny Chim, Jiawei Zhou, Jordan Clive, Joshua Maynez, João Sedoc, Juraj Juraska, Kaustubh Dhole, Khyathi Raghavi Chandu, Laura Perez Beltrachini, Leonardo F . R. Ribeiro, Lewis Tunstall, Li Zhang, Mahim Pushkarna, Mathias Creutz, Michael White, Mihir Sanjay Kale, Moussa Kamal Eddine, Nico Daheim, Nishant Subramani, Ondrej Dusek, Paul Pu Liang, Pawan Sasanka Ammanamanchi, Qi Zhu, Ratish Puduppully, Reno Kriz, Rifat Shahriyar, Ronald Cardenas, Saad Mahamood, Salomey Osei, Samuel Cahyawijaya, Sanja Štajner, Sebastien Montella, Shailza Jolly, Simon Mille, Tahmid Hasan, Tianhao Shen, Tosin Adewumi, Vikas Raunak, Vipul Raheja, Vitaly Nikolaev, Vivian Tsai, Yacine Jernite, Ying Xu, Yisi Sang, Yixin Liu, Yufang Hou

Scaling Under-Resourced TTS: A Data-Optimized Framework with Advanced Acoustic Modeling for Thai (2025.acl-industry)

Challenge:	Evaluations in machine learning rarely use the latest metrics, datasets, or human evaluation in favor of remaining compatible with prior work.
Approach:	They propose to use the Generation, Evaluation, and Metrics Benchmark to integrate new evaluation methods into existing evaluations.
Outcome:	The proposed evaluation infrastructure bridges the gap between the advantages of leaderboards and in-depth and evolving evaluations by allowing model developers to benefit from each other's work.

Copied to clipboard

Yizhong Geng, Jizhuo Xu, Zeyu Liang, Jinghan Yang, Xiaoyi Shi, Xiaoyu Shen

From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models (2024.findings-emnlp)

Challenge:	Text-to-speech (TTS) systems are limited by limited data and linguistic complexities.
Approach:	They propose a data-optimized framework with an advanced acoustic model to build high-quality TTS systems for low-resource scenarios.
Outcome:	The proposed framework enables zero-shot voice cloning and improved performance across diverse client applications, including finance, healthcare, education, and law.

Copied to clipboard

Qianyu He, Jie Zeng, Qianxi He, Jiaqing Liang, Yanghua Xiao

Chinese Toxic Language Mitigation via Sentiment Polarity Consistent Rewrites (2025.emnlp-main)

Challenge:	Large language models (LLMs) follow instructions with elaborate requirements, yet it remains under-explored how to enhance their ability to follow complex instructions with multiple constraints.
Approach:	They propose a method to obtain and utilize effective training data to enhance LLMs' ability to follow complex instructions with multiple constraints.
Outcome:	The proposed framework improves models' ability to follow instructions generally and generalize effectively across out-of-domain, in domain, and adversarial settings while maintaining general capabilities.

Copied to clipboard

Xintong Wang, Yixiao Liu, Jingheng Pan, Liang Ding, Longyue Wang, Chris Biemann

CorNav: Autonomous Agent with Self-Corrected Planning for Zero-Shot Vision-and-Language Navigation (2024.findings-acl)

Challenge:	Large language models (LLMs) can be effective at rewriting toxic content, but they often default to overly polite rewrites, distorting the emotional tone and communicative intent.
Approach:	They evaluate 17 large language models with variant architectures to evaluate their ability to rewrite toxic content while preserving the speaker's original intent.
Outcome:	The first Chinese detoxification dataset explicitly designed to preserve sentiment polarity is evaluated across five real-world scenarios.

Copied to clipboard

Xiwen Liang, Liang Ma, Shanshan Guo, Jianhua Han, Hang Xu, Shikui Ma, Xiaodan Liang

Can MLLMs Understand the Deep Implication Behind Chinese Images? (2025.acl-long)

Challenge:	Existing vision-and-language navigation methods do not incorporate environmental feedback into their decision-making processes.
Approach:	They propose a framework that incorporates environmental feedback into decision-making and a 3D simulator that renders realistic scenarios using Unreal Engine 5.
Outcome:	The proposed framework outperforms existing vision-and-language navigation methods in a zero-shot multi-task setting by 28.1% on average.

Copied to clipboard

Chenhao Zhang, Xi Feng, Yuelin Bai, Xeron Du, Jinchang Hou, Kaixin Deng, Guangzeng Han, Qinrui Li, Bingli Wang, Jiaheng Liu, Xingwei Qu, Yifei Zhang, Qixuan Zhao, Yiming Liang, Ziqiang Liu, Feiteng Fang, Min Yang, Wenhao Huang, Chenghua Lin, Ge Zhang, Shiwen Ni

DT-Solver: Automated Theorem Proving with Dynamic-Tree Sampling Guided by Proof-level Value Function (2023.acl-long)

Challenge:	MLLMs perform poorly on traditional culture images, indicating limitations in understanding high-level semantics and lacking a deep knowledge base of Chinese traditional culture.
Approach:	They propose to use Chinese images to assess MLLMs' higher-order perception and understanding of Chinese visual content.
Outcome:	The proposed model incorporates images that represent Chinese traditional culture, such as famous Chinese traditional paintings, to ensure the authenticity of the Chinese context.

Copied to clipboard

Haiming Wang, Ye Yuan, Zhengying Liu, Jianhao Shen, Yichun Yin, Jing Xiong, Enze Xie, Han Shi, Yujun Li, Lin Li, Jian Yin, Zhenguo Li, Xiaodan Liang

VCORE: Variance-Controlled Optimization-based Reweighting for Chain-of-Thought Supervision (2026.acl-long)

Challenge:	Recent advances in neural theorem-proving resort to large language models and tree searches.
Approach:	They propose a Dynamic-Tree Driven Theorem Solver to accommodate general theoremes by guiding the search procedure with state confidence and proof-level values.
Outcome:	The proposed method outperforms state-of-the-art methods on two popular theorem-proving datasets with a 6.65% improvement on average in terms of success rate.

Copied to clipboard

Xuan Gong, Senmiao Wang, Hanbo Huang, Ruoyu Sun, Shiyu Liang

Accurate Training of Web-based Question Answering Systems with Feedback from Ranked Users (2023.acl-industry)

Challenge:	Empirical evaluations demonstrate that VCORE achieves the strongest overall average performance, with especially clear gains on lower-capacity models.
Approach:	They propose a framework that reformulates supervision as a constrained optimization problem.
Outcome:	Empirical evaluations show that VCORE achieves the strongest overall average performance, with especially clear gains on lower-capacity models.

Copied to clipboard

Liang Wang, Ivano Lauriola, Alessandro Moschitti

Advancing SMoE for Continuous Domain Adaptation of MLLMs: Adaptive Router and Domain-Specific Loss (2025.acl-long)

Challenge:	Recent work shows that large-scale annotated datasets are essential for training state-of-the-art Question Answering (QA) models.
Approach:	They use large-scale annotated datasets to train question answering models . they use feedback data collected from deployed QA systems to provide cheaper supervision .
Outcome:	The proposed model improves on the large scale annotated datasets from QA systems . the proposed model can be easily supervised on large-scale unlabeled web data .

Copied to clipboard

Liang Zhang, Ziyao Lu, Fandong Meng, Hui Li, Jie Zhou, Jinsong Su

Do LLMs Play Dice? Exploring Probability Distribution Sampling in Large Language Models for Behavioral Simulation (2025.coling-main)

Challenge:	Recent studies have explored Continual Instruction Tuning (CIT) in Multimodal Large Language Models (MLLMs), with a primary focus on Task-incremental CIT, where MLLM are required to continuously acquire new tasks.
Approach:	They propose a Sparse Mixture of Expert (SMoE) based method for domain-incremental CIT in Multimodal Large Language Models (MLLMs) . they equip the SMoA module with a domain-specific autoregressive loss (DSAL) they establish a new benchmark to evaluate the efficacy of their method .
Outcome:	The proposed method outperforms all baselines and is based on a Sparse Mixture of Experts (SMoE) module .

Copied to clipboard

Jia Gu, Liang Pang, Huawei Shen, Xueqi Cheng

Take Care of Your Prompt Bias! Investigating and Mitigating Prompt Bias in Factual Knowledge Extraction (2024.lrec-main)

Challenge:	LLMs are used to emulate sequential decision-making processes of humans . however, their ability to perform probabilistic sampling is limited .
Approach:	They propose to use large language models (LLMs) as agents to emulate the sequential decision-making processes of humans represented as Markov decision-makers (MDPs).
Outcome:	The proposed models can understand probabilities, but struggle with sampling precision . integrating coding tools can improve sampling precision, but this level of sampling precision still makes it difficult to simulate human behavior as agents.

Copied to clipboard

Ziyang Xu, Keqin Peng, Liang Ding, Dacheng Tao, Xiliang Lu

HyperCRS: Hypergraph-Aware Multi-Grained Preference Learning to Burst Filter Bubbles in Conversational Recommendation System (2025.findings-acl)

Challenge:	Recent research shows that pre-trained language models suffer from “prompt bias” in factual knowledge extraction.
Approach:	They propose a representation-based approach to mitigate prompt bias during inference time by querying the model and removing it from its internal representations to generate debiased representations.
Outcome:	The proposed approach corrects the overfitted performance caused by prompt bias and significantly improves prompt retrieval capability.

Copied to clipboard

Yongsen Zheng, Mingjie Qian, Guohua Wang, Yang Liu, Ziliang Chen, Mingzhi Mao, Liang Lin, Kwok-Yan Lam

Invocation Refiner: A Plug-and-Play Module for Rectifying LLM Tool Invocations (2026.findings-acl)

Challenge:	Existing methods to analyze filter bubbles in the static recommendation environment are unable to burst them during user interactions.
Approach:	They propose a paradigm to learn multi-grained user preferences during dynamic user-system interactions via natural language conversations to burst filter bubbles.
Outcome:	The proposed paradigm achieves state-of-the-art performance and the superior of bursting filter bubbles in the conversational recommendation system.

Copied to clipboard

Qirui Jiao, Dian Jiao, Nan Du, Ying Shen, Liang Lin

Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems (2020.emnlp-main)

Challenge:	Large Language Models (LLMs) have shown remarkable capabilities in Tool-Integrated Reasoning (TIR) however, the practical application is often hindered by frequent errors in tool invocations, such as incorrect tool names, invalid parameters, wrong tool-call order, or malformed invocation formats.
Approach:	They propose a specialized post-processing module that performs independent reasoning on the input of a frozen upstream LLM and an advanced RL algorithm to improve the tool-use reliability of base LLMs.
Outcome:	The proposed module improves task completion rates and invocation accuracy over the raw outputs of various upstream LLMs on a diverse set of tool-use and reasoning benchmarks.

Copied to clipboard

Jinghui Qin, Lihui Lin, Xiaodan Liang, Rumin Zhang, Liang Lin

LongInsightBench: A Comprehensive Benchmark for Evaluating Omni-Modal Models on Human-Centric Long-Video Understanding. (2026.findings-acl)

Challenge:	Existing models focus on one-unknown linear MWPs.
Approach:	They propose a universal expression tree-structured solver that integrates multiple expression trees underlying a MWP into a single expression tree.
Outcome:	The proposed method outperforms state-of-the-art models on a MWPs dataset and generates a universal expression tree explicitly by deciding which symbol to generate .

Copied to clipboard

ZhaoYang Han, Qihan Lin, Hao Liang, Bowen Chen, Zhou Liu, Wentao Zhang

Toolscaler: Scalable Generative Tool Calling via Structure-Aware Semantic Tokenization (2025.findings-emnlp)

Challenge:	LongInsightBench is the first benchmark designed to assess models’ ability to understand long videos, with a focus on human language, viewpoints, actions, and other contextual elements.
Approach:	They propose a benchmark to assess models’ ability to understand long videos with a focus on human language, viewpoints, actions, and other contextual elements.
Outcome:	The proposed model excels in three key areas: a) long-duration, human-centric videos; b) diversifying and challenging task scenarios; c) quality assurance pipeline; and d) reliability.

Copied to clipboard

Yunyue Su, Zhang Jinshuai, Bowen Fang, Wen Ye, Jinghao Zhang, Bowen Song, Weiqiang Wang, Qiang Liu, Liang Wang

A Semantic-based Method for Unsupervised Commonsense Question Answering (2021.acl-long)

Challenge:	Extensive experiments demonstrate the effectiveness of SGTC across various tasks.
Approach:	They propose a generative tool invocation framework that introduces structure-aware semantic tokenization to encode tools as discrete code sequences.
Outcome:	The proposed framework reduces the size of the representation space and underutilizes collaborative signals among tools in downstream tasks.

Copied to clipboard

Yilin Niu, Fei Huang, Jiaming Liang, Wenkai Chen, Xiaoyan Zhu, Minlie Huang

Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning (2026.acl-long)

Challenge:	Existing methods to score candidates without labeled task data are difficult to use . e.g., pre-trained language models can be easily affected by irrelevant factors .
Approach:	They propose a method that generates plausible answers with generative models and uses them to select the correct answer.
Outcome:	The proposed method achieves the best results in unsupervised situations.

Copied to clipboard

Xue Zhang, Yunlong Liang, Fandong Meng, Songming Zhang, Kaiyu Huang, Yufeng Chen, Xu Jinan, Jie Zhou

Robust Lottery Tickets for Pre-trained Language Models (2022.acl-long)

Challenge:	Current Large Reasoning Models exhibit two critical limitations when processing non-English languages: (1) They struggle to maintain input-output language consistency; (2) They generally perform poorly with wrong reasoning paths and lower answer accuracy compared to English.
Approach:	They propose a language-consistency reward and a cross-lingual thinking alignment reward to improve the model's interpretability and accuracy.
Outcome:	The proposed model achieves nearly 100% language consistency and superior performance on two multilingual benchmarks (MMATH and PolyMath).

Copied to clipboard

Rui Zheng, Bao Rong, Yuhao Zhou, Di Liang, Sirui Wang, Wei Wu, Tao Gui, Qi Zhang, Xuanjing Huang

Self-Generated Critiques Boost Reward Modeling for Language Models (2025.naacl-long)

Challenge:	Recent studies have shown that pre-trained language models contain smaller matching subnetworks that are not robust to adversarial examples.
Approach:	They propose a method to find robust tickets hidden in pre-trained language models by learning binary weight masks and an adversarial loss objective to guide the search.
Outcome:	The proposed method improves on previous work on adversarial robustness evaluation.

Copied to clipboard

Yue Yu, Zhengxing Chen, Aston Zhang, Liang Tan, Chenguang Zhu, Richard Yuanzhe Pang, Yundi Qian, Xuewei Wang, Suchin Gururangan, Chao Zhang, Melanie Kambadur, Dhruv Mahajan, Rui Hou

Evaluating LLM-Generated Diagrams as Graphs (2025.emnlp-main)

Challenge:	Existing reward models produce scalar scores and struggle to incorporate critiques in a natural language format.
Approach:	They propose a framework that predicts critiques and rewards using self-generated critiques without extra supervision.
Outcome:	The proposed framework improves reward modeling accuracy by 3.7%-7.3% compared to standard reward models and LLM judges.

Copied to clipboard

Chumeng Liang, Jiaxuan You

Context or Knowledge is Not Always Necessary: A Contrastive Learning Framework for Emotion Recognition in Conversations (2023.findings-acl)

Challenge:	Existing methods on diagram generation with LLMs rely heavily on proprietary LLM systems.
Approach:	They propose a new evaluation metric to assess demonstration diagrams generated by large language models.
Outcome:	The proposed evaluation metric evaluates diagrams produced by state-of-the-art LLMs on recent research literature.

Copied to clipboard

Geng Tu, Bin Liang, Ruibin Mao, Min Yang, Ruifeng Xu

Filter-And-Refine: A MLLM Based Cascade System for Industrial-Scale Video Content Moderation (2025.acl-industry)

Challenge:	Existing studies focus on modeling context-sensitive dependencies and knowledge-sensitive dependences.
Approach:	They propose a framework based on contrastive learning called CKCL to distinguish utterances for better vector representations.
Outcome:	The proposed framework outperforms state-of-the-art models on four datasets.

Copied to clipboard

Zixuan Wang, Jinghao Shi, Hanzhong Liang, Xiang Shen, Vera Wen, Zhiqian Chen, Yifan Wu, Zhixin Zhang, Hongyu Xiong

Breaking the Reasoning Barrier A Survey on LLM Complex Reasoning through the Lens of Self-Evolution (2025.findings-acl)

Challenge:	Effective content moderation is essential for video platforms to safeguard user experience and uphold community standards.
Approach:	They propose a method to transform a generative MLLM into a multimodal classifier using minimal discriminative training data.
Outcome:	The proposed method improves F1 score by 66.50% over traditional classifiers while requiring only 2% of the fine-tuning data.

Copied to clipboard

Tao He, Hao Li, Jingchang Chen, Runxuan Liu, Yixin Cao, Lizi Liao, Zihao Zheng, Zheng Chu, Jiafeng Liang, Ming Liu, Bing Qin

MMSD2.0: Towards a Reliable Multi-modal Sarcasm Detection System (2023.findings-acl)

Challenge:	OpenAI's O1 and subsequent projects like DeepSeek R1 have significantly advanced research on complex reasoning in LLMs.
Approach:	They analyze existing reasoning studies from the perspective of self-evolution and summarize O1-like works from open-source projects like DeepSeek R1 and Kimi-k1.5.
Outcome:	The proposed models are based on open-source models and pioneer advanced methodologies like Scaling Reinforcement Learning (RL).

Copied to clipboard

Libo Qin, Shijue Huang, Qiguang Chen, Chenran Cai, Yudi Zhang, Bin Liang, Wanxiang Che, Ruifeng Xu

PCAD: Towards ASR-Robust Spoken Language Understanding via Prototype Calibration and Asymmetric Decoupling (2024.acl-long)

Challenge:	Existing benchmarks for multi-modal sarcasm detection have some shortcomings . a new framework can leverage multi-grained cues from multiple perspectives for multimodal detection .
Approach:	They propose a correction dataset that removes spurious cues and re-annotates the unreasonable samples.
Outcome:	The proposed framework outperforms the existing benchmarks in multi-modal sarcasm detection.

Copied to clipboard

Xianwei Zhuang, Xuxin Cheng, Liming Liang, Yuxin Xie, Zhichang Wang, Zhiqi Huang, Yuexian Zou

Learning from the Irrecoverable: Error-Localized Policy Optimization for Tool-Integrated LLM Reasoning (2026.acl-long)

Challenge:	Spoken language understanding (SLU) suffers from error propagation from automatic speech recognition (ASR) in actual scenarios.
Approach:	They propose a framework which calibrates bias and errors and achieves adaptive-balanced decoupling training by a prototype-based loss model.
Outcome:	The proposed framework outperforms existing approaches and achieves state-of-the-art performance on three datasets.

Copied to clipboard

Qiao Liang, Yuke Zhu, Chao Ge, Lei Yang, Ying Shen, Bo Zheng, Sheng Guo

Mechanistic Insights into Deferred Semantic Drift in LLMs (2026.findings-acl)

Challenge:	Tool-integrated reasoning (TIR) enables LLM agents to solve tasks through planning, tool use, and iterative revision, but outcome-only reinforcement learning suffers from sparse, delayed rewards and weak step-level credit assignment.
Approach:	They propose a tool-integrated reasoning approach that localizes the first irrecoverable step and leverages it for fine-grained credit assignment.
Outcome:	The proposed algorithm outperforms strong Agentic RL benchmarks in math, science QA, and code execution with additional gains in Pass@K and Major@K scaling, rollout ranking quality, and tool-call efficiency.

Copied to clipboard

Jingjie Zeng, Huayang Li, Liang Yang, Shaowu Zhang, Yuanyuan Sun, Hongfei Lin

Challenge:	Large Language Models (LLMs) face a fundamental challenge with delayed disambiguation: how can a model update the meaning of an early, ambiguous token when clarifying context only appears later in the sequence?
Approach:	They propose a method to defer semantic re-evaluation to subsequent tokens in a process they call "Deferred Semantic Drift" they demonstrate this mechanism in metaphor comprehension and provide causal validation by steering model outputs towards literal or metaphorical meanings via targeted activation interventions.
Outcome:	The proposed model can update the meaning of an ambiguous word when clarifying context arrives only after it has been processed.

RLSeek: Evidence-Grounded Reasoning for RAG Hallucination Detection (2026.acl-long)

Copied to clipboard

Zhaoheng Huang, Dacheng Wen, Yutao Zhu, Xiaoying Lian, Yushi Liang, Kai Hao, Nan Li, Liangjie Zhang, Qi Zhang, Ji-Rong Wen, Zhicheng Dou, Fangzhao Wu

Metaphor Reasoning is Meta-reasoning (2026.acl-long)

Challenge:	Recent work addresses this problem by training span-level hallucination detectors using reinforcement learning and chain-of-thought reasoning.
Approach:	They propose a framework that explicitly enforces active evidence seeking during CoT reasoning by requiring quotation of relevant source segments at each verification step.
Outcome:	The proposed framework improves hallucination span detection performance with limited reasoning overhead and improved robustness in out-of-domain settings.

Copied to clipboard

Qianyu He, Junting Lu, Yikai Zhang, Siyu Yuan, Xiaojun Meng, Jiansheng Wei, Jiaqing Liang, Yanghua Xiao

Single-to-mix Modality Alignment with Multimodal Large Language Model for Document Image Machine Translation (2025.acl-long)

Challenge:	Existing work on metaphor reasoning's impact on reasoning abilities is limited.
Approach:	They propose a system for synthesizing metaphorical riddles that satisfy five quality dimensions: diverse, balanced, reasoning-oriented, challenging, and verifiable.
Outcome:	The proposed system improves reasoning abilities across six domains using only thousands of metaphorical riddles.

Copied to clipboard

Yupu Liang, Yaping Zhang, Zhiyang Zhang, Yang Zhao, Lu Xiang, Chengqing Zong, Yu Zhou

Distilling Causal Effect from Miscellaneous Other-Class for Continual Named Entity Recognition (2022.emnlp-main)

Challenge:	Document Image Machine Translation (DIMT) faces generalization challenges due to limited training data and the complex interplay between visual and textual information.
Approach:	They propose a single-to-mix Modality alignment framework leveraging Multimodal Large Language Models (MLLMs) this framework aligns an imageonly encoder with multimodal representations of an MLLM pre-trained on large-scale document image datasets.
Outcome:	The proposed framework improves translation quality in cross-domain generalization and challenging document image scenarios.

Copied to clipboard

Junhao Zheng, Zhanxian Liang, Haibin Chen, Qianli Ma

Beta-LR: Interpretable Logical Reasoning based on Beta Distribution (2024.findings-naacl)

Challenge:	Existing methods for Named Entity Recognition (NER) are not able to learn Other-Class in the same way as new entity types.
Approach:	They propose a unified causal framework to retrieve causality from new entity types and Other-Class.
Outcome:	The proposed method outperforms the state-of-the-art method on three benchmark datasets.

Copied to clipboard

Yizhuo Ma, Ke Qin, Shuang Liang

Beyond Cross-Modal Alignment: Measuring and Leveraging Modality Gap in Vision-Language Models (2026.findings-acl)

Challenge:	Existing methods to capture logical information from text are limited by the uncertainty of the text.
Approach:	They propose a probabilistic embedding method to capture logical information from text . they embed texts into beta distributions on each dimension to eliminate logical uncertainty .
Outcome:	The proposed method achieves competitive performances on two datasets.

Copied to clipboard

Hanqi Yan, Xiangxiang Cui, Lu Yin, Jindong Gu, Paul Pu Liang, Yulan He, Yifei Wang

T2: An Adaptive Test-Time Scaling Strategy for Contextual Question Answering (2025.emnlp-main)

Challenge:	a recent study shows that vision-language models have modality gaps that persist even in well-aligned models.
Approach:	They propose a modality-dominance score to measure and leverage modality gaps . they propose automatic interpretability metrics to evaluate these features in a scalable manner .
Outcome:	The proposed framework allows for training-free probing and editing methods for understanding model perception across genders and generating adversarial examples.

Copied to clipboard

Zhengyi Zhao, Shubo Zhang, Zezhong Wang, Huimin Wang, Yutian Zhao, Bin Liang, Yefeng Zheng, Binyang Li, Kam-Fai Wong, Xian Wu

LexicalAT: Lexical-Based Adversarial Reinforcement Training for Robust Sentiment Classification (D19-1)

Challenge:	Existing efficient test-time scaling methods introduce budget constraints or early stop mechanisms to avoid overthinking for straightforward questions but add human bias to the reasoning process.
Approach:	They propose a framework that dynamically adapts reasoning depth based on question complexity.
Outcome:	Experimental results show that the proposed framework achieves higher accuracy than baseline methods and reduces computational overhead by up to 25.2%.

Copied to clipboard

Jingjing Xu, Liang Zhao, Hanqi Yan, Qi Zeng, Yun Liang, Xu Sun

Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation (2026.acl-long)

Challenge:	Existing text classification models are fragile and sensitive to simple perturbations.
Approach:	They propose a generator-classifier adversarial training approach to improve classification models . they use a large-scale lexical knowledge base to generate attacking examples .
Outcome:	The proposed approach outperforms strong baselines and reduces test errors on neural networks.

Copied to clipboard

Qianchi Zhang, Hainan Zhang, Liang Pang, Hong-Wei Zheng, Zhiming Zheng

Does it Make Sense? And Why? A Pilot Study for Sense Making and Explanation (P19-1)

Challenge:	Existing RAG methods focus on enhancing LLM robustness to low-quality retrieval, but neither address permutation sensitivity.
Approach:	They propose a method that exploits permutation sensitivity to mitigate hallucinations in Large Language Models.
Outcome:	The proposed model improves answer accuracy, reasoning consistency, and generalization across datasets, retrievers, and input lengths compared with strong baselines.

Copied to clipboard

Cunxiang Wang, Shuailong Liang, Yue Zhang, Xiaonan Li, Tian Gao

Distorted or Fabricated? A Survey on Hallucination in Video LLMs (2026.findings-acl)

Challenge:	Existing benchmarks measure common sense knowledge indirectly or without reasoning.
Approach:	They propose a benchmark to test whether a system can differentiate natural language statements that make sense from those that do not make sense.
Outcome:	The proposed benchmarks show that models trained on large corpora perform better than humans on some benchmarks.

Copied to clipboard

Yiyang Huang, Yitian Zhang, Yizhou Wang, Mingyuan Zhang, Liang Shi, Huimin Zeng, Yun Fu

Speculative Beam Search for Simultaneous Translation (D19-1)

Challenge:	Despite significant advances in video-language modeling, hallucinations remain a persistent challenge in video large language models.
Approach:	They present a systematic taxonomy that categorizes hallucinations into two core types: dynamic distortion and content fabrication.
Outcome:	The proposed taxonomy categorizes hallucinations into two core types: dynamic distortion and content fabrication.

Copied to clipboard

Renjie Zheng, Mingbo Ma, Baigong Zheng, Liang Huang

Well Begun is Half Done: Generator-agnostic Knowledge Pre-Selection for Knowledge-Grounded Dialogue (2023.emnlp-main)

Challenge:	Beam search is widely used in (full-sentence) machine translation but its application to simultaneous translation remains highly non-trivial.
Approach:	They propose a beam search algorithm that hallucinates several steps into the future to reach a more accurate decision by implicitly benefiting from a target language model.
Outcome:	The proposed method improves on language models over diverse language pairs and shows significant improvements over greedy search.

Copied to clipboard

Lang Qin, Yao Zhang, Hongru Liang, Jun Wang, Zhenglu Yang

Prompts Can Play Lottery Tickets Well: Achieving Lifelong Information Extraction via Lottery Prompt Tuning (2023.acl-long)

Challenge:	Existing knowledge selection methods are costly to learn and difficult to interpret when errors arise in the generated responses.
Approach:	They propose a generator-agnostic knowledge selection method to select context-related knowledge among different knowledge structures and variable knowledge requirements.
Outcome:	The proposed method can select knowledge accurately in advance and reduce learning, adjustment, and interpretation burden of later models.

Copied to clipboard

Zujie Liang, Feng Wei, Yin Jie, Yuxi Qian, Zhenghong Hao, Bing Han

Step-by-Step Mastery: Enhancing Soft Constraint Following Ability of Large Language Models (2025.findings-acl)

Challenge:	Existing research on information extraction tasks focuses on one specific task, but in real-world scenarios, new data of different IE tasks and domains come in a stream over time.
Approach:	They propose a parameter- and deployment-efficient prompt tuning method to evaluate the UIE system under a “lifelong learning” setting.
Outcome:	The proposed method is able to learn new tasks without forgetting old ones and expand knowledge and functionalities without retraining the whole system.

Copied to clipboard

Qingyu Ren, Jie Zeng, Qianyu He, Jiaqing Liang, Yanghua Xiao, Weikang Zhou, Zeye Sun, Fei Yu

Disentangled Phonetic Representation for Chinese Spelling Correction (2023.acl-long)

Challenge:	In real-world scenarios, user instructions often contain soft constraints, which are semantically related and cannot be rule-based verified, posing challenges for large language models.
Approach:	They propose a pipeline to construct datasets with high-quality outputs for instructions containing soft constraints automatically and use Direct Preference Optimization (DPO) as the training method.
Outcome:	The proposed model improves the LLMs' soft constraint following ability by using direct preference optimization (DPO) and constraint quantity.

Copied to clipboard

Zihong Liang, Xiaojun Quan, Qifan Wang

An ensemble CNN method for biomedical entity normalization (D19-57)

Challenge:	Chinese Spelling Correction (CSC) aims to detect and correct erroneous characters in Chinese sentences.
Approach:	They propose to integrate phonetic and character representations to allow interaction between textual and phonetic information.
Outcome:	The proposed method is superior to other methods on three benchmarks.

Copied to clipboard

Pan Deng, Haipeng Chen, Mengyao Huang, Xiaowen Ruan, Liang Xu

Compositional Mathematical Encoding for Math Word Problems (2023.findings-acl)

Challenge:	Named entity recognition (NER) and entity normalization (entity linking) are two fundamental natural language processing tasks to achieve entity normalizing.
Approach:	They propose a CNN method that normalizes microbiology-related entities to concepts in standard dictionaries.
Outcome:	The proposed method performs well in the BioNLP-OST19 shared task Bacteria Biotope.

Copied to clipboard

Zhenwen Liang, Jipeng Zhang, Kehan Guo, Xiaodong Wu, Jie Shao, Xiangliang Zhang

MQM-APE: Toward High-Quality Error Annotation Predictors with Automatic Post-Editing in LLM Translation Evaluators (2025.coling-main)

Challenge:	Existing MWP encoders work in a unimodal setting and map problem description to latent representation, then for decoding.
Approach:	They propose a Compositional Math Word Problem Solver which maps problem description to latent representation and decodes it in an interactive way.
Outcome:	Extensive experiments show that the proposed model outperforms state-of-the-art models on public benchmarks.

Copied to clipboard

Qingyu Lu, Liang Ding, Kanjian Zhang, Jinxia Zhang, Dacheng Tao

Sequence to General Tree: Knowledge-Guided Geometry Word Problem Solving (2021.acl-short)

Challenge:	Large Language Models (LLMs) have shown significant potential as judges for Machine Translation (MT) quality assessment.
Approach:	They propose a framework that automatically post-edits the original translation based on each error, thereby filtering out non-impactful errors.
Outcome:	The proposed framework improves reliability and quality of error spans against GEMBA-MQM, across eight LLMs in both high- and low-resource languages.

Copied to clipboard

Shih-hung Tsai, Chao-Chun Liang, Hsin-Min Wang, Keh-Yih Su

Document Image Machine Translation with Dynamic Multi-pre-trained Models Assembling (2024.naacl-long)

Challenge:	Existing neural solvers only generate binary expression trees that contain basic arithmetic operators and do not explicitly use the math formulas.
Approach:	They propose a sequence-to-general tree that generates interpretable and executable operation trees where nodes can be formulas with an arbitrary number of arguments.
Outcome:	The proposed tree generates interpretable and executable operation trees with formulas with an arbitrary number of arguments.

Copied to clipboard

Yupu Liang, Yaping Zhang, Cong Ma, Zhiyang Zhang, Yang Zhao, Lu Xiang, Chengqing Zong, Yu Zhou

DEFT: Distribution-guided Efficient Fine-Tuning for Human Alignment (2024.findings-emnlp)

Challenge:	Existing TIMT tasks focus on text-line-level images.
Approach:	They propose to extend the existing TIMT task and introduce a new framework to translate a source document image to markdown-formatted target translation.
Outcome:	The proposed task aims to translate a source document image with long context and complex layout structure to markdown-formatted target translation.

Copied to clipboard

Liang Zhu, Feiteng Fang, Yuelin Bai, Longze Chen, Zhexiang Zhang, Minghuan Tan, Min Yang

You Can Have a Second Chance: Unbiased and Multi-bit Watermarking for Diffusion Language Models with Regret-based Remasking (2026.acl-long)

Challenge:	Experimental results show that the methods enhanced by DEFT outperform the original methods in both alignment capability and generalization ability, with significantly reduced training time.
Approach:	They propose a distribution-based alignment framework that integrates data filtering and distributional guidance to improve alignment efficiency and generalization ability.
Outcome:	The proposed framework outperforms existing methods in alignment capability and generalization ability with significantly reduced training time.

Copied to clipboard

Ke Yang, Dongyang Liang, Jing Yu, Shuguang Yuan, Chi Chen

Why Do Emotions Change? Appraisal-Guided Reasoning for Emotion–Cause Triplet Extraction in Conversations (2026.acl-long)

Challenge:	Existing sequential LLMs cannot be directly applied to DLMs, as their generation order is arbitrary.
Approach:	They propose a stability-aware constraint that allows watermarking only in stable contexts and a bit-controlled, unbiased modulation to preserve the original DLM output distribution.
Outcome:	The proposed scheme achieves stable watermarking with minimal quality impact while maintaining high detection accuracy and multi-bit capacity.

Copied to clipboard

Qiao Liang, Ying Shen, Yao Liu, Tiantian Chen, Lin Zhang

CASN:Class-Aware Score Network for Textual Adversarial Detection (2023.acl-long)

Challenge:	Existing methods for multi-turn, multi-speaker multimodal affect understanding are difficult to maintain conversation-level consistency under within-speaks' emotion shifts.
Approach:	They propose a framework that combines appraisal-guided structured generation with graph-structured reinforcement learning to extract triplets from multi-turn multimodal conversations.
Outcome:	The proposed framework outperforms baselines on public MECTEC benchmarks and improves structure-aware metrics on emotion shift coherence and core events.

Copied to clipboard

Rong Bao, Rui Zheng, Liang Ding, Qi Zhang, Dacheng Tao

Adaptive Simultaneous Sign Language Translation with Confident Translation Length Estimation (2024.lrec-main)

Challenge:	Existing approaches to counteract adversarial attacks can be divided into two directions, adversarials defense and adversarially detection.
Approach:	They propose a score-based generative method to implicitly model the data distribution using a log-density distribution and supervised contrastive learning to guide the estimation using label information.
Outcome:	The proposed method improves on three text classification tasks on four advanced attack algorithms.

Copied to clipboard

Tong Sun, Biao Fu, Cong Hu, Liang Zhang, Ruiquan Zhang, Xiaodong Shi, Jinsong Su, Yidong Chen

An Empirical Study of Many-to-Many Summarization with Large Language Models (2025.acl-long)

Challenge:	Existing non-simultaneous sign language translation methods suffer from inherent inference delays in real-time scenarios.
Approach:	They propose an adaptive policy for simultaneous sign language translation that progressively converts incrementally received sign video into its corresponding natural sentence.
Outcome:	The proposed policy excels in situations requiring extremely low latency.

Copied to clipboard

Jiaan Wang, Fandong Meng, Zengkui Sun, Yunlong Liang, Yuxuan Cao, Jiarong Xu, Haoxiang Shi, Jie Zhou

SmartTrim: Adaptive Tokens and Attention Pruning for Efficient Vision-Language Models (2024.lrec-main)

Challenge:	Recent studies have shown that large language models (LLMs) have strong multilingual abilities, giving them the potential to perform M2MS in real applications.
Approach:	They propose to use many-to-many summarization (M2MS) to generate a brief summary in any language given a document also in any other language.
Outcome:	The proposed model outperforms zero-shot LLMs in terms of automatic evaluations.

Copied to clipboard

Zekun Wang, Jingchang Chen, Wangchunshu Zhou, Haichao Zhu, Jiafeng Liang, Liping Shan, Ming Liu, Dongliang Xu, Qing Yang, Bing Qin

QuAC: Question Answering in Context (D18-1)

Challenge:	Experimental results show that SmartTrim accelerates the original model by 2-3 times with minimal performance degradation.
Approach:	They propose an adaptive acceleration framework which prunes redundant token representations and attention heads within each layer of the original model.
Outcome:	The proposed framework accelerates the original model by 2-3 times with minimal performance degradation across vision-language tasks.

Copied to clipboard

Eunsol Choi, He He, Mohit Iyyer, Mark Yatskar, Wen-tau Yih, Yejin Choi, Percy Liang, Luke Zettlemoyer

ReflectRM: Boosting Generative Reward Models via Self-Reflection within a Unified Judgment Framework (2026.acl-long)

Challenge:	a dataset for Question Answering in Context contains 14K information-seeking QA dialogs . questions are often more open-ended, unanswerable, or only meaningful within the dialog context .
Approach:	They propose a dataset for Question Answering in Context that contains 14K dialogs . they use a student to ask questions about a Wikipedia section and a teacher to answer them .
Outcome:	The proposed dataset underperforms humans in a number of reference models . the dataset contains 14K information-seeking dialogs over sections from Wikipedia .

Copied to clipboard

Kai Qin, Liangxin Liu, Yu Liang, Longzheng Wang, null Wangyan, Zhang Yueyang, Long Xia, Zhiyuan Sun, Houde Liu, Daiting Shi

Challenge:	Existing methods for generating reward models focus on outcome-level supervision, neglecting analytical process quality, which constrains their potential.
Approach:	They propose a novel reward model that leverages self-reflection to assess analytical quality and enhance preference modeling.
Outcome:	The proposed model improves performance on four benchmarks and significantly mitigates positional bias.

Design Challenges and Misconceptions in Neural Sequence Labeling (C18-1)

Copied to clipboard

Jie Yang, Shuailong Liang, Yue Zhang

Hypernetwork-Assisted Parameter-Efficient Fine-Tuning with Meta-Knowledge Distillation for Domain Knowledge Disentanglement (2024.findings-naacl)

Challenge:	Existing neural sequence labeling models have been used for many tasks such as POS tagging, chunking and named entity recognition (NER).
Approach:	They propose to replicate twelve neural sequence labeling models and compare them to three benchmarks to find out which models are effective and which are inconsistent.
Outcome:	The proposed models are compared on NER, Chunking, and POS tagging benchmarks.

Copied to clipboard

Changqun Li, Linlin Wang, Xin Lin, Shizhou Huang, Liang He

Novel Slot Detection With an Incremental Setting (2023.findings-emnlp)

Challenge:	Recent work on domain adaptation for text summarization fails to account for the huge gap between dialogue and general articles.
Approach:	They propose a hypernetwork-assisted encoder-decoder architecture with parameter-efficient fine-tuning to disentangle domain-invariant knowledge from source domains while learning specific knowledge of the target domain.
Outcome:	The proposed model can disentangle domain-invariant knowledge from source domains while learning specific knowledge of the target domain.

Copied to clipboard

Chen Liang, Hongliang Li, Changhao Guan, Qingbin Liu, Jian Liu, Jinan Xu, Zhe Zhao

EfficientLLM: Unified Pruning-Aware Pretraining for Auto-Designed Compact Language Models (2026.acl-long)

Challenge:	Current dialogue systems face diverse user requests and rapid change domains, making quickly adapt to scenarios with previous unseen slot types becomes a major challenge.
Approach:	They propose an incremental novel slot detection task which separates the dialogue system to deal with novel types as two major phrases: 1) model discovers unknown slots; 2) training model to possess the capability to handle new classes.
Outcome:	The proposed approach overcomes catastrophic forgetting during the process of INSD and is highly effective.

Copied to clipboard

Xingrun Xing, Zheng Liu, Shitao Xiao, Boyan Gao, Yiming Liang, Haokun Lin, Xianlin Zeng, Guoqi Li, Jiajun Zhang

Pre-training with Meta Learning for Chinese Word Segmentation (2021.naacl-main)

Challenge:	Large language models (LLMs) driven by scaling laws can be developed in large model sizes.
Approach:	They propose a pruning-aware pretraining approach that decouples LLM pruning from direct pretraining.
Outcome:	The proposed model outperforms pretraining models with 100M 1B parameters in commen sense benchmarks.

Copied to clipboard

Zhen Ke, Liang Shi, Songtao Sun, Erli Meng, Bin Wang, Xipeng Qiu

Set Learning for Generative Information Extraction (2023.emnlp-main)

Challenge:	Recent studies show that pre-trained models are beneficial to Chinese Word Segmentation (CWS). However, these models lack task-specific prior segmentation knowledge.
Approach:	They propose a pre-trained Chinese word segmentation model MetaSeg which incorporates meta learning into a multi-criteria pre-training task.
Outcome:	Empirical results show that MetaSeg can achieve new state-of-the-art performance on twelve widely-used CWS datasets and significantly improve model performance in low-resource settings.

Copied to clipboard

Jiangnan Li, Yice Zhang, Bin Liang, Kam-Fai Wong, Ruifeng Xu

Edit Once, Update Everywhere: A Simple Framework for Cross-Lingual Knowledge Synchronization in LLMs (2025.findings-acl)

Challenge:	Recent efforts to employ sequence-to-sequence models to solve IE tasks have been focused on a single problem: structured objects are an unordered set, resulting in a potential order bias.
Approach:	They propose a sequence-to-sequence (Seq2Sequen) model that considers multiple permutations of structured objects to optimize set probability approximately.
Outcome:	The proposed model improves existing frameworks on vast tasks and datasets.

Copied to clipboard

Yuchen Wu, Liang Ding, Li Shen, Dacheng Tao

A Comparative Study of Faithfulness Metrics for Model Interpretability Methods (2022.acl-long)

Challenge:	Existing methods to update large language models focus on single-language editing or basic multilingual editing, failing to achieve true cross-linguistic knowledge synchronization.
Approach:	They propose a cross-linguistic knowledge democracy edit technique to improve cross-lingual performance.
Outcome:	The proposed method improves cross-lingual performance while maintaining high accuracy in monolingual settings.

Copied to clipboard

Chun Sik Chan, Huanqi Kong, Liang Guanqing

Strong and Simple Baselines for Multimodal Utterance Embeddings (N19-1)

Challenge:	Existing methods to reveal the reasoning processes of machine learning models are difficult to interpret due to their complexity.
Approach:	They propose to use diagnosticity and complexity to assess faithfulness of machine learning models . they propose to apply posthoc interpretation methods to reveal reasoning behind models based on internal reasoning .
Outcome:	The proposed interpretation metrics show conflicting preferences when comparing interpretations . sufficiency and comprehensiveness metrics have higher diagnosticity and lower complexity .

Copied to clipboard

Paul Pu Liang, Yao Chong Lim, Yao-Hung Hubert Tsai, Ruslan Salakhutdinov, Louis-Philippe Morency

SLIM: Let LLM Learn More and Forget Less with Soft LoRA and Identity Mixture (2025.naacl-long)

Challenge:	Human language is a rich multimodal signal consisting of spoken words, facial expressions, body gestures, and vocal intonations.
Approach:	They propose two simple but strong baselines to learn embeddings of multimodal utterances by factorizing the utterant into unimodal factors.
Outcome:	The proposed models show that they can be derived in closed form while maintaining simplicity and efficiency during learning and inference.

Copied to clipboard

Jiayi Han, Liang Du, Hongwei Du, Xiangguo Zhou, Yiwen Wu, Yuanfang Zhang, Weibo Zheng, Donghong Han

ANALOGYKB: Unlocking Analogical Reasoning of Language Models with A Million-scale Knowledge Base (2024.acl-long)

Challenge:	balancing the training budget, downstream performance, and general capabilities of large language models remains a challenge in many applications.
Approach:	They propose a mixture of expert framework based on Soft LoRA and Identity Mixture . SLIM allows dynamic routing between LoRA adapters and identity layers .
Outcome:	The proposed framework reduces training cost while maintaining general capabilities . it can be open-sourced upon publication.

Copied to clipboard

Siyu Yuan, Jiangjie Chen, Changzhi Sun, Jiaqing Liang, Yanghua Xiao, Deqing Yang

Counterfactual Debiasing for Fact Verification (2023.acl-long)

Challenge:	ANALOGYKB is a million-scale analogy knowledge base based on existing knowledge graphs (KGs) based upon relational knowledge triples, we can discover new analogies using the corresponding relations between concepts.
Approach:	They propose a million-scale analogy knowledge base derived from existing knowledge graphs (KGs) ANALOGYKB identifies analogies of the same relations and analogies from analogous relations .
Outcome:	The proposed model enables both smaller LMs and LLMs to gain better analogical reasoning capabilities.

Copied to clipboard

Weizhi Xu, Qiang Liu, Shu Wu, Liang Wang

High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metrics (2022.tacl-1)

Challenge:	Existing methods for debiasing factchecking models learn such biases instead of understanding the semantic relationship between the claim and evidence.
Approach:	They propose a counterfactual framework CLEVER which is augmentation-free and mitigates biases on the inference stage.
Outcome:	The proposed method is augmentation-free and mitigates biases on the inference stage.

Copied to clipboard

Markus Freitag, David Grangier, Qijun Tan, Bowen Liang

Breaking the Beam Search Curse: A Study of (Re-)Scoring Methods and Stopping Criteria for Neural Machine Translation (D18-1)

Challenge:	Neural machine translations are ranked below human translations in professional evaluations .
Approach:	They apply minimum bayes risk decoding to optimize different metrics of translation quality . they show that model estimates and translation quality only vaguely correlate .
Outcome:	The proposed method improves human translations with different models and metric.

Copied to clipboard

Yilin Yang, Liang Huang, Mingbo Ma

Sequential-NIAH: A Needle-In-A-Haystack Benchmark for Extracting Sequential Needles from Long Contexts (2025.emnlp-main)

Challenge:	Beam search is widely used in neural machine translation, but beam sizes larger than 5 hurt translation quality.
Approach:	They propose to use beam search to improve translation quality by using hyperparameter-free methods that outperform the widely-used heuristic of length normalization by +2.0 BLEU.
Outcome:	The proposed methods outperform the widely-used heuristic on Chinese-to-English translation and achieve the best results among all methods.

Copied to clipboard

Yifei Yu, Qian-Wen Zhang, Lingfeng Qiao, Di Yin, Fang Li, Jie Wang, Chen Zeng Xi, Suncong Zheng, Xiaolong Liang, Xing Sun

JTAV: Jointly Learning Social Media Content Representation by Fusing Textual, Acoustic, and Visual Features (C18-1)

Challenge:	Recent models have extended Corresponding Author. context lengths to millions of tokens while maintaining reasoning and comprehension capabilities.
Approach:	They propose a benchmark to evaluate the ability of large language models to extract sequential information items from long contexts.
Outcome:	The proposed model achieves maximum accuracy of 63.50% on six well-known LLMs.

Copied to clipboard

Hongru Liang, Haozheng Wang, Jun Wang, Shaodi You, Zhe Sun, Jin-Mao Wei, Zhenglu Yang

Beyond Prompt Engineering: A Systematic Analysis of Prompt Lexical Sensitivity and Its Impacts on Quality (2026.findings-acl)

Challenge:	Existing studies on learning social media content focus on single modal or bi-modal learning, but this approach is non-trivial and challenging because content is multi-modal and involves several types of data, including text, audio, and image.
Approach:	They propose to combine textual, acoustic, and visual information to learn social media content by fusing them jointly.
Outcome:	The proposed model outperforms the state-of-the-art approaches on real-world datasets by a large margin.

Copied to clipboard

Qipeng Xie, Zi Liang, Jiafei Wu, Yufei Chen, Weizheng Wang, Wenao Ma, Zhong Ming, Haiqin Yang, Kaishun Wu

SentiX: A Sentiment-Aware Pre-Trained Model for Cross-Domain Sentiment Analysis (2020.coling-main)

Challenge:	Existing studies on prompt engineering have focused on optimizing models for performance under stylistic perturbations.
Approach:	They conduct the first analysis of n-gram token-level mechanisms . they find that higher average performance is inherently associated with lower variance and greater stability.
Outcome:	The proposed model reduces the variance of the generated code by 40% . the proposed model is based on a large-scale dataset of 132,000 prompt variants .

Copied to clipboard

Jie Zhou, Junfeng Tian, Rui Wang, Yuanbin Wu, Wenming Xiao, Liang He

Analogical Math Word Problems Solving with Enhanced Problem-Solution Association (2022.emnlp-main)

Challenge:	Pre-trained language models have been widely applied to cross-domain NLP tasks like sentiment analysis, but fine-tuning them on the source domain tends to overfit, leading to inferior results on the target domain.
Approach:	They propose to pre-train a sentiment-aware language model (SentiX) via domain-invariant sentiment knowledge from large-scale review datasets and utilize it for cross-domain sentiment analysis tasks without fine-tuning.
Outcome:	The proposed model achieves state-of-the-art in all the cross-domain sentiment analysis tasks and can be trained with only 1% samples and better than BERT with 90% samples.

Copied to clipboard

Zhenwen Liang, Jipeng Zhang, Xiangliang Zhang

Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration (2023.findings-emnlp)

Challenge:	Analogical reasoning has long been used in mathematical education, as it enables students to apply common relational structures of mathematical situations to solve new problems.
Approach:	They propose to leverage analogical MWPs to advance the solver’s generalization ability across different kinds of MWps.
Outcome:	The proposed model has a stronger generalization ability in solving difficult MWPs due to the analogical learning from easy MWPS.

Copied to clipboard

Yang Deng, Lizi Liao, Liang Chen, Hongru Wang, Wenqiang Lei, Tat-Seng Chua

MaXIFE: Multilingual and Cross-lingual Instruction Following Evaluation (2025.acl-long)

Challenge:	Recent studies have shown that ChatGPT has limitations such as failing to ask clarifying questions to ambiguous queries or refusing problematic user requests.
Approach:	They propose a Proactive Chain-of-Thought prompting scheme which augments LLMs with the goal planning capability over descriptive reasoning chains to trigger proactivity.
Outcome:	The proposed scheme augments LLMs with the goal planning capability over descriptive reasoning chains to trigger the proactivity of LLM-based proactive dialogue systems.

Copied to clipboard

Yile Liu, Ziwei Ma, Xiu Jiang, Jinglu Hu, ChangJing ChangJing, Liang Li

Curriculum Prompt Learning with Self-Training for Abstractive Dialogue Summarization (2022.emnlp-main)

Challenge:	Existing evaluation methods focus on single-language scenarios, overlooking multilingual and cross-lingual contexts.
Approach:	They propose a tool to assess instruction-following capabilities across 23 different languages with 1667 verifiable instruction tasks.
Outcome:	MaXIFE evaluates instruction-following capabilities across 23 languages with 1667 verifiable instruction tasks.

Copied to clipboard

Changqun Li, Linlin Wang, Xin Lin, Gerard de Melo, Liang He

StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models (2024.findings-acl)

Challenge:	Existing methods to summarize dialogues are difficult due to insufficient training data and low information density.
Approach:	They propose a curriculum-based prompt learning method with self-training that gradually increases the degree of prompt perturbation, improving dialogue understanding and modeling capabilities.
Outcome:	The proposed model outperforms baseline models on the AMI and ICSI datasets and human evaluations show it is superior in the quality of the summary generation.

Copied to clipboard

Zhicheng Guo, Sijie Cheng, Hao Wang, Shihao Liang, Yujia Qin, Peng Li, Zhiyuan Liu, Maosong Sun, Yang Liu

Unsupervised Keyphrase Extraction by Jointly Modeling Local and Global Context (2021.emnlp-main)

Challenge:	Large Language Models (LLMs) have witnessed remarkable advancements in recent years, prompting the exploration of tool learning.
Approach:	They propose a virtual API server and stable evaluation system to assess the stability of large-scale real-time APIs.
Outcome:	The proposed benchmarks demonstrate the stability of the proposed system and its caching system.

Copied to clipboard

Xinnian Liang, Shuangzhi Wu, Mu Li, Zhoujun Li

SparseAdapter: An Easy Approach for Improving the Parameter-Efficiency of Adapters (2022.findings-emnlp)

Challenge:	Embedding based methods are widely used for unsupervised keyphrase extraction tasks.
Approach:	They propose a method where local and global contexts are jointly modeled.
Outcome:	The proposed method outperforms most models while generalizing better on input documents with different domains and length.

Copied to clipboard

Shwai He, Liang Ding, Daize Dong, Jeremy Zhang, Dacheng Tao

On the Off-Target Problem of Zero-Shot Multilingual Neural Machine Translation (2023.findings-acl)

Challenge:	Pretrain-finetuned models are increasingly complex and require more parameters to match the performance of full fine-tuning.
Approach:	They propose an efficient Adapter Tuning technique that freezes pretrained language models and fine-tunes a few extra modules.
Outcome:	The proposed setting outperforms the standard Adapter Tuning by 80% . the proposed setting is easy to use and has a high sparse ratio .

Copied to clipboard

Liang Chen, Shuming Ma, Dongdong Zhang, Furu Wei, Baobao Chang

MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents (2026.acl-long)

Challenge:	Despite its success, multilingual neural machine translation suffers from the off-target issue, where the translation is in the wrong language.
Approach:	They propose a language-aware vocabulary sharing algorithm that can be used to increase the lexical distance between languages by isolating the vocab of different languages in the decoder.
Outcome:	The proposed algorithm reduces off-target rate for 90 translation tasks from 29% to 8%, while improving overall BLEU score by an average of 1.9 points without extra training cost or sacrificing the supervised directions’ performance.

Copied to clipboard

Pengxiang Zhao, Guangyi Liu, Yaozhen Liang, Weiqing He, Zhengxi Lu, WenHao Wang, Yuehao Huang, Yuxiang Chai, Zhaolu Kang, Yaxuan Guo, Hao Wang, Kexin Zhang, Liang Liu, Yong Liu

Open-ended Commonsense Reasoning with Unrestricted Answer Candidates (2023.findings-emnlp)

Challenge:	Shortcuts such as APIs and deep-links have emerged as efficient complements to flexible GUI operations, but systematic evaluation of GUI–shortcut hybrid agents remains underexplored.
Approach:	They propose a benchmark that evaluates GUI-shortcut hybrid agents with a specific focus on the mobile domain.
Outcome:	MAS-Bench evaluates agent's ability to generate shortcuts by discovering and creating reusable, low-cost workflows.

Copied to clipboard

Chen Ling, Xuchao Zhang, Xujiang Zhao, Yanchi Liu, Wei Cheng, Mika Oishi, Takao Osaki, Katsushi Matsuda, Haifeng Chen, Liang Zhao

LLMDet: A Third Party Large Language Models Generated Text Detection Tool (2023.findings-emnlp)

Challenge:	Current approaches to commonsense reasoning are limited due to limited answer scope.
Approach:	They propose to solve a commonsense question without a pre-defined answer scope . they leverage pre-trained language models to iteratively retrieve reasoning paths on the external knowledge base .
Outcome:	The proposed method achieves better performance on two commonsense benchmark datasets.

Copied to clipboard

Kangxi Wu, Liang Pang, Huawei Shen, Xueqi Cheng, Tat-Seng Chua

OneEE: A One-Stage Framework for Fast Overlapping and Nested Event Extraction (2022.coling-1)

Challenge:	Existing detection tools rely on access to LLMs and can only distinguish between machine-generated and human-authored text.
Approach:	They propose a model-specific, secure, efficient, and extendable detection tool that can source text from specific LLMs.
Outcome:	The proposed tool can source text from specific LLMs, such as GPT-2, OPT, LLaMA, and others.

Copied to clipboard

Hu Cao, Jingye Li, Fangfang Su, Fei Li, Hao Fei, Shengqiong Wu, Bobo Li, Liang Zhao, Donghong Ji

Are Sample-Efficient NLP Models More Robust? (2023.acl-short)

Challenge:	Event extraction (EE) is an essential task of information extraction, which aims to extract structured event information from unstructured text.
Approach:	They propose a tagging scheme and a model to form EE as word-word relation recognition using parallel grid tapping.
Outcome:	The proposed model achieves state-of-the-art on 3 overlapped and nested EE benchmarks and faster than baselines.

Copied to clipboard

Nelson F. Liu, Ananya Kumar, Percy Liang, Robin Jia

Learning Latent Relations for Temporal Knowledge Graph Reasoning (2023.acl-long)

Challenge:	Recent work in image classification and extractive question answering have observed that pre-trained models trained on less in-distribution data have better out-of-distortion performance.
Approach:	They conduct a large empirical study to investigate the relationship between sample efficiency and robustness.
Outcome:	The results show that pre-trained models with lower sample efficiency perform better on some tasks but not others.

Copied to clipboard

Mengqi Zhang, Yuwei Xia, Qiang Liu, Shu Wu, Liang Wang

SELF-GUARD: Empower the LLM to Safeguard Itself (2024.naacl-long)

Challenge:	Existing methods for Temporal Knowledge Graph reasoning capture intra- and inter-time latent relations between entities that appear at different times.
Approach:	They propose a Latent relations Learning method for TKG reasoning that captures latent relations between entities at different times.
Outcome:	The proposed method exploits the intra- and inter-time latent relations of entities at different times.

Copied to clipboard

Zezhong Wang, Fangkai Yang, Lu Wang, Pu Zhao, Hongru Wang, Liang Chen, Qingwei Lin, Kam-Fai Wong

PromptST: Abstract Prompt Learning for End-to-End Speech Translation (2023.emnlp-main)

Challenge:	Recent studies have investigated methods to improve the safety of large language models (LLMs) safety training involves fine-tuning the LLM with adversarial samples, which activate the LRM’s capabilities against jailbreak.
Approach:	They propose a safety training approach that integrates safety training and safeguards to train the LLM to perform harmfulness detection on its own outputs.
Outcome:	The proposed method reduces harmful output and adds a [harmful] or [harmless] tag to the end of the LLM's response.

Copied to clipboard

Tengfei Yu, Liang Ding, Xuebo Liu, Kehai Chen, Meishan Zhang, Dacheng Tao, Min Zhang

Length Extrapolation of Transformers: A Survey from the Perspective of Positional Encoding (2024.findings-emnlp)

Challenge:	Experimental results show that PromptST can improve speech-to-text translation by capturing richer linguistic knowledge.
Approach:	They propose a plug-in prompt-enhanced S2T model that captures richer linguistic knowledge . they use a 10GB linguistic probing benchmark to investigate the fusion of speech and text features .
Outcome:	The proposed model can improve on a strong baseline by capturing richer linguistic knowledge.

Copied to clipboard

Liang Zhao, Xiachong Feng, Xiaocheng Feng, Weihong Zhong, Dongliang Xu, Qing Yang, Hongtao Liu, Bing Qin, Ting Liu

KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from Server (2024.emnlp-main)

Challenge:	Existing methods to enhance length extrapolation of large language models have been developed, but a systematic survey is lacking.
Approach:	They propose to examine the effects of positional encoding on length extrapolation.
Outcome:	The proposed methods improve the extrapolation of large language models, but they are still lacking a systematic survey.

Copied to clipboard

WenHao Wang, Xiaoyu Liang, Rui Ye, Jingyi Chai, Siheng Chen, Yanfeng Wang

A Survey of Deep Learning for Mathematical Reasoning (2023.acl-long)

Challenge:	Existing methods to train large language models on private data are not effective because they rely on a local model for generation, resulting in a performance decline, or expose private data to API servers.
Approach:	They propose a client-server framework which enhances synthetic data quality and improves model performance while ensuring privacy.
Outcome:	The proposed framework improves model performance and privacy while learning local knowledge from the private data with differential privacy (DP) and distilling professional knowledge from server.

Copied to clipboard

Pan Lu, Liang Qiu, Wenhao Yu, Sean Welleck, Kai-Wei Chang

AdaJudge: Adaptive Multi-Perspective Judging for Reward Modeling (2026.acl-long)

Challenge:	a survey of deep learning for mathematical reasoning examines the field . a comprehensive reading list is provided to assist readers interested in the field.
Approach:	They present a survey of deep learning for mathematical reasoning over the past decade . they outline directions for future research and highlight potential for further exploration .
Outcome:	The proposed framework is based on the results of a decade-long survey of deep learning for mathematical reasoning.

Copied to clipboard

Yongliang Miao, Yangyang Liang, Mengnan Du

Challenge:	Existing reward models rely on a static pooling strategy to condense sequences into scalar scores, which is ill-suited for fine-grained discrimination.
Approach:	They propose a framework that jointly adapts representation and aggregation to address these limitations by integrating a static inductive bias with a representational mismatch.
Outcome:	Experiments on RM-Bench and JudgeBench show that AdaJudge outperforms strong off-the-shelf reward models and traditional pooling baselines.

From Text to Historical Ecological Knowledge: The Construction and Application of the Shan Jing Knowledge Base (2024.lrec-main)

Copied to clipboard

Ke Liang, Chu-Ren Huang, Xin-Lan Jiang

Piecing It All Together: Verifying Multi-Hop Multimodal Claims (2025.coling-main)

Challenge:	Traditional Ecological Knowledge (TEK) is a shared cultural heritage and crucial instrument to tackle environmental challenges.
Approach:	They propose to build a language resource based on Shanhai Jing (the classic of mountains and seas) written 2000 years ago and uses a stylized narrative and juxtaposition of knowledge from multiple domains to build the knowledge base.
Outcome:	The proposed knowledge base contains 1432 systematically classified entities and 3294 relationships.

Copied to clipboard

Haoran Wang, Aman Rangapur, Xiongxiao Xu, Yueqing Liang, Haroon Gharwi, Carl Yang, Kai Shu

Training Verifier to Assessing Complex Real-World Tool-Use Trajectories (2026.findings-acl)

Challenge:	Existing claim verification datasets often do not require systems to perform complex reasoning or effectively interpret multimodal evidence.
Approach:	They propose a task that requires models to reason over multiple pieces of evidence . they construct a large-scale dataset comprising 15k multi-hop claims paired with multimodal evidence - generated and refined using large language models with additional input from human feedback.
Outcome:	The proposed method is based on human performance benchmarks and human reasoning hops.

Copied to clipboard

Linzhuang Sun, Mingyang Chen, Hao Liang, Tianpeng Li, Zhou Yijie, Chenzheng Zhu, Tianyu Guo, Huanyao Zhang, Jingxuan Wei, Bihui Yu, Fan Yang, Wentao Zhang

Challenge:	Existing methods for training effective AI agents often resort to synthetic data generation.
Approach:	They propose a plug-and-play framework for data quality control in tool-use scenarios . they construct a tool-verify dataset and release a benchmark to assess its performance .
Outcome:	The proposed framework surpasses Qwen2.5-72B-Instruct on Tool-V-Bench and the previous APIGen-MT dataset.

Targeting the Needle, Ignoring the Haystack: Anchoring Crucial Cues for Evolving Scam Call Detection via an LLM-Assisted Classifier (2026.findings-acl)

Copied to clipboard

Tong Wu, Qinliang Su, Jianxing Yu, Bo Liang, Minhua Huang

Movie101: A New Movie Understanding Benchmark (2023.acl-long)

Challenge:	Existing methods for fraud detection on online service platforms often fail to generalize due to the scarcity of labeled data and the continuous evolution of conversational contexts.
Approach:	They propose a framework that anchors detection on Semantic Primitives . they prioritize stable evidence over conversational noise to ensure a verifiable fraud tactic .
Outcome:	The proposed framework achieves superior robustness and efficiency compared to baselines . it prioritizes stable evidence over diverse conversational noise .

Copied to clipboard

Zihao Yue, Qi Zhang, Anwen Hu, Liang Zhang, Ziheng Wang, Qin Jin

Distantly Supervised Contrastive Learning for Low-Resource Scripting Language Summarization (2024.lrec-main)

Challenge:	Existing methods to narrate movies with no actors are difficult to implement in real situations . a new metric is proposed to provide the best correlation with human evaluation .
Approach:	They propose a large-scale Chinese movie benchmark to help visually impaired enjoy movies . they propose metric called Movie Narration Score (MNScore) which achieves best correlation with human evaluation.
Outcome:	The proposed method outperforms baselines and the existing methods.

Copied to clipboard

Junzhe Liang, Haifeng Sun, Zirui Zhuang, Qi Qi, Jingyu Wang, Jianxin Liao

CFBench: A Comprehensive Constraints-Following Benchmark for LLMs (2025.acl-long)

Challenge:	Existing methods for code summarization are limited in resources and require atomic commands and category constraints to enhance code representations.
Approach:	They propose a framework that leverages limited atomic commands and category constraints to enhance code representations.
Outcome:	The proposed framework outperforms baseline methods in a number of domains and demonstrates superiority over competing frameworks.

Copied to clipboard

Tao Zhang, ChengLIn Zhu, Yanjun Shen, Wenjing Luo, Yan Zhang, Hao Liang, Tao Zhang, Fan Yang, Mingan Lin, Yujing Qiao, Weipeng Chen, Bin Cui, Wentao Zhang, Zenan Zhou

Context-aware Difference Distilling for Multi-change Captioning (2024.acl-long)

Challenge:	Existing evaluations of Large Language Models (LLMs) focus on fragmented constraints or narrow scenarios, but they overlook the comprehensiveness and authenticity of constraints from the user’s perspective.
Approach:	They propose a Chinese Comprehensive Constraints Following Benchmark for LLMs that compiles constraints from real-world instructions and constructs a systematic framework for constraint types.
Outcome:	The proposed framework integrates multi-dimensional assessment criteria with requirement prioritization, covering various perspectives of constraints, instructions, and requirement fulfillment.

Copied to clipboard

Yunbin Tu, Liang Li, Li Su, Zheng-Jun Zha, Chenggang Yan, Qingming Huang

MSD: Saliency-aware Knowledge Distillation for Multimodal Understanding (2021.findings-emnlp)

Challenge:	Existing methods for multi-change captioning are difficult because it requires a higher level of cognition to reason an arbitrary number of changes.
Approach:	They propose a context-aware difference distilling network to capture all genuine changes for yielding sentences.
Outcome:	The proposed network captures all genuine changes for yielding sentences on three public datasets.

Copied to clipboard

Woojeong Jin, Maziar Sanjabi, Shaoliang Nie, Liang Tan, Xiang Ren, Hamed Firooz

WebCPM: Interactive Web Search for Chinese Long-form Question Answering (2023.acl-long)

Challenge:	Current knowledge distillation models are limited and lack performance on multimodal datasets.
Approach:	They propose a multimodal knowledge distillation framework to transfer knowledge from a teacher on multimodal tasks by learning the teacher's behavior within each modality.
Outcome:	The proposed framework achieves better performance than KD on four multimodal datasets.

Copied to clipboard

Yujia Qin, Zihan Cai, Dian Jin, Lan Yan, Shihao Liang, Kunlun Zhu, Yankai Lin, Xu Han, Ning Ding, Huadong Wang, Ruobing Xie, Fanchao Qi, Zhiyuan Liu, Maosong Sun, Jie Zhou

Random Smooth-based Certified Defense against Text Adversarial Attack (2024.findings-eacl)

Challenge:	Long-form question answering requires two procedures: information retrieval and information synthesis.
Approach:	They propose a Chinese long-form question answering dataset called WebCPM . the dataset is based on a web search interface that engages with a search engine in real time .
Outcome:	The proposed dataset generates answers that are no worse than human-written ones . the dataset is the first Chinese LFQA dataset .

Copied to clipboard

Zeliang Zhang, Wei Yao, Susan Liang, Chenliang Xu

Prompting Large Language Models with Chain-of-Thought for Few-Shot Knowledge Base Question Generation (2023.emnlp-main)

Challenge:	Textual adversarial examples train models on the worst-case text generated by substituting words in original texts with synonyms, but due to the discrete word embedding representations, the large search space hinders the robust training efficiency.
Approach:	They propose to treat the word substitution as a continuous perturbation on the word embedding representation and apply random smooth techniques to approximate the word replacement operation.
Outcome:	The proposed method outperforms conventional methods and improves the robustness in training.

Copied to clipboard

Yuanyuan Liang, Jianing Wang, Hanlun Zhu, Lei Wang, Weining Qian, Yunshi Lan

Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge (2024.emnlp-main)

Challenge:	Existing methods for question generation over knowledge bases rely on annotated data for fine-tuning . emergence of Large Language Models (LLMs) has shown impressive generalization ability in few-shot tasks.
Approach:	They propose to use a logical form to generate a question in a reasoning problem . they propose to extend the prompting method into a method that can generate questions in logical forms .
Outcome:	The proposed method outperforms baselines on three public KBQG datasets.

Copied to clipboard

Yuxuan Wang, Yueqian Wang, Pengfei Wu, Jianxin Liang, Dongyan Zhao, Yang Liu, Zilong Zheng

Cross-Lingual Ability of Multilingual Masked Language Models: A Study of Language Structure (2022.acl-long)

Challenge:	despite advances in multimodal large language models, the challenge of interpreting long-form videos remains a challenge . despite advancements in video-language benchmarks, the inefficiency in temporal grounding and limited pre-trained context window size remains .
Approach:	They propose a framework that bootstraps MLLMs with advanced temporal grounding capabilities and broadens their contextual scope.
Outcome:	The proposed framework significantly enhances the temporal capabilities of existing MLLMs.

Copied to clipboard

Yuan Chai, Yaobo Liang, Nan Duan

RISER: Orchestrating Latent Reasoning Skills for Adaptive Activation Steering (2026.findings-acl)

Challenge:	Multilingual pre-trained language models have shown impressive cross-lingual ability.
Approach:	They argue that cross-language ability comes from commonality between languages . they create an artificial language by modifying property in source language .
Outcome:	The proposed model can be implemented in multilingual and low-resource language scenarios without cross-lingual supervision or aligned data.

Copied to clipboard

Wencheng Ye, Xiaoyang Yuan, Yi Bin, Hengyu Jin, Liang Peng, Pengpeng Zeng, Heng Tao Shen

GraphAgent: Agentic Graph Language Assistant (2025.emnlp-main)

Challenge:	Existing methods for domain-specific reasoning with large language models require updating parameter updates.
Approach:	They propose a plug-and-play intervention framework that adaptively steers LLM reasoning in activation space.
Outcome:	The proposed framework achieves zero-shot accuracy improvements of 3.4–6.5% over the base model while outperforming chain-of-thought-style reasoning with 2–3 higher token efficiency and robust accuracy gains.

Copied to clipboard

Yuhao Yang, Jiabin Tang, Lianghao Xia, Xingchen Zou, Yuxuan Liang, Chao Huang

ReasonRec: A Reasoning-Augmented Multimodal Agent for Unified Recommendation (2026.findings-acl)

Challenge:	Real-world data combines structured and unstructured formats, capturing explicit relationships and implicit semantic interdependencies.
Approach:	They propose GraphAgent, an automated agent pipeline addressing both explicit and implicit graph-enhanced semantic dependencies for predictive and generative tasks.
Outcome:	Extensive experiments on diverse datasets validate GraphAgent’s effectiveness in graph-related predictive and text generative tasks.

Copied to clipboard

Yihua Zhang, Mingfu Liang, Jiyan Yang, Rong Jin, Wen-Yen Chen, Yiping Han, Huayu Li, Buyun Zhang, Liang Luo, Luke Simon, Sijia Liu, Tianlong Chen, Xi Liu

RAAT: Relation-Augmented Attention Transformer for Relation Modeling in Document-Level Event Extraction (2022.naacl-main)

Challenge:	Recent advances in multimodal recommenders lack explicit reasoning and self-awareness of uncertainty.
Approach:	They propose a reasoning-augmented multimodal agent structured around a three-stage explicit reasoning pipeline.
Outcome:	The proposed agent improves ranking metrics and performance on four standard recommendation tasks across five real-world datasets.

Copied to clipboard

Yuan Liang, Zhuoxuan Jiang, Di Yin, Bo Ren

Cross-modal Attention Congruence Regularization for Vision-Language Relation Alignment (2023.acl-long)

Challenge:	Existing methods focus on sentencelevel event extraction (SEE), but they are inconsistent with actual situations.
Approach:	They propose a document-level event extraction framework which can model relation dependencies by a relation-augmented Attention Transformer.
Outcome:	The proposed framework can achieve state-of-the-art performance on two public datasets.

Copied to clipboard

Rohan Pandey, Rulin Shao, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency

A Semantic Filter Based on Relations for Knowledge Graph Completion (2021.emnlp-main)

Challenge:	Despite recent progress towards scaling up multimodal vision-language models, these models struggle on compositional generalization benchmarks such as Winoground.
Approach:	They propose to use a cross-modal attention regularization loss to enforce relation alignment by capturing the semantic relation ‘in’ to match the visual attention from the mug to the grass.
Outcome:	The proposed approach improves Winoground Group score by 5.75 points .

Copied to clipboard

Zongwei Liang, Junan Yang, Hui Liu, Keju Huang

VoxMind: An End-to-End Agentic Spoken Dialogue System (2026.acl-long)

Challenge:	Knowledge graph embedding is a new form of knowledge graphing that allows for better link prediction.
Approach:	They propose to use relational embedding to fit symmetry/antisymmetry and combination relationships.
Outcome:	The proposed model can fit symmetry/antisymmetry and combination relationships.

Copied to clipboard

Tianle Liang, Yifu Chen, Shengpeng Ji, Yijun Chen, Zhiyang Jia, Jingyu Lu, Fan Zhuo, Xueyi Pu, Yangzhuo Li, Zhou Zhao

Rˆ3Net:Relation-embedded Representation Reconstruction Network for Change Captioning (2021.emnlp-main)

Challenge:	Existing research on end-to-end spoken dialogue models has focused on core perception and generation, with limited exploration of tool-augmented extensions.
Approach:	They propose a framework to equip end-to-end spoken dialogue models with comprehensive agentic abilities by leveraging a 470-hour AgentChat dataset.
Outcome:	The proposed framework outperforms Gemini-2.5-Pro on spoken agent tasks while maintaining general conversational quality.

Copied to clipboard

Yunbin Tu, Liang Li, Chenggang Yan, Shengxiang Gao, Zhengtao Yu

ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System (2026.acl-long)

Challenge:	Existing work on change captioning uses a natural language sentence to describe disagreement between two images.
Approach:	They propose a Relation-embedded Representation Reconstruction Network to distinguish real change from clutter and irrelevant changes.
Outcome:	The proposed method achieves state-of-the-art on two public datasets.

Copied to clipboard

Jiacheng Liang, Yao Ma, Tharindu Kumarage, Satyapriya Krishna, Rahul Gupta, Kai-Wei Chang, Aram Galstyan, Charith Peris

Language Models Get a Gender Makeover: Mitigating Gender Bias with Few-Shot Data Interventions (2023.acl-short)

Challenge:	Existing red-teaming approaches focus on policy-level weaknesses, but they overlook systemic weaknesses . aRES exploits dual-targeting weaknesses in both the core LLM and the RM simultaneously.
Approach:	a new framework uncovers weaknesses in both the core and the reward models simultaneously . a "Safety Mentor" generates semantically coherent adversarial prompts .
Outcome:	ARES uncovers weaknesses in both the core LLM and the RM simultaneously . it fine-tunes the LM to detect harmful content, then optimizes the core model .

Copied to clipboard

Himanshu Thakur, Atishay Jain, Praneetha Vaddamanu, Paul Pu Liang, Louis-Philippe Morency

Converting the Point of View of Messages Spoken to Virtual Assistants (2020.findings-emnlp)

Challenge:	Existing approaches to de-bias pre-trained large language models focus on changes to training regime, but this is not feasible.
Approach:	They propose to de-bias a pre-trained model by fine-tuning it on only 10 examples . they show that the technique performs better than competitive baselines .
Outcome:	The proposed method performs better than competitive state-of-the-art baselines with minimal loss in language modeling ability.

Copied to clipboard

Gunhee Lee, Vera Zu, Sai Srujana Buddi, Dennis Liang, Purva Kulkarni, Jack FitzGerald

Aligning Cross-lingual Sentence Representations with Dual Momentum Contrast (2021.emnlp-main)

Challenge:	Using a voice message, virtual assistants extract the message and send it to the user’s contact, rather than properly converting it to “I love you.”
Approach:	They propose to take a voice message from one user, convert it to “I love you” and deliver it to its target user.
Outcome:	The proposed system can take a voice message from one user, convert the point of view of the message, and then deliver the result to its target user.

Copied to clipboard

Liang Wang, Wei Zhao, Jingming Liu

GRAG: Graph Retrieval-Augmented Generation (2025.findings-naacl)

Challenge:	Existing work uses sentences within the same batch as negatives, which suffers from easy negatives.
Approach:	They propose to align sentence representations from different languages into a unified embedding space . they adapt MoCo to further improve the quality of alignment .
Outcome:	The proposed model achieves state-of-the-art on several tasks.

Copied to clipboard

Yuntong Hu, Zhihan Lei, Zheng Zhang, Bo Pan, Chen Ling, Liang Zhao

ExpBERT: Representation Engineering with Natural Language Explanations (2020.acl-main)

Challenge:	Naive Retrieval-Augmented Generation (RAG) focuses on individual documents during retrieval and is not suitable for networked documents.
Approach:	They propose a novel divide-and-conquer strategy that retrieves optimal subgraph structure in linear time.
Outcome:	The proposed approach outperforms current state-of-the-art methods on graph reasoning benchmarks.

Copied to clipboard

Shikhar Murty, Pang Wei Koh, Percy Liang

JANUS: Joint Autoregressive and Non-autoregressive Training with Auxiliary Loss for Sequence Generation (2022.emnlp-main)

Challenge:	Existing models with explanations use semantic parsers to interpret explanations, but they can only parse low-level statements like "'wife' appears between o 1 and 2 "
Approach:	They propose to use natural language explanations to specify inductive biases . they use BERT fine-tuned on MultiNLI to "interpret" the explanations with respect to the input sentence .
Outcome:	The proposed method matches a baseline with less labeled data and improves on the baseline with the same amount of labele.

Copied to clipboard

Xiaobo Liang, Lijun Wu, Juntao Li, Min Zhang

Discourse Structure-Aware Prefix for Generation-Based End-to-End Argumentation Mining (2024.findings-acl)

Challenge:	Existing approaches to train autoregressive and non-autoregressive models only consider relevance of model parameters, ignoring correlations between the two manners.
Approach:	They propose a joint autoregressive and non-autoregressive training method using aUxiliary losS to enhance the model performance in both AR and NAR manners simultaneously.
Outcome:	The proposed method improves the model performance in both AR and NAR manners and reduces the inference latency.

Copied to clipboard

Yang Sun, Guanrong Chen, Caihua Yang, Jianzhu Bao, Bin Liang, Xi Zeng, Min Yang, Ruifeng Xu

PPTC Benchmark: Evaluating Large Language Models for PowerPoint Task Completion (2024.findings-acl)

Challenge:	Recent advances in AM models overlook the integration of supplementary discourse structure information, resulting in suboptimal outcomes.
Approach:	They propose a framework which generates discourse structure-aware prefixes for each layer of the generation model.
Outcome:	The proposed framework achieves state-of-the-art performance on two AM benchmarks.

Copied to clipboard

Yiduo Guo, Zekai Zhang, Yaobo Liang, Dongyan Zhao, Nan Duan

ESC-Eval: Evaluating Emotion Support Conversations in Large Language Models (2024.emnlp-main)

Challenge:	Recent evaluations of Large Language Models (LLMs) focus on their zero-shot/few-shot capabilities for basic natural language tasks and their ability to translate instructions into tool APIs.
Approach:	They propose a PowerPoint Task Completion benchmark to assess LLMs’ ability to create and edit PPT files based on user instructions.
Outcome:	The proposed system outperforms open-source and closed LLMs with 75.1% accuracy in single-turn dialogue testing but only achieves 6% session accuracy.

Copied to clipboard

Haiquan Zhao, Lingyu Li, Shisong Chen, Shuqi Kong, Jiaan Wang, Kexin Huang, Tianle Gu, Yixu Wang, Jian Wang, Liang Dandan, Zhixu Li, Yan Teng, Yanghua Xiao, Yingchun Wang

ConsistRM: Improving Generative Reward Models via Consistency-Aware Self-Training (2026.acl-long)

Challenge:	Emotion Support Conversation (ESC) is a crucial application for reducing stress and providing emotional guidance.
Approach:	They re-organize 2,801 role-playing cards to define roles of role-players . they train a specific role- playing model called ESC-Role which behaves more like a confused person than GPT-4 .
Outcome:	The proposed model behaves more like a confused person than GPT-4, and the model performs better than GPLs.

Copied to clipboard

Yu Liang, Liangxin Liu, Longzheng Wang, null Wangyan, Zhang Yueyang, Long Xia, Zhiyuan Sun, Daiting Shi

Challenge:	ConsistRM is a self-training framework that enables effective and stable GRM training without human annotations.
Approach:	They propose a self-training framework that enables effective and stable GRM training without human annotations.
Outcome:	The proposed framework outperforms vanilla Reinforcement Fine-Tuning (RFT) by 1.5% on five benchmark datasets.

DocStruct: A Multimodal Method to Extract Hierarchy Structure in Document for General Form Understanding (2020.findings-emnlp)

Copied to clipboard

Zilong Wang, Mingjie Zhan, Xuebo Liu, Ding Liang

Can Multimodal LLMs See Materials Clearly? A Multimodal Benchmark on Materials Characterization (2025.findings-emnlp)

Challenge:	Form understanding is a complex task because of the textual contents and organizational structure of forms.
Approach:	They propose to use multimodal methods to extract key-value pairs from forms . they validate their method on two benchmarks and demonstrate their effectiveness .
Outcome:	The proposed method is validated on two benchmarks, MedForm and FUNSD.

Copied to clipboard

Zhengzhao Lai, Youbin Zheng, Zhenyang Cai, Haonan Lyu, Jingpu Yang, Hong-Qing Liang, Yan Hu, Benyou Wang

Learning Language and Multimodal Privacy-Preserving Markers of Mood from Mobile Data (2021.acl-long)

Challenge:	characterization imaging data is fundamental to acquiring materials information.
Approach:	a team of researchers develop a benchmark for materials characterization imaging data . the goal is to bridge this gap by addressing 1,500 questions that require expert-level expertise.
Outcome:	a new benchmark for materials characterization imaging data is presented . the benchmark reveals that MLLMs perform poorly when addressing higher-level questions .

Copied to clipboard

Paul Pu Liang, Terrance Liu, Anna Cai, Michal Muszynski, Ryo Ishii, Nick Allen, Randy Auerbach, David Brent, Ruslan Salakhutdinov, Louis-Philippe Morency

Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive Translation (2021.acl-long)

Challenge:	Mental health conditions remain underdiagnosed in many countries despite access to advanced medical care . a new approach to learn mood markers from mobile data is needed to improve accuracy and improve learning from typed text.
Approach:	They propose to use mobile data to learn mood markers without identifying users through personal or protected attributes.
Outcome:	The proposed model obfuscates user identities while remaining predictive . future directions include better models and pre-learning from typed text .

Copied to clipboard

Liang Ding, Longyue Wang, Xuebo Liu, Derek F. Wong, Dacheng Tao, Zhaopeng Tu

HearSay Benchmark: Do Audio LLMs Leak What They Hear? (2026.findings-acl)

Challenge:	Knowledge distillation (KD) is commonly used to construct synthetic data for training non-autoregressive translation models.
Approach:	They propose to use knowledge distillation to generate training data for non-autoregressive translation models by leveraging pretraining.
Outcome:	The proposed approach achieves 28.2 and 33.9 BLEU points on the WMT14 English-German and WMT16 Romanian-English datasets.

Copied to clipboard

Jin Wang, Kaiwen Luo, Liang Lin, Weiliu Wang, Yitian Chen, Moayad Aloqaily, Xuehai Tang, Zhenhong Zhou, Kun Wang, Li Sun, Qingsong Wen

Adaptive Helpfulness–Harmlessness Alignment with Preference Vectors (2026.eacl-long)

Challenge:	Recent advances in audio large language models have led to their potential privacy implications unexplored.
Approach:	They propose a benchmark to examine whether ALLMs leak user privacy through acoustic voiceprints.
Outcome:	The proposed benchmark is constructed from over 22,000 real-world audio clips.

Copied to clipboard

Ren-Wei Liang, Chin Ting Hsu, Chan-Hung Yu, Saransh Agrawal, Shih-Cheng Huang, Chieh-Yen Lin, Shang-Tse Chen, Kuan-Hao Huang, Shao-Hua Sun

Giving Control Back to Models: Enabling Offensive Language Detection Models to Autonomously Identify and Mitigate Biases (2024.findings-emnlp)

Challenge:	Existing approaches to balancing helpfulness and harmlessness suffer from performance conflicts, limited controllability, and poor extendability.
Approach:	They propose a framework that allows users to control their own preferences and dynamically merge them at test time.
Outcome:	The proposed framework improves helpfulness without conservatism and smooth control over preference trade-offs.

Copied to clipboard

Jiapeng Liu, Weijie Li, Xiaochao Fan, Wenjun Deng, Liang Yang, Yong Li, Yufeng Diao

MacLaSa: Multi-Aspect Controllable Text Generation via Efficient Sampling from Compact Latent Space (2023.findings-emnlp)

Challenge:	Existing models often rely on specific words to predict offensive content, compromising model fairness and potentially exacerbates biases against vulnerable and minority groups.
Approach:	They propose a bias self-awareness and data self-iteration framework to help models identify and mitigate biases by integrating multiple natural language processing techniques.
Outcome:	The proposed framework reduces false positive rate of models in in-distribution and out-of-difference tests, enhances model accuracy and fairness, and shows promising performance improvements on larger datasets.

Copied to clipboard

Hanxing Ding, Liang Pang, Zihao Wei, Huawei Shen, Xueqi Cheng, Tat-Seng Chua

SimOAP: Improve Coherence and Consistency in Persona-based Dialogue Generation via Over-sampling and Post-evaluation (2023.acl-long)

Challenge:	Existing approaches to multi-aspect controllable text generation require expensive iteration / searching within the discrete text space during the decoding stage, resulting in a degradation of text quality due to the domain discrepancies between different aspects.
Approach:	They propose a framework that estimates compact latent space for multiple aspects and performs efficient Sampling with a fast sampler to eliminate domain discrepancies.
Outcome:	The proposed framework outperforms baselines on attribute relevance and textual quality while maintaining a high inference speed.

Copied to clipboard

Junkai Zhou, Liang Pang, Huawei Shen, Xueqi Cheng

RSDA: Restoring Stale Data Affinity via Dynamic Renovation Strategy for Mitigating Data Scarcity (2026.acl-long)

Challenge:	Existing work on large-scale corpora-based language models is limited and hard to generalize to all types of pre-trained language models.
Approach:	They propose a two-stage SimOAP strategy that over-samples and post-evaluates large-scale responses from existing models and selects a good response based on multiple evaluation metrics.
Outcome:	The proposed strategy outperforms baseline and automatic evaluation strategies in both automatic and human evaluations.

Copied to clipboard

Yidan Liang, Jia Zhu, Weijie Shi, Hanghui Guo, Yue Cui, Jiawei Shen, Guoqing Ma, Jingjiang Liu, Qingyu Niu, Yilin Wang, Shimin Di, Jiajie Xu

Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification (2026.acl-long)

Challenge:	High-quality data is the cornerstone of advancing large language models, but the supply of premium data is nearing depletion, while vast stale corpora remain underutilized.
Approach:	They propose a framework to restore stale data affinity by quantifying the latent value of samples and employing a dynamic renovation strategy selection mechanism to determine the optimal component-level strategy.
Outcome:	The proposed framework achieves performance improvements using less than 10% of the data volume, underscoring that the latent potential of stale corpora remains largely untapped.

Copied to clipboard

Zenghao Duan, Zhiyi Yin, Zhichao Shi, Liang Pang, Shaoling Jing, Zihe Huang, Jiayi Wu, Yu Yan, Jingcheng Deng, Huawei Shen, Xueqi Cheng

Challenge:	Large language models (LLMs) exhibit exceptional performance but pose inherent risks of generating toxic content.
Approach:	They propose a method that removes toxic subspaces from FFN parameters . they propose to use a lightweight method to eliminate toxic subespaces .
Outcome:	The proposed method achieves SOTA detoxification while preserving general capabilities without large-scale retraining.

m3P: Towards Multimodal Multilingual Translation with Multimodal Prompt (2024.lrec-main)

Copied to clipboard

Jian Yang, Hongcheng Guo, Yuwei Yin, Jiaqi Bai, Bing Wang, Jiaheng Liu, Xinnian Liang, LinZheng Chai, Liqun Yang, Zhoujun Li

Composable Cross-prompt Essay Scoring by Merging Models (2025.emnlp-main)

Challenge:	Existing multimodal neural machine translation models focus on bilingual translation, but experimental results show that they outperform the text-only baselines and multilingual multimodal methods by a large margin.
Approach:	They propose a framework to leverage the multimodal prompt to guide the Multimodal Multilingual Neural Machine Translation (m3P) this framework aligns the representations of different languages with the same meaning and generates the conditional vision-language memory for translation.
Outcome:	The proposed framework outperforms previous text-only baselines and multilingual multimodal methods by a large margin.

Copied to clipboard

Sanwoo Lee, Kun Liang, Yunfang Wu

RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs (2025.findings-emnlp)

Challenge:	Existing approaches to cross-prompt automated essay scoring use all available sources . however, using multiple sources for continual adaptation raises privacy concerns .
Approach:	They propose a source-free adaptation approach that selectively merges the parameters of individual models without further access to the source datasets.
Outcome:	The proposed method outperforms joint-training methods on all sources while maintaining computational efficiency.

Copied to clipboard

Zhongzhan Huang, Guoming Ling, Yupei Lin, Yandong Chen, Shanshan Zhong, Hefeng Wu, Liang Lin

PAGED: A Benchmark for Procedural Graphs Extraction from Documents (2024.acl-long)

Challenge:	a lack of comprehensive benchmarks for Routing large language models has hindered the development of routers.
Approach:	They propose a router-based benchmark to evaluate Routing large language models . the benchmark includes performance records for 12 popular LLM evaluations .
Outcome:	The proposed model-level scaling up phenomenon can surpass the best single model in the pool and many existing strong LLMs.

Copied to clipboard

Weihong Du, Wenrui Liao, Hongru Liang, Wenqiang Lei

FRVA: Fact-Retrieval and Verification Augmented Entailment Tree Generation for Explainable Question Answering (2024.findings-acl)

Challenge:	Existing methods for extraction of procedural graphs from documents are not solving the task well.
Approach:	They propose a benchmark to test automatic extraction of procedural graphs from documents . they involve three advanced large language models and enhance them with a novel self-refine strategy .
Outcome:	The proposed benchmark systematically examines the progress of current methods and explores the potential of emerging large language models (LLMs) on this task.

Copied to clipboard

Yue Fan, Hu Zhang, Ru Li, YuJie Wang, Hongye Tan, Jiye Liang

Expanding the Boundaries of Vision Prior Knowledge in Multi-modal Large Language Models (2026.eacl-long)

Challenge:	Existing methods for generating a entailment tree exhibit the reasoning chains from knowledge facts to predicted answers, but they have large fact search spaces and error accumulation problems resulting in the generation of invalid steps.
Approach:	They propose a Fact-Retrieval and Verification Augmented bidirectional entailment tree generation method that contains two systems.
Outcome:	The proposed method outperforms existing models and achieves state-of-the-art performance in fact selection and structural correctness.

Copied to clipboard

Qiao Liang, Yanjiang Liu, Weixiang Zhou, Ben He, Yaojie Lu, Hongyu Lin, Jia Zheng, Xianpei Han, Le Sun, Yingfei Sun

Summary-Oriented Vision Modeling for Multimodal Abstractive Summarization (2023.acl-long)

Challenge:	Existing research treats MLLMs as unified systems optimized through end-to-end training, but the impact of vision encoder’s prior knowledge is seldom investigated.
Approach:	They propose a metric to quantify the effect of prior knowledge on MLLM performance by integrating prior knowledge at the vision encoder level into a training framework.
Outcome:	The proposed training framework incorporates prior knowledge at the vision encoder level, and significantly boosts visual understanding capabilities of MLLMs.

Copied to clipboard

Yunlong Liang, Fandong Meng, Jinan Xu, Jiaan Wang, Yufeng Chen, Jie Zhou

COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values (2026.findings-eacl)

Challenge:	Existing studies on multimodal abstractive summarization focus on how to use extracted visual features to produce a concise summary given the multimodal data.
Approach:	They propose to improve the visual quality of the multimodal abstractive summarization model by capturing summary-oriented visual features.
Outcome:	The proposed approach achieves state-of-the-art under 44 languages and is highly effective on high-resource English datasets.

Copied to clipboard

Siwei Wu, JinCheng Ren, Xeron Du, Shuyue Guo, Xingwei Qu, Yiming Liang, Jie Liu, Yunwen Li, Tyler Loakman, Tianyu Zheng, Boyu Feng, Huaqing Yuan, Zili Wang, Jiaheng Liu, Wenhao Huang, Chenglin Cai, Haoran Que, Jian Yang, Yuelin Bai, Zekun Moore Wang, Zhouliang Yu, Qunshu Lin, Ding Pan, Yuchen Eleanor Jiang, Tiannan Wang, Wangchunshu Zhou, Shenzhi Wang, Xingyuan Bu, Minghao Liu, Guoyin Wang, Ge Zhang, Chenghua Lin

Semantic-Space Exploration and Exploitation in RLVR for LLM Reasoning (2026.findings-acl)

Challenge:	Existing Chinese preference datasets suffer from limited scale, restricted domain coverage, and insufficiently rigorous data validation.
Approach:	They propose an LLM-based data annotation pipeline with no human intervention to annotate Chinese preference datasets.
Outcome:	The proposed pipeline outperforms existing Chinese preference datasets on AlignBench and Chinese Reward Benchmark.

Copied to clipboard

Fanding Huang, Guanbo Huang, Xiao Fan, Yi He, Xiao Liang, Xiao Chen, Qinting Jiang, Faisal Nadeem Khan, Jingyan Jiang, Zhi Wang

XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation (2020.emnlp-main)

Challenge:	Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have substantially improved the reasoning abilities of Large Language Models (LLMs).
Approach:	They propose a method that balances exploration and exploitation in the hidden-state space of response trajectories.
Outcome:	The proposed model yields consistent improvements across models, algorithms and reasoning benchmarks.

Copied to clipboard

Yaobo Liang, Nan Duan, Yeyun Gong, Ning Wu, Fenfei Guo, Weizhen Qi, Ming Gong, Linjun Shou, Daxin Jiang, Guihong Cao, Xiaodong Fan, Ruofei Zhang, Rahul Agrawal, Edward Cui, Sining Wei, Taroon Bharti, Ying Qiao, Jiun-Hung Chen, Winnie Wu, Shuguang Liu, Fan Yang, Daniel Campos, Rangan Majumder, Ming Zhou

Optimal Partial Transport Based Sentence Selection for Long-form Document Matching (2022.coling-1)

Challenge:	XGLUE provides a benchmark dataset to train large-scale cross-lingual pre-trained models . XCLUE provides 11 diversified tasks that cover both understanding and generation scenarios .
Approach:	They introduce a new benchmark dataset to train large-scale cross-lingual pre-trained models using multilingual and bilingual corpora.
Outcome:	The proposed dataset is labeled in English and includes only natural language understanding tasks.

Copied to clipboard

Weijie Yu, Liang Pang, Jun Xu, Bing Su, Zhenhua Dong, Ji-Rong Wen

Challenge:	Existing methods for document matching are limited by the partial nature of the sentence-level matching signals.
Approach:	They propose a matching approach that equips existing document matching models with an Optimal Partial Transport component, namely OPT-Match, which selects the key sentences that play a major role in matching.
Outcome:	The proposed approach outperforms existing models on four publicly available datasets and the key sentences selected by it are consistent with human-provided rationales.

Instructions are all you need: Self-supervised Reinforcement Learning for Instruction Following (2026.acl-long)

Copied to clipboard

Qingyu Ren, Qianyu He, Powei Chang, Jie Zeng, Zeye Sun, Fei Yu, Jiaqing Liang, Yanghua Xiao

He He, Nanyun Peng, Percy Liang

Challenge:	Existing reinforcement learning approaches suffer from dependency on external supervision and sparse reward signals from multi-constraint tasks.
Approach:	They propose a self-supervised reinforcement learning framework that eliminates dependency on external supervision by deriving reward signals directly from instructions and generating pseudo-labels for reward model training.
Outcome:	The proposed framework achieves strong improvements across 3 in-domain and 5 out-of-domain datasets while maintaining computational efficiency.

Pun Generation with Surprise (N19-1)

Copied to clipboard

METNet: A Mutual Enhanced Transformation Network for Aspect-based Sentiment Analysis (2020.coling-main)

Challenge:	In this paper, we explore creative generation with a focus on puns.
Approach:	They propose an unsupervised approach to generating puns using lots of raw text and a surprisal principle.
Outcome:	The proposed approach generates puns 30% of the time, doubles the neural generation baseline.

Copied to clipboard

Bin Jiang, Jing Hou, Wanyue Zhou, Chao Yang, Shihan Wang, Liang Pang

Less, but Better: Efficient Multilingual Expansion for LLMs via Layer-wise Mixture-of-Experts (2025.acl-long)

Challenge:	Existing methods for learning complex sentences with multiple aspects are ill-equipped to learn complex sentences .
Approach:	They propose a mutual enhanced transformation network for the ABSA task . it improves representation learning of the aspect with contextual semantic features .
Outcome:	The proposed model improves representation learning of the aspect with contextual semantic features, giving the aspect more abundant information.

Copied to clipboard

Xue Zhang, Yunlong Liang, Fandong Meng, Songming Zhang, Yufeng Chen, Jinan Xu, Jie Zhou

SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Models (2022.acl-long)

Challenge:	Existing large language models (LLMs) have remarkable ability in high-resource languages, but their performance in multilingual scenarios is still limited.
Approach:	They propose a layer-wise expert allocation algorithm to determine the appropriate number of new experts for each layer.
Outcome:	The proposed method outperforms the previous state-of-the-art baseline with 60% fewer experts in the single-expansion setting and 33.3% fewer in the lifelong-expanding setting.

Copied to clipboard

Liang Wang, Wei Zhao, Zhuoyu Wei, Jingming Liu

LLM-based Open Domain Planning by Leveraging Entity-Attribute-Level Domain Models (2025.findings-emnlp)

Challenge:	Text-based methods lag behind graph embedding-based approaches for knowledge graph completion (KGC)
Approach:	They propose three types of negatives to improve contrastive learning to improve learning efficiency.
Outcome:	The proposed model outperforms embedding-based methods on several benchmark datasets.

Copied to clipboard

Dongning Rao, Songlin He, Zhihua Jiang, Ruishi Liang

Challenge:	Currently, large language models (LLMs) based on Open domain Natural language planning have limited application potential.
Approach:	They propose a dataset with a baseline for Open domain Natural language planning . the dataset provides the largest dataset for textual procedures to date .
Outcome:	The proposed dataset provides the largest dataset for textual procedures to date . it leverages entity-attribute-level action models to reveal relevant physical properties .

Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers (2025.findings-emnlp)

Copied to clipboard

Yingyu Liang, Heshan Liu, Zhenmei Shi, Zhao Song, Zhuoyan Xu, Jiale Zhao, Zhen Zhuang

FedSpaLLM: Federated Pruning of Large Language Models (2025.naacl-long)

Challenge:	a large computational cost for attention computation in large language models is a major obstacle .
Approach:	They propose a convolution-like structure for attention computation using convolution matrices . they then propose an efficient approximation method to approximate the attention matrix .
Outcome:	The proposed method achieves nearly linear time complexity in n1+o(1) time.

Copied to clipboard

Guangji Bai, Yijiang Li, Zilinghan Li, Liang Zhao, Kibaek Kim

Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Training (2024.acl-long)

Challenge:	Existing pruning methods assume public access to calibration data, which is impractical for privacy-sensitive applications.
Approach:	They propose a federated learning framework for pruning LLMs that prunes models locally based on private data while accounting for system heterogeneity and communication efficiency.
Outcome:	The proposed framework reduces communication overhead and personalizes pruning process based on client resources in federated settings.

Copied to clipboard

Junqing He, Kunhao Pan, Xiaoqun Dong, Zhuoyang Song, LiuYiBo LiuYiBo, Qianguosun Qianguosun, Yuxin Liang, Hao Wang, Enming Zhang, Jiaxing Zhang

Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation (P19-1)

Challenge:	Large language models suffer from severe hallucinations, compromising performance in knowledge-oriented QA, dialogue, and writing.
Approach:	They propose to enhance the information searching and reflection ability of large language models by training them in position-agnostic multi-step QA tasks to improve their model's accuracy.
Outcome:	The proposed model improves in multi-doc QA and other benchmarks by 13.7% absolute gain in shuffled settings, by 21.5% in passage retrieval task.

Copied to clipboard

Ning Dai, Jianze Liang, Xipeng Qiu, Xuanjing Huang

SHARP: Steering Hallucination in LVLMs via Representation Engineering (2025.emnlp-main)

Challenge:	Disentangling the content and style in the latent space is prevalent in text style transfer . recurrent neural networks (RNN) based encoder and decoder cannot deal with the long-term dependency .
Approach:	They propose a style transformer which disentangles style information in latent space . they propose encoding and decoding methods that disentangle style information .
Outcome:	The proposed method can achieve better style transfer and better content preservation.

Copied to clipboard

Junfei Wu, Yue Ding, Guofan Liu, Tianze Xia, Ziyue Huang, Dianbo Sui, Qiang Liu, Shu Wu, Liang Wang, Tieniu Tan

Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation (2025.findings-naacl)

Challenge:	Large Vision-Language Models (LVLMs) generate responses that are plausible but incorrect or unsupported—commonly referred to as hallucinations.
Approach:	They propose a representation-level intervention framework that modulates hallucination-related features during inference by probing their encoded features.
Outcome:	The proposed framework reduces hallucinations while maintaining the performance and generalization capabilities of Large Vision-Language Models (LVLMs).

Copied to clipboard

Sirui Xia, Xintao Wang, Jiaqing Liang, Yifei Zhang, Weikang Zhou, Jiaji Deng, Fei Yu, Yanghua Xiao

Towards Infinite-Long Prefix in Transformer (2025.emnlp-main)

Challenge:	Existing methods to enhance credibility and verifiability of large language models (LLMs) mainly focus on passage-level or paragraph-level references or citations, which fall short in verifikatability.
Approach:	They propose a method that provides sentence-level citations in LLM-generated responses.
Outcome:	The proposed method achieves 90% accuracy in long-form question-answering tasks.

Copied to clipboard

Yingyu Liang, Zhenmei Shi, Zhao Song, Chiwun Yang

Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention (2025.acl-long)

Challenge:	Prefix Learning is an empirically efficient and effective method for language models . but the theoretical understandings are limited on the performance of such methods .
Approach:	They propose a method that can train an ultra-long prefix in a stylized setting using the Neural Tangent Kernel framework.
Outcome:	The proposed method can achieve superior performance on vision, natural language, and math data.

Copied to clipboard

Jingyang Yuan, Huazuo Gao, Damai Dai, Junyu Luo, Liang Zhao, Zhengyan Zhang, Zhenda Xie, Yuxing Wei, Lean Wang, Zhiping Xiao, Yuqing Wang, Chong Ruan, Ming Zhang, Wenfeng Liang, Wangding Zeng

Learning Dynamic Representations and Policies from Multimodal Clinical Time-Series with Informative Missingness (2026.findings-acl)

Challenge:	Long-context modeling is crucial for next-generation language models, but high computational cost of standard attention mechanisms poses significant computational challenges.
Approach:	They propose a natively trained Sparse Attention mechanism that integrates algorithms with hardware-aligned optimizations to achieve efficient long-context modeling.
Outcome:	The proposed model maintains or exceeds Full Attention models across general benchmarks, long-context tasks, and instruction-based reasoning.

Copied to clipboard

Zihan Liang, Ziwen Pan, Ruoxuan Xiong

MinT: Boosting Generalization in Mathematical Reasoning via Multi-view Fine-tuning (2024.lrec-main)

Challenge:	Existing methods to accommodate missingness in clinical time series, but how to extract and use information carried by the observation process itself remains underexplored.
Approach:	They propose a patient representation learning framework that leverages informative missingness to learn multimodal clinical time series from structured and textual data.
Outcome:	The proposed framework improves offline treatment policy learning and adverse outcome prediction on ICU sepsis cohorts from MIMIC-III, MIMIC IV, and eICU.

Copied to clipboard

Zhenwen Liang, Dian Yu, Xiaoman Pan, Wenlin Yao, Qingkai Zeng, Xiangliang Zhang, Dong Yu

Mitigating Language-Level Performance Disparity in mPLMs via Teacher Language Selection and Cross-lingual Self-Distillation (2024.naacl-long)

Challenge:	Existing methods focus on specializing LMs in mathematical reasoning and rely on knowledge distillation.
Approach:	They propose a multi-view fine-tuning method that exploits existing mathematical problem datasets with diverse annotation styles.
Outcome:	The proposed method outperforms existing methods that rely heavily on LLM teachers . it grants models generalization ability across views and datasets, and the capability to learn from inaccurate or incomplete data.

Copied to clipboard

Haozhe Zhao, Zefan Cai, Shuzheng Si, Liang Chen, Yufeng He, Kaikai An, Baobao Chang

Multi-Scale Distribution Deep Variational Autoencoder for Explanation Generation (2022.findings-acl)

Challenge:	Large-scale multilingual pretrained language models (mPLMs) yield impressive performance on cross-language tasks, yet significant performance disparities exist across different languages within the same mPLm.
Approach:	They propose to leverage the learned knowledge from well-performing languages to guide under-performing ones within the same mPLM.
Outcome:	The proposed model shows that it can guide under-performing languages while minimizing language-level performance disparities across different mPLMs.

Copied to clipboard

ZeFeng Cai, Linlin Wang, Gerard de Melo, Fei Sun, Liang He

Bridging the Gap between Training and Inference: Multi-Candidate Optimization for Diverse Neural Machine Translation (2022.findings-naacl)

Challenge:	Existing methods for generating explanations for recommender systems produce generic explanations that fail to incorporate user and item specific details.
Approach:	They propose a multi-scale distribution deepvariational autoencoder with a prior network that eliminates noise while retaining meaningful signals in the input.
Outcome:	The proposed models can generate explanations with concrete input-specific contents.

Copied to clipboard

Huan Lin, Baosong Yang, Liang Yao, Dayiheng Liu, Haibo Zhang, Jun Xie, Min Zhang, Jinsong Su

Self-Critique Guided Iterative Reasoning for Multi-hop Question Answering (2025.findings-acl)

Challenge:	Existing diverse NMT models lack translation diversity due to a discrepancy between training and inference . despite the success of diverse NTM, there is still a lack of translation diversity .
Approach:	They propose a multi-candidate optimization framework for diverse NMT to deal with this defect.
Outcome:	The proposed framework is transparent to basic diverse NMT models, and universally makes better trade-off between diversity and quality.

Copied to clipboard

Zheng Chu, Huiming Fan, Jingchang Chen, Qianyu Wang, Mingda Yang, Jiafeng Liang, Zhongjie Wang, Hao Li, Guo Tang, Ming Liu, Bing Qin

Probing Structural Knowledge from Pre-trained Language Model for Argumentation Relation Classification (2022.findings-emnlp)

Challenge:	Large language models (LLMs) have demonstrated remarkable reasoning capabilities, but they still face challenges in knowledge-intensive multi-hop reasoning.
Approach:	They propose a method that uses self-critique feedback to guide iterative reasoning by enabling iteration and self-evaluation of its intermediate reasoning steps.
Outcome:	The proposed method surpasses the previous SOTA by 8.6% on three multi-hop reasoning datasets.

Copied to clipboard

Yang Sun, Bin Liang, Jianzhu Bao, Min Yang, Ruifeng Xu

Causality-aware Concept Extraction based on Knowledge-guided Prompting (2023.acl-long)

Challenge:	Argumentation relation classification (ARC) is the most challenging subtask of argumentation mining.
Approach:	They propose a dual prior graph neural network to explore probing knowledge and syntactical information for comprehensively modeling the relationship between AC pairs.
Outcome:	The proposed model outperforms the state-of-the-art models on three public datasets.

Copied to clipboard

Siyu Yuan, Deqing Yang, Jinxi Liu, Shuyu Tian, Jiaqing Liang, Yanghua Xiao, Rui Xie

Focus on the Target’s Vocabulary: Masked Label Smoothing for Machine Translation (2022.acl-short)

Challenge:	Concepts in knowledge graphs (KGs) are far from complete in existing knowledge graph models.
Approach:	They propose to equip a PLM-based extractor with a knowledge-guided prompt to alleviate concept bias by removing spurious co-occurrence correlations from existing knowledge.
Outcome:	The proposed prompt can alleviate concept bias and improve the performance of existing models.

Copied to clipboard

Liang Chen, Runxin Xu, Baobao Chang

AlignCap: Aligning Speech Emotion Captioning to Human Preferences (2024.emnlp-main)

Challenge:	Label smoothing and vocabulary sharing are widely used in neural machine translation models, but they can be conflicting and lead to suboptimal performance.
Approach:	They propose a mechanism that masks the soft label probability of source-side words to zero and integrates label smoothing with vocabulary sharing to improve translation quality.
Outcome:	The proposed mechanism improves translation quality and model calibration on bilingual and multilingual datasets, while retaining the original smoothing method.

Copied to clipboard

Ziqi Liang, Haoxiang Shi, Hanhui Chen

Dense Procedure Captioning in Narrated Instructional Videos (P19-1)

Challenge:	Existing methods for speech emotion capture often produce hallucinations and lose generalization on unseen speech.
Approach:	They propose to align speech emotion captioning to human preference based on large language model (LLM) and human preference regularization to eliminate factuality and faithfulness hallucinations.
Outcome:	Experiments show that AlignCap performs better than existing methods on Zero-shot SEC task.

Copied to clipboard

Botian Shi, Lei Ji, Yaobo Liang, Nan Duan, Peng Chen, Zhendong Niu, Ming Zhou

GRADE: Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems (2020.emnlp-main)

Challenge:	Existing models for video dense captioning learn video segments and generate captions without considering transcripts.
Approach:	They propose a model to generate procedure captions from narrated instructional videos . they extract procedures by a cross-modality module and generate captions by encoding video frames and transcripts within each extracted procedure.
Outcome:	The proposed model can extract procedures from narrated instructional videos and generate procedure captions by encoding video frames and transcripts.

Copied to clipboard

Lishan Huang, Zheng Ye, Jinghui Qin, Liang Lin, Xiaodan Liang

FocalOrder: Focal Preference Optimization for Reading Order Detection (2026.acl-long)

Challenge:	Existing evaluation metrics only consider surface features or utterance-level semantics, without explicitly considering the fine-grained topic transition dynamics of dialogue flows.
Approach:	They propose a graph-enhanced evaluation metric GRADE to evaluate dialogue coherence . GRADE incorporates utterance-level contextualized representations and fine-grained topic-level graph representations to improve communication logic.
Outcome:	The proposed evaluation metric outperforms state-of-the-art metrics on measuring diverse dialogue models in terms of Pearson and Spearman correlations with human judgments.

Copied to clipboard

Fuyuan Liu, Dianyu Yu, He Ren, Nayu Liu, Xiaomian Kang, Delai Qiu, Fa Zhang, Genpeng Zhen, Shengping Liu, Liang Jiaen, null Weihuang, Yining Wang, Junnan Zhu

Challenge:	Existing methods for document comprehension rely on uniform supervision, resulting in a performance degradation in the intermediate sections.
Approach:	They propose a framework driven by Focal Preference Optimization to detect reading order in document layouts.
Outcome:	The proposed framework outperforms competing baselines and surpasses large-scale general VLMs.

Little Giants: Synthesizing High-Quality Embedding Data at Scale (2025.naacl-long)

Copied to clipboard

Haonan Chen, Liang Wang, Nan Yang, Yutao Zhu, Ziliang Zhao, Furu Wei, Zhicheng Dou

OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs (2024.findings-emnlp)

Challenge:	Synthetic data generation is an increasingly popular way of training models without the need for large, manually labeled datasets.
Approach:	They propose a framework that aligns open-source small models to efficiently generate large-scale embedding data.
Outcome:	The proposed framework outperforms state-of-the-art embedding models by using only 1/10 of the GPT API calls.

Copied to clipboard

Jintian Zhang, Cheng Peng, Mengshu Sun, Xiang Chen, Lei Liang, Zhiqiang Zhang, Jun Zhou, Huajun Chen, Ningyu Zhang

ATP: AMRize Then Parse! Enhancing AMR Parsing with PseudoAMRs (2022.findings-naacl)

Challenge:	Recent advances in Large Language Models (LLMs) have significantly enhanced the generative capabilities for various NLP tasks, but they still suffer from hallucinations due to their exclusive reliance on parametric knowledge.
Approach:	They propose a framework that integrates retrieval tokens generated autoregressively into a single LLM to handle both tasks simultaneously in a unified forward pass.
Outcome:	The proposed framework bridges the traditionally separate training approaches for generation and retrieval by incorporating retrieval tokens generated autoregressively.

Copied to clipboard

Liang Chen, Peiyi Wang, Runxin Xu, Tianyu Liu, Zhifang Sui, Baobao Chang

Do Large Language Models have Problem-Solving Capability under Incomplete Information Scenarios? (2024.findings-acl)

Challenge:	Abstract Meaning Representation (AMR) implicitly involves compound semantic annotations.
Approach:	They propose to use auxiliary tasks which are semantically or formally related to enhance AMR parsing.
Outcome:	The proposed method achieves state-of-the-art performance on benchmarks especially in topology-related scores.

Copied to clipboard

Yuyan Chen, Yueze Li, Songzhou Yan, Sijia Liu, Jiaqing Liang, Yanghua Xiao

WatME: Towards Lossless Watermarking Through Lexical Redundancy (2024.acl-long)

Challenge:	Existing games such as "Who is undercover" are subjective and difficult to evaluate .
Approach:	They propose a game called BrainKing that evaluates LLMs' problem-solving capability under incomplete information scenarios.
Outcome:	The proposed game requires LLMs to identify target entities with limited yes-or-no questions and potential misleading answers.

Copied to clipboard

Liang Chen, Yatao Bian, Yang Deng, Deng Cai, Shuaiyi Li, Peilin Zhao, Kam-Fai Wong

Challenge:	Existing methods for text watermarking rely on arbitrary vocabulary partitioning during decoding, which compromises the availability of suitable tokens and significantly degrades the quality of responses.
Approach:	They propose a method that leverages linguistic prior knowledge of lexical redundancies in LLM vocabularies to seamlessly integrate watermarks.
Outcome:	The proposed approach preserves the expressive power of large language models while preserving watermark detectability.

KCVR: Knowledge-Centric Video Reconstruction for Structured Pedagogical Summarization via Dynamic Graph Planning (2026.acl-long)

Copied to clipboard

Jingjiang Liu, Jia Zhu, Hanghui Guo, Weijie Shi, Yue Cui, Xiaokang Jin, Yilin Wang, Qingyu Niu, Jiawei Shen, Guoqing Ma, Yidan Liang, Shimin Di, Jiajie Xu

PCA-Bench: Evaluating Multimodal Large Language Models in Perception-Cognition-Action Chain (2024.findings-acl)

Challenge:	Existing summarization methods compress content for gist browsing, but they break prerequisite logic in instructional videos.
Approach:	They propose a framework that decouples epistemic planning from content generation.
Outcome:	The proposed framework outperforms strong end-to-end baselines on Knowledge Progression Consistency and Learning Objective Coverage.

Copied to clipboard

Liang Chen, Yichi Zhang, Shuhuai Ren, Haozhe Zhao, Zefan Cai, Yuchi Wang, Peiyi Wang, Xiangdi Meng, Tianyu Liu, Baobao Chang

Beyond Language: Learning Commonsense from Images for Reasoning (2020.findings-emnlp)

Challenge:	a new multimodal decision-making benchmark evaluates the integrated capabilities of multimodal large language models.
Approach:	They propose a multimodal decision-making benchmark for evaluating MLLMs . they propose an automatic evaluation protocol to assess 10 prevalent ML models .
Outcome:	The proposed benchmark improves performance of multimodal large language models in three scenarios . the model is required to integrate multiple capabilities to make accurate decisions .

Copied to clipboard

Wanqing Cui, Yanyan Lan, Liang Pang, Jiafeng Guo, Xueqi Cheng

LS-Guard: Adaptive Safety Guardrails Tailored to Individual LLMs (2026.findings-acl)

Challenge:	Existing commonsense reasoning methods use raw texts to perform data representation and answer prediction tasks.
Approach:	They propose a novel approach to learn commonsense from images instead of limited raw texts or costly knowledge bases.
Outcome:	The proposed approach outperforms language-based methods on commonsense reasoning problems on two commonsence reasoning problems.

Copied to clipboard

Jinggui Liang, Lizi Liao

Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pre-training (2026.findings-eacl)

Challenge:	Existing security guardrails built from static datasets ignore each model’s unique safety profile and often force trade-offs between safety and utility.
Approach:	They propose a framework for learning model-specific guardrails tailored to each LLM’s vulnerabilities.
Outcome:	The proposed framework significantly outperforms baseline guardrails on multiple real-world LLMs, achieving superior robustness, adaptability, and generalization.

Copied to clipboard

Jeffrey Li, Joshua P Gardner, Doug Kang, Fangping Shi, Karanjeet Singh, Chun-Liang Li, Herumb Shandilya, David Leo Wright Hall, Oncel Tuzel, Percy Liang, Ludwig Schmidt, Hadi Pouransari, Fartash Faghri

HyperNetwork-based Decoupling to Improve Model Generalization for Few-Shot Relation Extraction (2023.emnlp-main)

Challenge:	Existing open-source datasets predominantly apply a single fixed extractor to all webpages.
Approach:	They propose to take a Union over different extractors to improve model performance . they show that extractor choice can significantly impact downstream task performance based on content type .
Outcome:	The proposed approach can increase the token yield of DCLM-Baseline by 71% while maintaining benchmark performance.

Copied to clipboard

Liang Zhang, Chulun Zhou, Fandong Meng, Jinsong Su, Yidong Chen, Jie Zhou

VLM2-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues (2025.acl-long)

Challenge:	Existing studies cannot generalize well to unseen relations using Prototypical Networks . current approaches are dependent on large amount of labeled data and cannot deal with unseense relations well.
Approach:	They propose a HyperNetwork-based Decoupling approach to improve FSRE generalization . they propose FSre models with an encoder, network generator and refined classifiers .
Outcome:	The proposed method improves the generalization of few-shot relation extraction models.

Copied to clipboard

Jianshu Zhang, Dongyu Yao, Renjie Pi, Paul Pu Liang, Yi R. Fung

Improving Encoder by Auxiliary Supervision Tasks for Table-to-Text Generation (2021.acl-long)

Challenge:	Existing vision-language models lack the ability to visually link matching visual cues across images or frames.
Approach:	They propose a benchmark to assess whether vision-language models can Visually Link Matching cues with 9 subtasks and over 3,000 test cases.
Outcome:	The proposed benchmarks on multiple images and videos do not demonstrate that vision-language models can link visual cues across images or frames.

Copied to clipboard

Liang Li, Can Ma, Yinliang Yue, Dayong Hu

Revisiting Parameter-Efficient Tuning: Are We Really There Yet? (2022.emnlp-main)

Challenge:	Experimental results show that our method not only has a good generalization but also outperforms previous methods on several metrics: BLEU, Content Selection, Content Ordering.
Approach:	They propose to build an entity graph from the input tables and introduce a reasoning module to perform reasoning on the graph.
Outcome:	The proposed method outperforms previous methods on several metrics: BLEU, Content Selection, Content Ordering.

Copied to clipboard

Guanzheng Chen, Fangyu Liu, Zaiqiao Meng, Shangsong Liang

Revisit Few-shot Intent Classification with PLMs: Direct Fine-tuning vs. Continual Pre-training (2023.findings-acl)

Challenge:	Pretrained language models (PLMs) are used as backbones to be combined with additional parameters and finetuned on downstream tasks in an end-to-end manner.
Approach:	They propose to use a fraction of parameters to tune pretrained language models (PLMs) this is the first comprehensive investigation into the training and evaluation of PETuning methods.
Outcome:	The proposed methods have been validated and tested with a rigorous evaluation protocol and have shown that they are unstable and inconsistent.

Copied to clipboard

Haode Zhang, Haowen Liang, Li-Ming Zhan, Xiao-Ming Wu, Albert Y.S. Lam

Improving Text Embeddings with Large Language Models (2024.acl-long)

Challenge:	Recent progress in intent detection relies on deep models and datasets with well-crafted annotations.
Approach:	They propose a continual pre-training approach to train deep learning models . they propose augmentation method and sequential self-distillation to boost performance .
Outcome:	The proposed method outperforms methods that employ continual pre-training on labeled datasets on few-shot intent detection tasks.

Copied to clipboard

Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei

An Examination of the Compositionality of Large Generative Vision-Language Models (2024.naacl-long)

Challenge:	Existing methods for obtaining text embeddings require complex training pipelines . authors leverage proprietary LLMs to generate diverse synthetic data for text embeds based on 93 languages .
Approach:	They propose a method for obtaining high-quality text embeddings using only synthetic data and less than 1k training steps.
Outcome:	The proposed method achieves strong performance on competitive text embedding benchmarks without using any labeled data.

Copied to clipboard

Teli Ma, Rong Li, Junwei Liang

3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset (2024.lrec-main)

Challenge:	Recent studies have focused on the compositionality of vision-language models (VLMs) however, the performance of GVLMs in multimodal compositional reasoning remains under-explored.
Approach:	They propose a syntactical bias score to quantify GVLMs' syntaktical bias . they propose 'SADE' task to assess GVLs's robustness against inclination toward syntical correctness.
Outcome:	The proposed benchmarks are based on evaluation metrics and current benchmarks.

Copied to clipboard

Xinyu Ma, Xuebo Liu, Derek F. Wong, Jun Rao, Bei Li, Liang Ding, Lidia S. Chao, Dacheng Tao, Min Zhang

VCSUM: A Versatile Chinese Meeting Summarization Dataset (2023.findings-acl)

Challenge:	Existing studies have shown that visual information in existing MMT datasets is insufficient, causing models to disregard it and overestimate their capabilities.
Approach:	They propose to use 3AM to create an ambiguity-aware multimodal machine translation dataset.
Outcome:	The proposed dataset includes more ambiguity and a greater variety of captions and images than other MMT datasets.

Copied to clipboard

Han Wu, Mingjie Zhan, Haochen Tan, Zhaohui Hou, Ding Liang, Linqi Song

EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving (2026.acl-long)

Challenge:	Compared to news and chat summarization, meeting summarizing is decelerated by the limited data.
Approach:	They propose a Chinese meeting summarization dataset that provides annotations for each transcript and a set of benchmark models to facilitate further research.
Outcome:	The proposed model can be used to summarize the content of meeting transcripts in Chinese.

Copied to clipboard

Mukai Li, Linfeng Song, Zhenwen Liang, Jiahao Xu, Shansan Gong, Qi Liu, Haitao Mi, Dong Yu

CLAIMCHECK: How Grounded are LLM Critiques of Scientific Papers? (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) have recently advanced the field of Automated Theorem Proving (ATP) Existing cost analyses regulate only the number of sampling passes, ignoring the substantial disparities in sampling costs.
Approach:	They propose to integrate two complementary methods into a unified EconRL pipeline to increase pass rates under constrained sampling passes.
Outcome:	The proposed method reduces token usage and sample passes while maintaining the original performance.

Copied to clipboard

Jiefu Ou, William Gantt Walden, Kate Sanders, Zhengping Jiang, Kaiser Sun, Jeffrey Cheng, William Jurayj, Miriam Wanner, Shaobo Liang, Candice Morgan, Seunghoon Han, Weiqi Wang, Chandler May, Hannah Recknor, Daniel Khashabi, Benjamin Van Durme

Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning (2025.acl-long)

Challenge:	CLAIMCHECK is an annotated dataset of NeurIPS 2023 and 2024 submissions and reviews from OpenReview.
Approach:	They annotate NeurIPS 2023 and 2024 submissions and reviews for weaknesses and dispute them for fine-grained labels of validity, objectivity, and type of the identified weaknesses.
Outcome:	The proposed dataset is richly annotated by ML experts for weaknesses statements in the reviews and the claims that they dispute, as well as fine-grained labels of validity, objectivity, and type of the identified weaknesses.

Copied to clipboard

Chenxi Huang, Shaotian Yan, Liang Xie, Binbin Lin, Sinan Fan, Yue Xin, Deng Cai, Chen Shen, Jieping Ye

Uncertainty Quantification for In-Context Learning of Large Language Models (2024.naacl-long)

Challenge:	Representation Fine-tuning (ReFT) is a proposed method for improving parameter efficiency . however, it yields suboptimal performance, as fixed-position representations have uncertain impact on outputs .
Approach:	They propose a method that fine-tunes critical representations in a low-rank linear subspace while freezing the base model.
Outcome:	The proposed method improves accuracy of LLaMA-2-7B and ReFT by 18.2 and 3.8 on GSM8K.

Copied to clipboard

Chen Ling, Xujiang Zhao, Xuchao Zhang, Wei Cheng, Yanchi Liu, Yiyou Sun, Mika Oishi, Takao Osaki, Katsushi Matsuda, Jie Ji, Guangji Bai, Liang Zhao, Haifeng Chen

ReasMark: A Robust Watermark for Attributing LLM Reasoning Under Knowledge Distillation Attacks (2026.acl-long)

Challenge:	Existing studies on in-context learning have focused on quantifying the uncertainty associated with the model's response, but they neglect the complexity of the LLM and the uniqueness of in-constitut learning.
Approach:	They propose a method to quantify the uncertainty associated with in-context learning and propose corresponding estimation method to quantify both types of uncertainties.
Outcome:	The proposed method offers an unsupervised way to understand the prediction of in-context learning in a plug-and-play fashion.

Copied to clipboard

Peizhuo Lv, Ruihua Zhou, Yunpeng Li, Ruigang Liang, Xingshuo Han, XiaoFeng Wang, Wei Dong, Yuling Liu

Enhancing Opinion Role Labeling with Semantic-Aware Word Representations from Semantic Role Labeling (N19-1)

Challenge:	Existing reasoning-enhanced large language models fail to provide reliable attribution of reasoning behavior once it is transferred through knowledge distillation.
Approach:	They propose to embed a reasoning-length gap in a model by querying a target domain and training a local student to imitate its outputs.
Outcome:	et al. show that ReasMark outperforms baselines while preserving task utility.

Copied to clipboard

Meishan Zhang, Peili Liang, Guohong Fu

Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs? (2025.findings-acl)

Challenge:	Existing work on opinion role labeling (ORL) is highly correlative with semantic role labeled (SRL) SRL is used to identify opinion holders and holder expressions for a given predicate.
Approach:	They propose a method to enhance opinion role labeling by presenting semantic-aware word representations which are learned from SRL.
Outcome:	The proposed method outperforms two other methods on a benchmark MPQA corpus and achieves higher F scores.

Copied to clipboard

Qingyuan Liang, Zhao Zhang, Zeyu Sun, Zheng Lin, Qi Luo, Xiao Yueyi, Yizhou Chen, Yuqun Zhang, Haotian Zhang, Lu Zhang, Chenbin Chenbin, Yingfei Xiong

Distance-Adaptive Quaternion Knowledge Graph Embedding with Bidirectional Rotation (2025.coling-main)

Challenge:	Existing research demonstrates the effectiveness of grammar-based code representations in small-scale models, showing their ability to reduce syntax errors and enhance performance.
Approach:	They develop a series of billion-scale grammar-based code representations that incorporate grammar rules into the code generation process.
Outcome:	Experiments on HumanEval and MBPP show that grammar-based representations reduce syntax errors and improve performance even in billion-scale models.

Copied to clipboard

Weihua Wang, Qiuyu Liang, Feilong Bao, Guanglai Gao

Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study (2025.findings-emnlp)

Challenge:	Existing knowledge graph embedding models measure the plausibility of triplets either through semantic matching or distance scoring functions.
Approach:	They propose to combine semantic matching with entity’s geometric distance to better measure the plausibility of triplets.
Outcome:	The proposed model outperforms existing models on well-known knowledge graph completion benchmark datasets.

Copied to clipboard

Yujun Zhou, Jiayi Ye, Zipeng Ling, Yufei Han, Yue Huang, Haomin Zhuang, Zhenwen Liang, Kehan Guo, Taicheng Guo, Xiangqi Wang, Xiangliang Zhang

ACE-M3: Automatic Capability Evaluator for Multimodal Medical Models (2025.coling-main)

Challenge:	Existing benchmarks that rely on final-answer accuracy fail to capture the quality of the reasoning process.
Approach:	They propose a fine-grained evaluation framework that assesses logical reasoning across three dimensions: overall accuracy, stepwise soundness, and representation-level probing.
Outcome:	The proposed framework assesses logical reasoning across three dimensions: overall accuracy, stepwise soundness, and representation-level probing.

Copied to clipboard

Xiechi Zhang, Shunfan Zheng, Linlin Wang, Gerard de Melo, Zhu Cao, Xiaoling Wang, Liang He

Dynamic Heterogeneous-Graph Reasoning with Language Models and Knowledge Representation Learning for Commonsense Question Answering (2023.acl-long)

Challenge:	Existing metrics for multimodal large language models only focus on token overlap and may not align with human judgment.
Approach:	They propose an open-source model that assesses the question answering abilities of multimodal large language models.
Outcome:	Experiments show that the ACE-M3 model performs better than existing models and is more reliable than existing metrics.

Copied to clipboard

Yujie Wang, Hu Zhang, Jiye Liang, Ru Li

Speech Sense Disambiguation: Tackling Homophone Ambiguity in End-to-End Speech Translation (2024.acl-long)

Challenge:	Existing methods for QA use knowledge graphs, but they ignore subgraph optimization and subgraph deepening.
Approach:	They propose a dynamic heterogeneous-graph reasoning method with LMs and knowledge representation learning that optimizes the structure and knowledge representing of the HKG using a two-stage pruning strategy and knowledge-representation learning.
Outcome:	The proposed method improves on existing methods at CommonsenseQA and OpenBookQA.

Copied to clipboard

Tengfei Yu, Xuebo Liu, Liang Ding, Kehai Chen, Dacheng Tao, Min Zhang

On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning (2026.acl-long)

Challenge:	End-to-end speech translation (ST) models require simultaneous crossmodal and crosslingual transformations to be effective.
Approach:	They propose a homophone-aware contrastive learning approach that integrates a speech-text masking strategy to reduce ambiguity.
Outcome:	The proposed approach achieves SOTA results on BLEU scores on different MuST-C and CoVoST ST tasks, underlining its effectiveness in reducing speech sense ambiguity.

Copied to clipboard

Changyu Liu, Yiyang Liu, Taowen Wang, Qiao Zhuang, James Chenhao Liang, Wenhao Yang, Renjing Xu, Qifan Wang, Dongfang Liu, Cheng Han

Smurfs: Multi-Agent System using Context-Efficient DFSDT for Tool Planning (2025.naacl-long)

Challenge:	Existing vision-language-action models are unsuitable for simulated or physical-world deployments . current methods fail when confronted with inherent real-world dynamic variability.
Approach:	They propose a test-time reinforcement learning framework that enables on-the-fly policy adaptation during inference.
Outcome:	Empirical results show that the proposed framework improves adaptability, stability and task success in dynamic, previously unseen scenarios.

Copied to clipboard

Junzhi Chen, Juhao Liang, Benyou Wang

A Survey of Multimodal Mathematical Reasoning: From Perception, Alignment to Reasoning (2026.acl-long)

Challenge:	Teaching large language models to use tools for solving complex problems can grant them human-like reasoning abilities.
Approach:	They propose a multi-agent system that enhances the Deep First Search Decision Tree (DFSDT) to address issues like error propagation and limited exploration in ReAct .
Outcome:	The proposed system reduces token usage by 60.9% compared to existing methods and performs on par with GPT-4-DFSDT.

Copied to clipboard

Tianyu Yang, Sihong Wu, Yilun Zhao, Zhenwen Liang, Lisen Dai, Chen Zhao, Minhao Cheng, Arman Cohan, Xiangliang Zhang

SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval (2024.findings-acl)

Challenge:	Multimodal mathematical Reasoning (MMR) has attracted increasing attention for its ability to solve mathematical problems involving both textual and visual modalities.
Approach:	They review the theoretical frameworks of multimodal reasoning and examine the challenges they face in visual math tasks.
Outcome:	The proposed models can solve problems involving both textual and visual modalities.

Copied to clipboard

Siwei Wu, Yizhi Li, Kang Zhu, Ge Zhang, Yiming Liang, Kaijing Ma, Chenghao Xiao, Haoran Zhang, Bohao Yang, Wenhu Chen, Wenhao Huang, Noura Al Moubayed, Jie Fu, Chenghua Lin

MetaGPT: Merging Large Language Models Using Model Exclusive Task Arithmetic (2024.emnlp-main)

Challenge:	Multi-modal information retrieval (MMIR) is a rapidly evolving field . current benchmarks for image-text pairings overlook the scientific domain .
Approach:	They develop a scientific domain-specific MMIR benchmark to evaluate image-text pairings using open-access research paper corpora.
Outcome:	The proposed benchmarks are based on 530K image-text pairs extracted from scientific documents with detailed captions.

Copied to clipboard

Yuyan Zhou, Liang Song, Bingning Wang, Weipeng Chen

Making Long-Context Language Models Better Multi-Hop Reasoners (2024.acl-long)

Challenge:	Existing methods face the trilemma of performance, data privacy, and computational costs, which hinders their application to LLMs.
Approach:	They propose a model-exclusive task arithmetic method for merging GPT-scale models which is data-agnostic and bypasses the heavy search process.
Outcome:	The proposed method achieves state-of-the-art performance on multiple tasks while minimizing the average loss difference between the merged model and each individual task model.

Copied to clipboard

Yanyang Li, Shuo Liang, Michael Lyu, Liwei Wang

From Feedback to Checklists: Grounded Evaluation of AI-Generated Clinical Notes (2025.emnlp-industry)

Challenge:	Recent advances in long-context modeling have enhanced language models for complex tasks, but they struggle with multi-hop reasoning and noisy contexts.
Approach:	They propose an approach that prompts LMs to supply attributions for each assertion during reasoning.
Outcome:	The proposed model achieves competitive performance on multi-hop reasoning benchmarks, closely paralleling proprietary LMs such as ChatGPT and Claude-instant.

Copied to clipboard

Karen Zhou, John Michael Giorgi, Pranav Mani, Peng Xu, Davis Liang, Chenhao Tan

Challenge:	Existing automated metrics fail to align with real-world physician preferences.
Approach:	They propose a pipeline that distills real user feedback into structured checklists for note evaluation that are interpretable, grounded in human feedback, and enforceable by LLM-based evaluators.
Outcome:	The proposed checklist outperforms baseline evaluations in coverage, diversity, and predictive power for human ratings.

JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse (2025.findings-acl)

Copied to clipboard

Muyao Li, Zihao Wang, Kaichen He, Xiaojian Ma, Yitao Liang

MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation (2022.naacl-main)

Challenge:	Visual Language Action models have shown promise in decision-making tasks, but have been neglected in previous work .
Approach:	They propose a new paradigm for visual language action models that enhances the foundation model prior to action-specific tuning by first post-training it on a curated set of visual and linguistic tasks using self-supervised learning.
Outcome:	The proposed model outperforms the best agent baseline on a diverse set of atomic tasks and surpasses imitation learning-based policies in Minecraft.

Copied to clipboard

Simiao Zuo, Qingru Zhang, Chen Liang, Pengcheng He, Tuo Zhao, Weizhu Chen

Guiding AMR Parsing with Reverse Graph Linearization (2023.findings-emnlp)

Challenge:	Existing methods for training pre-trained language models have limited practicality due to latency requirements.
Approach:	They propose a method that uses a Mixture-of-Experts structure to increase model capacity and inference speed.
Outcome:	The proposed method outperforms existing distillation methods on natural language understanding and question answering tasks.

Copied to clipboard

Bofei Gao, Liang Chen, Peiyi Wang, Zhifang Sui, Baobao Chang

BiSyn-GAT+: Bi-Syntax Aware Graph Attention Network for Aspect-based Sentiment Analysis (2022.findings-acl)

Challenge:	Abstract Meaning Representation (AMR) parsing aims to extract an abstract semantic graph from a sentence.
Approach:	They propose a new framework that allows for reversed linearization of AMR graphs . they propose to combine sequence-to-sequence approaches with a linearized graph .
Outcome:	The proposed framework outperforms the best AMR parser by 0.8 and 0.5 Smatch scores on the AMR 2.0 and AMR 3.0 datasets.

Copied to clipboard

Shuo Liang, Wei Wei, Xian-Ling Mao, Fei Wang, Zhiyong He

Attending via both Fine-tuning and Compressing (2021.findings-acl)

Challenge:	Aspect-based sentiment analysis is challenging because a sentence may contain multiple aspects or complicated relationships.
Approach:	They propose a bi-syntax aware Graph Attention Network to model the context of every aspect and sentiment relations across aspects for learning.
Outcome:	The proposed model outperforms the state-of-the-art methods on four benchmark datasets.

Copied to clipboard

Jie Zhou, Yuanbin Wu, Qin Chen, Xuanjing Huang, Liang He

Adaptive Schema-aware Event Extraction with Retrieval-Augmented Generation (2025.findings-emnlp)

Challenge:	Existing studies show that attention mechanisms can improve models' interpretation, but they are not explicable.
Approach:	They propose a framework consisting of a learner and a compressor to purify attention scores . they propose to fine-tune and compress the attention mechanism to obtain a more faithful explanation .
Outcome:	The proposed framework improves performance and interpretability on eight benchmark datasets.

Copied to clipboard

Sheng Liang, Hang Lv, Zhihao Wen, Yaxiong Wu, Yongyue Zhang, Hao Wang, Yong Liu

TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models (2025.findings-acl)

Challenge:	Event extraction is a task in natural language processing that involves identifying and extracting event information from unstructured text.
Approach:	They propose a paradigm that combines schema paraphrasing with schema retrieval-augmented generation.
Outcome:	The proposed paradigm retrieves paraphrased schemas and accurately generates targeted structures.

Copied to clipboard

Jaewoo Lee, Keyang Xuan, Chanakya Ekbote, Sandeep Polisetty, Yi R. Fung, Paul Pu Liang

Probing Graph Decomposition for Argument Pair Extraction (2023.findings-acl)

Challenge:	Existing pruning methods fail to account for unique token attributes across layers and modalities inherent to MLLMs.
Approach:	They propose a pruning framework that takes into account unique token attributes across layers and modalities inherent to MLLMs.
Outcome:	The proposed pruning framework outperforms existing pruning techniques on two state-of-the-art MLLMs.

Copied to clipboard

Yang Sun, Bin Liang, Jianzhu Bao, Yice Zhang, Geng Tu, Min Yang, Ruifeng Xu

Sheep’s Skin, Wolf’s Deeds: Are LLMs Ready for Metaphorical Implicit Hate Speech? (2025.acl-long)

Challenge:	Argument pair extraction (APE) aims to extract interactive argument pairs from two passages within a discussion.
Approach:	They propose a method to extract interactive argument pairs from two passages . they propose to decompose the probing graph into four sub-graphs based on inter- and intra-passage perspectives .
Outcome:	The proposed method improves on strong baselines on two benchmark datasets.

Copied to clipboard

Jingjie Zeng, Liang Yang, Zekun Wang, Yuanyuan Sun, Hongfei Lin

MPBoCo: Multimodal Prompt-based Boundary-enhanced Continual Framework for Joint Entity and Relation Extraction (2026.acl-long)

Challenge:	specialized models fail to detect implicit hate speech due to its indirectly expressed hateful intent . advanced LLMs often misinterpret metaphorical implicit hate content, resulting in its propagation .
Approach:	They propose a Jailbreaking strategy and Energy-based Constrained Decoding techniques to detect implicit hate speech in large language models.
Outcome:	The proposed model can generate metaphorical implicit hate speech, but it fails to detect it effectively.

Copied to clipboard

Guanglu Sun, Xinyu Liu, Lili Liang, Yang Yu, Fei Lang, Suxia Zhu, Ming Liu

H-MAS: Hierarchical Multi-Agent Scheduling for Multi-Tenant LLM Serving (2026.findings-acl)

Challenge:	Existing methods struggle to balance real-time adaptability and computational efficiency in continual learning scenarios.
Approach:	They propose a Continual Multimodal Entity and Relation Joint Extraction task and a Multimodal Prompt-based Boundary-enhanced Continuum framework that stores task-specific knowledge via learnable multimodal prompts.
Outcome:	The proposed framework outperforms baseline methods in real-world scenarios by 5.5% and 7.2%.

Copied to clipboard

Yuhan Liu, Cong Xu, Qi Jia, Yihua Wang, Feiyu Chen, Liang Jin, Lu Liu, Yaqian Zhao, Yuting Ding, Xiang Li

Challenge:	Multi-tenant Model-as-a-Service (MaaS) workloads exhibit non-stationarity across multiple time scales . existing request schedulers often rely on a fixed policy that remains unchanged at runtime .
Approach:	They propose a hierarchical multi-agent scheduler that operates in a layered closed loop . they propose to maintain 1.2–3.0 higher Goodput than SGLang and vLLM .
Outcome:	Experiments show that H-MAS achieves 1.2–3.0 higher Goodput than SGLang and vLLM . it maintains more stable QoS under diverse request lengths and heterogeneous SLO targets .

Efficient Hyperparameter Optimization for LLM Reinforcement Learning (2026.acl-long)

Copied to clipboard

Minping Chen, Bowen Xiao, Du Liang, Chuxuan Zeng, Zeyi Wen

Data-to-Text Generation with Style Imitation (2020.findings-emnlp)

Challenge:	Existing hyperparameter optimization methods are inefficient in reinforcement learning due to model scale and resource-intensive training cycles.
Approach:	They propose a hyperparameter optimization method that adapts both model size and training budget as fidelity.
Outcome:	The proposed method significantly improves the computational efficiency of each trial (up to 14.9) over existing HPO methods.

Copied to clipboard

Shuai Lin, Wentao Wang, Zichao Yang, Xiaodan Liang, Frank F. Xu, Eric Xing, Zhiting Hu

Graph-based Relation Mining for Context-free Out-of-vocabulary Word Embedding Learning (2023.acl-long)

Challenge:	Recent approaches to data-to-text generation focus on improving content fidelity, but lack explicit control over writing styles.
Approach:	They propose a way to control writing styles by using existing sentences as "soft" templates . they conduct experiments in restaurants and sports domains to test their approach .
Outcome:	The proposed approach achieves stronger performance than a range of comparison methods.

Copied to clipboard

Ziran Liang, Yuyin Lu, HeGang Chen, Yanghui Rao

PEDNet: A Persona Enhanced Dual Alternating Learning Network for Conversational Response Generation (2020.coling-main)

Challenge:	Existing word embedding methods fail to model complex word formation well.
Approach:	They propose a graph-based relation mining method for OOV word embedding learning that can infer high-quality embeddables for OV words through passing and aggregating semantic attributes and relational information in the WRG.
Outcome:	The proposed method outperforms state-of-the-art models on both intrinsic and downstream tasks when faced with OOV words.

Copied to clipboard

Bin Jiang, Wanyue Zhou, Jingxu Yang, Chao Yang, Shihan Wang, Liang Pang

Training Classifiers with Natural Language Explanations (P18-1)

Challenge:	Existing persona-based dialogue models generate personalized responses using predefined persona information, but they lack personality.
Approach:	They propose a persona-based dual Alternating Learning Network that generates personalized responses using predefined persona information.
Outcome:	The proposed method produces more personalized responses than baseline methods.

Copied to clipboard

Braden Hancock, Paroma Varma, Stephanie Wang, Martin Bringmann, Percy Liang, Christopher Ré

AssistSR: Task-oriented Video Segment Retrieval for Personal AI Assistant (2022.findings-emnlp)

Challenge:	a semantic parser converts explanations into programmatic labeling functions . a standard protocol for obtaining a labeled dataset provides only one bit of information per example .
Approach:	They propose a framework where an annotator provides an explanation for each labeling decision . they use a semantic parser to convert these explanations into programmatic labeling functions .
Outcome:	The proposed framework trains classifiers faster by providing explanations instead of labels . the proposed framework is based on a rule-based semantic parser .

Copied to clipboard

Weixian Lei, Difei Gao, Yuxuan Wang, Dongxing Mao, Zihan Liang, Lingmin Ran, Mike Zheng Shou

Robust Encodings: A Framework for Combating Adversarial Typos (2020.acl-main)

Challenge:	Currently, personal AI assistants on the phone and AR glasses can assist our daily life in addressing our questions like "how to adjust the date for this watch?"
Approach:	They propose a task that asks a question about affordance of items in our daily life . they construct a dataset that contains 3.2k multimodal questions on 1.6k video segments .
Outcome:	The proposed task outperforms baseline methods while still having room for improvement in the future.

Copied to clipboard

Erik Jones, Robin Jia, Aditi Raghunathan, Percy Liang

Flexibly Utilize Memory for Long-Term Conversation via a Fragment-then-Compose Framework (2025.emnlp-main)

Challenge:	Existing procedures to defend against adversarial perturbations of inputs are heuristic in nature and susceptible to stronger attacks.
Approach:	They propose a framework that provides robustness without compromises on model architecture.
Outcome:	The proposed framework achieves robustness on six tasks while incompatible with state-of-the-art models like BERT.

Copied to clipboard

Cai Ke, Yiming Du, Bin Liang, Yifan Xiang, Lin Gui, Zhongyang Li, Baojun Wang, Yue Yu, Hui Wang, Kam-Fai Wong, Ruifeng Xu

Speculative Reward Model Boosts Decision Making Ability of LLMs Cost-Effectively (2025.acl-industry)

Challenge:	Large language models extract useful information from conversation history to enhance the response in long-term conversations.
Approach:	They propose a Fragment-then-Compose framework to optimize memory utilization for long-term open-domain conversation.
Outcome:	The proposed framework can be used to extract useful information from conversation history . it can be adapted to different situations and improve response generation .

Copied to clipboard

Jiawei Gu, Shangsong Liang

Actively Learn from LLMs with Uncertainty Propagation for Generalized Category Discovery (2024.naacl-long)

Challenge:	Existing approaches prioritize performance but overlook the balance between effectiveness and computational cost.
Approach:	They propose a plug-and-play framework that integrates with existing search strategies to improve LLM decision-making while maintaining efficiency.
Outcome:	The proposed framework reduces costs to 1/10 of the original search framework while maintaining effectiveness.

Copied to clipboard

Jinggui Liang, Lizi Liao, Hao Fei, Bobo Li, Jing Jiang

Challenge:	Generalized category discovery (GCD) is a crucial task in open-world computing, where new categories frequently emerge, necessitating models that can adapt and learn continually.
Approach:	They propose to integrate the feedback from LLMs into an active learning paradigm to simplify the labeling task and minimize the spread of inaccurate feedback.
Outcome:	The proposed approach significantly improves baseline models at a nominal average cost.

SPEAK: Spiking Neurons as an Entropy-Aware Tokenizer for Large Language Models (2026.acl-long)

Copied to clipboard

Ming Chen, Wenyao Li, Chao Liang, Shi Gu, Peng Lin, De Ma, Huajin Tang, Qian Zheng, Gang Pan

Causal Representation Learning from Multimodal Clinical Records under Non-Random Modality Missingness (2025.emnlp-main)

Challenge:	Existing tokenizers fail to explicitly leverage historical tokenization results . large language models (LLMs) have demonstrated remarkable effectiveness across NLP tasks .
Approach:	They propose a tokenizer that integrates spiking neurons to explicitly leverage historical tokenization results.
Outcome:	The proposed tokenizer leverages historical tokenization results, but does not selectively leverage history based on contextual relevance.

Copied to clipboard

Zihan Liang, Ziwen Pan, Ruoxuan Xiong

MiniLongBench: The Low-cost Long Context Understanding Benchmark for Large Language Models (2025.acl-long)

Challenge:	Clinical notes are often missing from clinical notes, resulting in modality missing-not-at-random (MMNAR) . large language models fine-tuned or adapted to clinical tasks have shown promise in medical reasoning, outcome prediction, and decision support.
Approach:	They propose a framework that leverages observed data and informative missingness in multimodal clinical records.
Outcome:	The proposed framework leverages observed data and informative missingness in multimodal clinical records.

Copied to clipboard

Zhongzhan Huang, Guoming Ling, Shanshan Zhong, Hefeng Wu, Liang Lin

Unleashing the Power of Imbalanced Modality Information for Multi-modal Knowledge Graph Completion (2024.lrec-main)

Challenge:	Existing LCU benchmarks for large language models often result in prohibitively high evaluation costs . existing benchmarks exhibit significant redundancy, which means inefficiency in evaluation .
Approach:	They propose a data compression method tailored for long-text data with sparse information characteristics.
Outcome:	The proposed method reduces evaluation costs to 4.5% of the long-text benchmark LongBench . the proposed method is based on a long-term LCU benchmark with sparse information characteristics .

Copied to clipboard

Yichi Zhang, Zhuo Chen, Lei Liang, Huajun Chen, Wen Zhang

Unsupervised Dense Retrieval with Relevance-Aware Contrastive Pre-Training (2023.findings-acl)

Challenge:	Existing MMKGC methods overlook the imbalance problem of modality information among entities, resulting in inadequate modal fusion and inefficient utilization of the raw modality.
Approach:	They propose to integrate structural, visual, and textual information of entities into the discriminant models to predict the missing triples.
Outcome:	The proposed model outperforms 19 recent methods and achieves state-of-the-art results on three public MMKGC benchmarks.

Copied to clipboard

Yibin Lei, Liang Ding, Yu Cao, Changtong Zan, Andrew Yates, Dacheng Tao

SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval (2023.acl-long)

Challenge:	Dense retrievers have impressive performance, but their demand for abundant training data limits their application scenarios.
Approach:	They propose a method which uses unlabeled data to construct pseudo-positive examples from unlabelled data and then contrastively weighs the contrastive loss of different pairs according to the estimated relevance.
Outcome:	The proposed method beats the SOTA unsupervised Contriever model on BEIR and open-domain QA retrieval benchmarks and is a good few-shot learner.

Copied to clipboard

Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei

Locality Preserving Sentence Encoding (2021.findings-emnlp)

Challenge:	SimLM uses a simple bottleneck architecture that learns to compress the passage information into a dense vector through self-supervised pre-training.
Approach:	They propose a simple yet effective pre-training method for dense passage retrieval that learns to compress the passage information into a dense vector through self-supervised pre-tuning.
Outcome:	The proposed method outperforms multi-vector approaches on large-scale passage retrieval datasets and shows significant improvements over baselines.

Copied to clipboard

Changrong Min, Yonghe Chu, Liang Yang, Bo Xu, Hongfei Lin

The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis (2026.acl-long)

Challenge:	Existing word embeddings can be used to learn sentence embedds on the sentence level.
Approach:	They propose a sentence embedding method that uses the inner product to compute semantic similarity between sentences.
Outcome:	The proposed method encodes sentences better in the sense of semantic structures.

Copied to clipboard

Zihao Wei, Liang Pang, Jiahao Liu, Wenjie Shi, Jingcheng Deng, Shicheng Xu, Zenghao Duan, Jingang Wang, Fei Sun, Huawei Shen, Xueqi Cheng

OPERA: Operation-Pivoted Discrete Reasoning over Text (2022.naacl-main)

Challenge:	Explicit reasoning trajectories increase performance but often trigger overthinking . despite its importance, this study examines how each step of reasoning affects the final outcome .
Approach:	They propose a Reasoning Completion Point Detector that detects the RCP by monitoring rank dynamics of termination tokens.
Outcome:	The proposed method reduces token usage by up to 44% while preserving accuracy.

Copied to clipboard

Yongwei Zhou, Junwei Bao, Chaoqun Duan, Haipeng Sun, Jiahui Liang, Yifan Wang, Jing Zhao, Youzheng Wu, Xiaodong He, Tiejun Zhao

Self-Training with Differentiable Teacher (2022.findings-naacl)

Challenge:	Existing methods to predict logical forms ignore the utilization of symbolic operations and lack reasoning ability and interpretability.
Approach:	They propose an operation-pivoted discrete reasoning framework that uses symbolic operations as neural modules to facilitate reasoning ability and interpretability.
Outcome:	Extensive experiments on DROP and RACENum datasets show the reasoning ability of OPERA.

Copied to clipboard

Simiao Zuo, Yue Yu, Chen Liang, Haoming Jiang, Siawpeng Er, Chao Zhang, Tuo Zhao, Hongyuan Zha

SCOPE: Preserving Modality-Specific Cues to Mitigate Modality Laziness in Multimodal Learning (2026.findings-acl)

Challenge:	Existing methods for self-training are interpreted as teacher-student frameworks, where the teacher generates pseudo-labels and the student makes predictions.
Approach:	They propose a differentiable self-training method that treats teacher-student as a Stackelberg game where a leader is always in a more advantageous position than a follower.
Outcome:	The proposed model outperforms existing methods on semi- and weakly-supervised learning tasks on semi and weak supervised tasks.

Copied to clipboard

Jingfan Yang, Rui Zhang, Liang Hong, Ke Yuan

A Data-Centric Framework for Composable NLP Workflows (2020.emnlp-demos)

Challenge:	Existing approaches to learning multimodal representations emphasize shared semantics and overlook modality-specific cues.
Approach:	They propose a framework for learning complete multimodal representations using shared and practical cues.
Outcome:	SCOPE outperforms SOTA benchmarks on four datasets and achieves 27.10% accuracy improvement.

Copied to clipboard

Zhengzhong Liu, Guanxiong Ding, Avinash Bukkittu, Mansi Gupta, Pengzhi Gao, Atif Ahmed, Shikun Zhang, Xin Gao, Swapnil Singhavi, Linwei Li, Wei Wei, Zecong Hu, Haoran Shi, Xiaodan Liang, Teruko Mitamura, Eric Xing, Zhiting Hu

Challenge:	Empirical natural language processing (NLP) systems involve interoperation among multiple components . a wealth of NLP toolkits exist ( 4), such as spaCy, DKPro, CoreNLP.
Approach:	They propose a unified open-source framework that supports fast development of NLP workflows . framework includes processors for NLP tasks, visualization, and annotation .
Outcome:	The framework offers processors for NLP tasks, visualization, and annotation, and is extensible . it is delivered through two modularized yet integratable open-source projects, Forte and Stave .

Gold-Medal-Level Olympiad Geometry Solving with Efficient Heuristic Auxiliary Constructions (2026.acl-long)

Copied to clipboard

Boyan Duan, Xiao Liang, Shuai Lu, Yaoxiang Wang, Yelong Shen, Kai-Wei Chang, Ying Nian Wu, Mao Yang, Weizhu Chen, Yeyun Gong

PibE-MPP: A Play-it-by-Ear Masking Performance Plug-in for LLMs (2026.findings-acl)

Challenge:	Existing methods for geometry theorem proving in Euclidean geometry are challenging and require a neural network to perform.
Approach:	They propose a method for adding auxiliary points in geometry that runs on CPUs without relying on neural network-based inference.
Outcome:	The proposed method achieves silver-medal-level human performance on IMO-30 benchmark.

Copied to clipboard

Mengwei Wang, Simin Niu, Xun Liang, Yuefeng Ma, Sensen Zhang, Jiawei Yang, Shichao Song, Hanyu Wang, Huayi Lai

One2Set + Large Language Model: Best Partners for Keyphrase Generation (2024.emnlp-main)

Challenge:	Random masking is a widely adopted classic baseline in large language models (LLMs).
Approach:	They propose a play-it-by-ear masking performance plug-in which enables LLMs to adaptively select masking target combinations for each task.
Outcome:	The proposed performance plug-in retains the advantages and mitigates the drawbacks of random masking in large language models.

Copied to clipboard

Liangying Shao, Liang Zhang, Minlong Peng, Guoqi Ma, Hao Yue, Mingming Sun, Jinsong Su

Speeding Up Neural Machine Translation Decoding by Cube Pruning (D18-1)

Challenge:	Existing selection methods make redundant selections, causing poor recall and accuracy.
Approach:	They propose a framework to generate keyphrases from a one2set-based model and an LLM as selector.
Outcome:	The proposed framework surpasses state-of-the-art models in absent keyphrase prediction.

Copied to clipboard

Wen Zhang, Liang Huang, Yang Feng, Lei Shen, Qun Liu

Mitigating Matthew Effect: Multi-Hypergraph Boosted Multi-Interest Self-Supervised Learning for Conversational Recommendation (2024.emnlp-main)

Challenge:	Neural machine translation suffers from slow translation speed due to the large search space . a trade-off has to be made between translation quality and speed, argues a new study .
Approach:	They apply cube pruning technique to speed up dynamic programming into neural machine translation to speed it up.
Outcome:	The proposed method can translate faster on GPUs and CPUs with better translation quality than naive beam search.

Copied to clipboard

Yongsen Zheng, Ruilin Xu, Guohua Wang, Liang Lin, Kwok-Yan Lam

Pseudo2Real: Task Arithmetic for Pseudo-Label Correction in Automatic Speech Recognition (2026.findings-acl)

Challenge:	Existing methods to mitigate Matthew effect in offline recommendation systems are not effective . a number of studies have identified two root causes for the Matthew effect .
Approach:	They propose a framework to address the Matthew effect in conversational recommendation systems . they build hypergraphs to learn multi-level user interests to alleviate the Matthew effec .
Outcome:	The proposed framework achieves state-of-the-art performance on four CRS-based datasets . it improves on item-, entity-, word-oriented multiple-channel hypergraphs compared with existing methods .

Copied to clipboard

Yi-Cheng Lin, Yu-Hsuan Li Liang, Hsuan Su, Tzu-Quan Lin, Shang-Tse Chen, Yun-Nung Chen, Hung-yi Lee

Decide less, communicate more: On the construct validity of end-to-end fact-checking in medicine (2026.findings-acl)

Challenge:	ASR models can be used to correct accent-specific errors without ground truth . pseudo-labels inherit the teacher model's systematic biases, authors say .
Approach:	They propose a parameter-space correction technique that captures pseudo-label biases . they propose achieving up to 35% relative WER reduction on a pseudo-labeled target model .
Outcome:	The proposed model achieves 35% relative WER reduction on ten African accents with the Whisper tiny model.

Copied to clipboard

Sebastian Antony Joseph, Lily Chen, Barry Wei, Michael Mackert, Iain James Marshall, Paul Pu Liang, Ramez Kouzy, Byron C Wallace, Junyi Jessy Li

Interpreting Positional Information in Perspective of Word Order (2023.acl-long)

Challenge:	Evidence-based medicine connects to every individual, yet the nature of it is highly technical . e-fact-checking systems that connect to medical decisions are largely unused . we examine how clinical experts verify real claims from social media .
Approach:	They propose that fact-checking should be approached as an interactive communication problem . they argue that social media and AI have made medical knowledge accessible .
Outcome:	The proposed method is based on the work of a clinical expert on social media . it reveals that the method is difficult to connect claims to clinical trials .

Copied to clipboard

Zhang Xilong, Liu Ruochen, Liu Jin, Liang Xuefeng

Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation (2020.acl-main)

Challenge:	Attention mechanism is a powerful and effective method utilized in natural language processing, but it is insensitive to positional information.
Approach:	They propose a weight concatenation operation to evaluate its efficacy in machine translation tasks.
Outcome:	The proposed operation can encode positional information and confirms our hypothesis.

Copied to clipboard

Weixin Liang, James Zou, Zhou Yu

Skip-Thinking: Chunk-wise Chain-of-Thought Distillation Enable Smaller Language Models to Reason Better and Faster (2025.emnlp-main)

Challenge:	Existing automatic dialog evaluation metrics are mostly reference-based . Existing models that measure self-reported user ratings are biased and variance among different users.
Approach:	They propose an automatic evaluation model that automatically cleans self-reported user ratings as it trains on them.
Outcome:	The proposed model achieves 89.2% accuracy in the dialog comparison task.

Copied to clipboard

Xiaoshu Chen, Sihang Zhou, Ke Liang, Xiaoyu Sun, Xinwang Liu

Born a BabyNet with Hierarchical Parental Supervision for End-to-End Text Image Machine Translation (2024.lrec-main)

Challenge:	Existing methods train small language models to learn long rationales in one iteration.
Approach:	They propose a method that uses a heuristic search to divide rationale into internal chunks . they propose CWT, which uses CWt to focus SLM on learning from only one chunk per iteration.
Outcome:	The proposed method can guide a large language model (LLM) in reasoning tasks.

Copied to clipboard

Cong Ma, Yaping Zhang, Zhiyang Zhang, Yupu Liang, Yang Zhao, Yu Zhou, Chengqing Zong

ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models (2025.acl-long)

Challenge:	Existing research on text image machine translation (TIMT) is divided into two types: Cascade methods combine text image recognition and MT models to recognize source language text images.
Approach:	They propose a method which is optimized with hierarchical parental supervision to improve translation performance.
Outcome:	The proposed method significantly outperforms existing methods on synthetic and real-world tests on both synthetic and realistic images.

Copied to clipboard

Xuxu Liu, Siyuan Liang, Mengya Han, Yong Luo, Aishan Liu, Xiantao Cai, Zheng He, Dacheng Tao

Commonality and Individuality! Integrating Humor Commonality with Speaker Individuality for Humor Recognition (2025.naacl-long)

Challenge:	Existing backdoor models are limited in coverage of attack, system integrity and backdoor alignment . ELBA-Bench provides over 1300 experiments encompassing 12 attack methods, 18 datasets, and 12 LLMs.
Approach:	They propose a framework that allows attackers to inject backdoor through parameter efficient fine-tuning or without fine-uning techniques.
Outcome:	ELBA-Bench provides over 1300 experiments encompassing 12 attack methods, 18 datasets, and 12 LLMs.

Copied to clipboard

Haohao Zhu, Xiaokun Zhang, Zeyuan Zeng, Junyu Lu, Zewen Bai, Liang Yang, Hongfei Lin

Commonsense Reasoning

Challenge:	Current methods for humor recognition focus on one aspect of humor commonalities, ignoring the multifaceted nature of humor.
Approach:	They propose a commonality and individuality incorporated network for humor recognition that integrates multifaceted humor commonalities with speaker individuality.
Outcome:	The proposed model integrates multifaceted humor commonalities with speaker individuality to deepen the understanding of humor expressions.

Stealthy Attack on Large Language Model based Recommendation (2024.acl-long)

Copied to clipboard

Jinghao Zhang, Yuting Liu, Qiang Liu, Shu Wu, Guibing Guo, Liang Wang

Knowing-how & Knowing-that: A New Task for Machine Comprehension of User Manuals (2023.findings-acl)

Challenge:	Recent advances in recommender systems have been overlooked due to their emphasis on textual content.
Approach:	They propose to introduce large language models into recommendation models to exploit the semantic understanding and strong transferability of LLMs.
Outcome:	The proposed approach significantly boosts an item’s exposure by altering its textual content during the testing phase, without requiring direct interference with the model’s training process.

Copied to clipboard

Hongru Liang, Jia Liu, Weihong Du, Dingnan Jin, Wenqiang Lei, Zujie Wen, Jiancheng Lv

Improving MLLM’s Document Image Machine Translation via Synchronously Self-reviewing Its OCR Proficiency (2025.findings-acl)

Challenge:	Existing methods for machine reading comprehension of user manuals have trouble answering complex questions.
Approach:	They propose a knowing-how & knowing-that task that requires the model to answer factoid-style, procedure-style and inconsistent questions about user manuals.
Outcome:	The proposed model can answer factoid-style, procedure-style and inconsistent questions about user manuals.

Copied to clipboard

Yupu Liang, Yaping Zhang, Zhiyang Zhang, Zhiyuan Chen, Yang Zhao, Lu Xiang, Chengqing Zong, Yu Zhou

SynthAgent: Adapting Web Agents with Synthetic Supervision (2026.acl-long)

Challenge:	Multimodal Large Language Models (MLLMs) have shown strong performance in document image tasks, especially Optical Character Recognition (OCR). However, they struggle with Document Image Machine Translation (DIMT), which requires handling both cross-modal and cross-lingual challenges.
Approach:	They propose a novel fine-tuning paradigm that allows the model to generate OCR text before producing translation text, which allows it to leverage its strong monolingual OCR ability while learning to translate text across languages.
Outcome:	The proposed model can leverage its strong monolingual OCR ability while learning to translate text across languages.

Copied to clipboard

Zhaoyang Wang, Yiming Liang, Xuchao Zhang, Qianhui Wu, Siwei Han, Anson Bastos, Rujia Wang, Chetan Bansal, Baolin Peng, Jianfeng Gao, Saravan Rajmohan, Huaxiu Yao

Towards Effective Automatic Debt Collection with Persona Awareness (2023.emnlp-industry)

Challenge:	Existing studies have focused on synthetic supervision but have encountered data quality issues.
Approach:	They propose a fully synthetic supervision framework that aims at improving data quality via dual refinement of both tasks and trajectories.
Outcome:	The proposed framework outperforms existing methods on standardized benchmarks and shows promising results on a standardized test.

Copied to clipboard

Tong Zhang, Junhong Liu, Chen Huang, Jia Liu, Hongru Liang, Zujie Wen, Wenqiang Lei

M3HG: Multimodal, Multi-scale, and Multi-type Node Heterogeneous Graph for Emotion Cause Triplet Extraction in Conversations (2025.findings-acl)

Challenge:	Existing debt collection agents fail to tailor strategies to debtor personas, leading to ineffective collection.
Approach:	They present a commercial practice on debt collection agents that organizes debtor personas into a taxonomy and constructs a persona-aware conversation dataset.
Outcome:	The proposed agent increases recovery rate by 3.31% and collects additional 100K RMB after two months of testing.

Copied to clipboard

Qiao Liang, Ying Shen, Tiantian Chen, Lin Zhang

Multi-View Source Ablation for Faithful Summarization (2023.findings-eacl)

Challenge:	Existing methods for ECAC focus on textual contexts, overlooking other modalities.
Approach:	They propose a multimodal, multi-scenario MECTEC dataset that captures emotional and causal contexts and effectively fuses contextual information at different levels.
Outcome:	The proposed model captures emotional and causal contexts and effectively fuses contextual information at both inter- and intra-utterance levels.

Copied to clipboard

Shuyang Cao, Liang Ma, Di Lu, Robert L Logan IV, Joel Tetreault, Alejandro Jaimes

Tool learning via Inference-time Scaling and Cycle Verifier (2025.findings-acl)

Challenge:	MuFaSSa is a metric for evaluating faithfulness of abstractive summaries . it uses different strategies to remove information from source document to form multiple ablated views .
Approach:	They propose a metric for evaluating faithfulness of abstractive summaries using multiple ablated views.
Outcome:	The proposed metric outperforms existing models on summarization tasks and human-annotated faithfulness labels.

Copied to clipboard

Xiaobo Liang, Wenjin Xie, Juntao Li, Wanfu Wang, Yibin Chen, Kehai Chen, Min Zhang

Challenge:	In inference-time scaling, Chain-of-Thought (CoT) data is scarce or even unavailable.
Approach:	They propose a method which establishes an inference cycle to synthesize user queries and CoT data.
Outcome:	The proposed method achieves a 75.4% pass rate and a 79.6% win rate using small models in StableToolBench.

LTRS: Improving Word Sense Disambiguation via Learning to Rank Senses (2025.coling-main)

Copied to clipboard

Hansi Wang, Yue Wang, Qiliang Liang, Yang Liu

How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmark (2025.emnlp-main)

Challenge:	Conventional training strategies only consider predefined senses for target words and learn each of them from relatively limited instances, neglecting the influence of similar ones.
Approach:	They propose a method to rank senses to improve the task of word Sense Disambiguation (WSD) by ranking an expanded list of sense definitions.
Outcome:	The proposed method achieves a SOTA F1 score of 79.6% in Chinese WSD and shows faster convergence than previous methods.

Copied to clipboard

Minglai Yang, Ethan Huang, Liang Zhang, Mihai Surdeanu, William Yang Wang, Liangming Pan

JoTR: A Joint Transformer and Reinforcement Learning Framework for Dialogue Policy Learning (2024.lrec-main)

Challenge:	Prior work has not explored the mechanisms underlying this sensitivity.
Approach:	They propose a synthetic benchmark to evaluate Large Language Models’ reasoning robustness against systematically controlled irrelevant context (IC).
Outcome:	The proposed model improves in-distribution and out-of-disttribution scenarios while training with strong distractors.

Copied to clipboard

Wai-Chung Kwan, Huimin Wang, Hongru Wang, Zezhong Wang, Bin Liang, Xian Wu, Yefeng Zheng, Kam-Fai Wong

Adaptive Information Seeking for Open-Domain Question Answering (2021.emnlp-main)

Challenge:	Dialogue policy learning (DPL) aims to determine an abstract representation (also known as action) to guide what the response should be.
Approach:	They propose a joint Transformer-based model that generates a token-grained policy that allows more dynamic dialogue action generation without the need for predefined action candidates.
Outcome:	The proposed model outperforms existing models showing improvements of 9% and 13% in success rate and 34% and 37% in diversity of dialogue actions across two benchmark dialogue modeling tasks.

Copied to clipboard

Yunchang Zhu, Liang Pang, Yanyan Lan, Huawei Shen, Xueqi Cheng

QAEncoder: Towards Aligned Representation Learning in Question Answering Systems (2025.acl-long)

Challenge:	Existing iterative approaches to open-domain question answering use predefined strategies . e.g., BM25, DPR, and hyperlink are defined as actions .
Approach:	They propose a novel adaptive information-seeking strategy for open-domain question answering . they propose to use a partially observed Markov decision process to select a proper retrieval action .
Outcome:	Experiments on SQuAD Open and HotpotQA fullwiki show that AISO outperforms baseline methods with predefined strategies in retrieval and answer evaluations.

Copied to clipboard

Zhengren Wang, Qinhan Yu, Shida Wei, Zhiyu Li, Feiyu Xiong, Xiaoxing Wang, Simin Niu, Hao Liang, Wentao Zhang

An Iterative Multi-Knowledge Transfer Network for Aspect-Based Sentiment Analysis (2021.findings-emnlp)

Challenge:	Modern QA systems entail retrieval-augmented generation (RAG) for accurate and trustworthy responses, but the inherent gap between user queries and relevant documents hinders precise matching.
Approach:	They propose a retrieval-augmented generation (RAG)-based approach to bridge this gap by attaching document fingerprints to the embedding to estimate the expectation of potential queries.
Outcome:	Experiments across diverse datasets, languages, and embedding models confirm the proposed solution is simple-yet-effective with zero additional index storage, retrieval latency, training costs, or catastrophic forgetting and hallucination issues.

Copied to clipboard

Yunlong Liang, Fandong Meng, Jinchao Zhang, Yufeng Chen, Jinan Xu, Jie Zhou

AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models (2024.findings-naacl)

Challenge:	Existing approaches to Aspect-based sentiment analysis do not exploit the interactive relations among subtasks and do not utilize document-level labeled domain/sentiment knowledge, which restricts their performance.
Approach:	They propose an iterative multi-knowledge transfer network for end-to-end ABSA that leverages the inter-task interaction between subtasks.
Outcome:	The proposed approach improves on three benchmark datasets.

Copied to clipboard

Wanjun Zhong, Ruixiang Cui, Yiduo Guo, Yaobo Liang, Shuai Lu, Yanlin Wang, Amin Saied, Weizhu Chen, Nan Duan

A Survey of Inductive Reasoning for Large Language Models (2026.acl-long)

Challenge:	Traditional benchmarks for evaluating foundation models often fail to accurately represent their general abilities for human-centric tasks.
Approach:	They propose a bilingual benchmark to assess foundation models in the context of human-centric standardized exams such as college entrance exams, law school admission tests, and math competitions.
Outcome:	The proposed benchmark exceeds the average human performance on SAT, LSAT, and math competitions with 95% accuracy and 92.5% on the Chinese college entrance English exam.

Copied to clipboard

Kedi Chen, Dezhao Ruan, Yuhao Dan, Yaoting Wang, Siyu Yan, Xuecheng Wu, Yinqi Zhang, Qin Chen, Jie Zhou, Liang He, Biqing Qi, Linyang Li, Qipeng Guo, Xiaoming Shi, Wei Zhang

Efficient Data Labeling by Hierarchical Crowdsourcing with Large Language Models (2025.coling-main)

Challenge:	Inductive reasoning is an important task for large language models (LLMs).
Approach:	They propose a survey of inductive reasoning for large language models . they categorize methods into three main areas: post-training enhancement, test-time exploration, and data augmentation.
Outcome:	The proposed method improves inductive reasoning in large language models.

Copied to clipboard

Haodi Zhang, Junyu Yang, Jinyin Nie, Peirou Liang, Kaishun Wu, Defu Lian, Rui Mao, Yuanfeng Song

In-Context Example Retrieval from Multi-Perspectives for Few-Shot Aspect-Based Sentiment Analysis (2024.lrec-main)

Challenge:	Large language models (LLMs) have been gaining attention for their impressive performance in in-context dialogues.
Approach:	They propose a hierarchical framework that leverages multiple LLMs for efficient data labeling under budget constraints.
Outcome:	The proposed framework outperforms human labelers and GPT-4 in terms of accuracy and efficiency.

Copied to clipboard

Qianlong Wang, Hongling Xu, Keyang Ding, Bin Liang, Ruifeng Xu

DABERT: Dual Attention Enhanced BERT for Semantic Matching (2022.coling-1)

Challenge:	Existing approaches to solve few-shot aspect-based sentiment analysis (ABSA) are suboptimal for this task because of in-context examples .
Approach:	They propose to retrieve in-context examples for few-shot aspect-based sentiment analysis . they construct positive and negative pairs from three perspectives and train the retriever .
Outcome:	The proposed retrieval framework outperforms baselines on four ABSA datasets.

Copied to clipboard

Sirui Wang, Di Liang, Jian Song, Yuntao Li, Wei Wu

In-context Learning for Few-shot Multimodal Named Entity Recognition (2023.findings-emnlp)

Challenge:	Existing models for semantic sentence matching lack the ability to capture subtle differences.
Approach:	They propose to use a Transformer-based pre-trained language model to capture fine-grained differences in sentence pairs by introducing a dual attention module and a fusion module to learn the aggregation of difference and affinity features.
Outcome:	The proposed method is able to capture fine-grained differences in sentence pairs.

Copied to clipboard

Chenran Cai, Qianlong Wang, Bin Liang, Bing Qin, Min Yang, Kam-Fai Wong, Ruifeng Xu

An Information Minimization Based Contrastive Learning Model for Unsupervised Sentence Embeddings Learning (2022.coling-1)

Challenge:	Existing methods for named entity recognition are time-consuming and laborintensive.
Approach:	They propose a few-shot multimodal named entity recognition task that uses few examples to locate and identify named entities for a text-image pair.
Outcome:	The proposed framework outperforms baselines under several few-shot settings.

Copied to clipboard

Shaobin Chen, Jie Zhou, Yuling Sun, Liang He

Selective Question Answering under Domain Shift (2020.acl-main)

Challenge:	Recent contrastive learning methods keep positive pairs similar and push negative pairs apart, which leads to redundant information in sentence embeddings.
Approach:	They propose a contrastive learning approach which maximizes mutual information and minimizes the information entropy between positive and negative instances.
Outcome:	The proposed model outperforms all previous competitors on supervised and unsupervised tasks.

Copied to clipboard

Amita Kamath, Robin Jia, Percy Liang

Unlocking Recursive Thinking of LLMs: Alignment via Refinement (2025.findings-acl)

Challenge:	Deployed question answering (QA) models need to know when to abstain from answering questions that diverge from their training data.
Approach:	They propose a selective question answering under domain shift in which a QA model is tested on a mixture of in-domain and out-of-domain data and must answer (i.e., not abstain on) as many questions as possible.
Outcome:	The proposed method answers 56% of questions while maintaining 80% accuracy.

Copied to clipboard

Haoke Zhang, Xiaobo Liang, Cunxiang Wang, Juntao Li, Min Zhang

Challenge:	Existing methods for recursive reasoning are limited due to lack of expert-curated data.
Approach:	They propose a method that unlocks the potential of Large Language Models for recursive reasoning through long-form Chain of Thought.
Outcome:	The proposed method outperforms preference optimization methods on the openAI o1-series models by 20% on 3k synthetic samples.

MMRA: A Benchmark for Evaluating Multi-Granularity and Multi-Image Relational Association Capabilities in Large Visual Language Models (2026.findings-eacl)

Copied to clipboard

Siwei Wu, King Zhu, Yu Bai, Yiming Liang, Yizhi Li, Haoning Wu, Jiaheng Liu, Ruibo Liu, Xingwei Qu, Xuxin Cheng, Ge Zhang, Wenhao Huang, Chenghua Lin

X-ray Made Simple: Lay Radiology Report Generation and Robust Evaluation (2026.findings-acl)

Challenge:	Current multimodal benchmarks focus on facts within individual images, but neglect associative relations among multiple images.
Approach:	They propose a multi-image relational association task and a MMRA benchmark to evaluate LVLMs.
Outcome:	The proposed benchmarks show that entity-level multi-image perception tasks pose greater challenges than image-level tasks.

Copied to clipboard

Kun Zhao, Chenghao Xiao, Sixing Yan, Haoteng Tang, William K. Cheung, Noura Al Moubayed, Liang Zhan, Chenghua Lin

Game on Tree: Visual Hallucination Mitigation via Coarse-to-Fine View Tree and Game Theory (2024.emnlp-main)

Challenge:	Technical language and templated nature of professional reports hinder patient comprehension and allow models to artificially boost lexical metrics such as BLEU by reproducing common report patterns.
Approach:	They propose a layman's RRG framework that leverages layperson-friendly language to enhance patient accessibility and promote robust evaluation and report generation by encouraging models to focus on semantic accuracy over rigid templates.
Outcome:	The proposed framework improves model performance with more layman-style data, compared to templated professional language and inflated lexical scores.

Copied to clipboard

Xianwei Zhuang, Zhihong Zhu, Zhanpeng Chen, Yuxin Xie, Liming Liang, Yuexian Zou

Debatrix: Multi-dimensional Debate Judge with Iterative Chronological Analysis Based on LLM (2024.findings-acl)

Challenge:	Large vision-language models produce unfaithful visual hallucinations, also known as visual halluinations, which hinders their application in multimodal understanding and decision-making.
Approach:	They propose a plug-and-play train-free decoding algorithm for mitigating visual hallucinations . they leverage visual information to construct a coarse-to-fine visual view tree .
Outcome:	The proposed algorithm reduces visual hallucinations (VH) by leveraging visual information to construct a coarse-to-fine visual view tree (CFTree)

Copied to clipboard

Jingcong Liang, Rong Ye, Meng Han, Ruofei Lai, Xinyu Zhang, Xuanjing Huang, Zhongyu Wei

Challenge:	Recent studies have focused on short dialogues, but mainly on short debates.
Approach:	They propose to use Large Language Models to construct an automated debate judge to evaluate multi-turn debates.
Outcome:	The proposed system improves on the PanelBench benchmark, which compares its performance to actual debate outcomes.

REACT: Representation Extraction And Controllable Tuning to Overcome Overfitting in LLM Knowledge Editing (2025.emnlp-main)

Copied to clipboard

Haitian Zhong, Yuhuan Liu, Ziyang Xu, Guofan Liu, Qiang Liu, Shu Wu, Zhe Zhao, Liang Wang, Tieniu Tan

Source Critical Reinforcement Learning for Transferring Spoken Language Understanding to a New Language (C18-1)

Challenge:	Large language model editing methods suffer from overfitting, where factual updates can propagate beyond their intended scope, overemphasizing the edited target even when it’s contextually inappropriate.
Approach:	They propose a framework for precise and controllable knowledge editing that utilizes two-phase representations and a linear transformation to compute a directional "belief shift" vector.
Outcome:	The proposed framework significantly reduces overfitting across nearly all evaluation metrics and on COUNTERFACT and MQuAKE.

Copied to clipboard

He Bai, Yu Zhou, Jiajun Zhang, Liang Zhao, Mei-Yuh Hwang, Chengqing Zong

A Survey on Cross-Lingual Summarization (2022.tacl-1)

Challenge:	a study aims to develop a language transferring system to avoid the trouble of acquiring and labeling a new big SLU corpus . general-purpose translators cannot handle the lot of semantic labels, not to mention cultural differences . a RL-based language transfer method can be used to adapt the adapted translator to a target language .
Approach:	They propose to use reinforcement learning to adapt a spoken language understanding model to a target language.
Outcome:	The proposed language transferring method improves domain classification accuracy by 22% compared with naive translation . the proposed language transfer method can be used on Chinese to English translators with more proper slot tags .

Copied to clipboard

Jiaan Wang, Fandong Meng, Duo Zheng, Yunlong Liang, Zhixu Li, Jianfeng Qu, Jie Zhou

Multiview Identifiers Enhanced Generative Retrieval (2023.acl-long)

Challenge:	Cross-lingual summarization is a task of generating a summary in one language for a given document in a different language.
Approach:	They present a systematic review of the literature on cross-lingual summarization . they summarize previous efforts and compare them with each other .
Outcome:	The proposed approach is compared with previous approaches and summarizes them to provide a deeper analysis.

Copied to clipboard

Yongqi Li, Nan Yang, Liang Wang, Furu Wei, Wenjie Li

Graph-to-Text Generation with Dynamic Structure Pruning (2022.coling-1)

Challenge:	Current approaches use a numeric ID or text piece as the identifier, but these identifieres cannot cover a passage’s content well.
Approach:	They propose a new type of identifier that is generated based on the content of a passage and could integrate contextualized information that text pieces lack.
Outcome:	The proposed approach performs the best in generative retrieval on three public datasets.

Copied to clipboard

Liang Li, Ruiying Geng, Bowen Li, Can Ma, Yinliang Yue, Binhua Li, Yongbin Li

An Empirical Study on Multiple Knowledge from ChatGPT for Emotion Recognition in Conversations (2023.findings-emnlp)

Challenge:	Recent studies show that explicitly modeling the input graph structure can significantly improve the performance.
Approach:	They propose a structure-aware cross-attention mechanism to re-encode the graph representation conditioning on the newly generated context at each decoding step.
Outcome:	The proposed model improves performance on two graph-to-text datasets with only minor increase on computational cost.

Copied to clipboard

Geng Tu, Bin Liang, Bing Qin, Kam-Fai Wong, Ruifeng Xu

MultiLingPoT: Boosting Mathematical Reasoning in LLMs through Multilingual Program Integration (2025.findings-emnlp)

Challenge:	Existing efforts in ERC focus on context- and speaker-sensitive dependencies, but lack of annotated data and high cost of obtaining such knowledge is a blank slate.
Approach:	They propose a Multiple Knowledge Fusion Model to integrate multiple knowledge generated by Large Language Models (LLMs) they analyze the contribution and complementarity of this knowledge into the model.
Outcome:	The proposed model integrates multiple knowledge generated by LLMs and analyzes its contribution and complementarity on three public datasets.

Copied to clipboard

Nianqi Li, Zujie Liang, Siyu Yuan, Jiaqing Liang, Feng Wei, Yanghua Xiao

CoreEval: Automatically Building Contamination-Resilient Datasets with Real-World Knowledge toward Reliable LLM Evaluation (2025.acl-long)

Challenge:	Program-of-Thought is an important way for LLMs to solve mathematical problems.
Approach:	They propose a multilingual programme reasoning method that uses program instead of natural language in reasoning and proposes to integrate multilingual integration into the training and inference.
Outcome:	The proposed method improves individual language’s reasoning accuracy by 2.5% and improves performance by 8%.

Copied to clipboard

Jingqian Zhao, Bingbing Wang, Geng Tu, Yice Zhang, Qianlong Wang, Bin Liang, Jing Li, Ruifeng Xu

Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning (2026.findings-acl)

Challenge:	Publicly available datasets can be used to evaluate performance of large language models . however, contamination of test data can artificially inflate model performance .
Approach:	They propose a Contamination-resilient Evaluation strategy that updates data with real-world knowledge.
Outcome:	The proposed evaluation strategy can be used to update datasets with real-world knowledge.

Copied to clipboard

Yongcan Yu, Lingxiao He, Jian Liang, Kuangpu Guo, Meng Wang, Qianlong Xie, Xingxing Wang, Ran He

Multimodal Language Analysis with Recurrent Multistage Fusion (D18-1)

Challenge:	a framework to mitigate spurious optimization signals is proposed for test-time reinforcement learning (TTRL) Reinforcement learning with verifiable rewards (RLVR) is an effective paradigm for improving large language models on structured challenging reasoning tasks.
Approach:	They propose a framework to mitigate spurious optimization signals from label noise . they propose to use a frequency-based sampling strategy to exclude ambiguous samples .
Outcome:	The proposed framework outperforms existing TTRL baselines on three large language models across multiple mathematical reasoning benchmarks.

Copied to clipboard

Paul Pu Liang, Ziyin Liu, AmirAli Bagher Zadeh, Louis-Philippe Morency

Croppable Knowledge Graph Embedding (2025.acl-long)

Challenge:	Comprehending multimodal language requires modeling interactions between modalities and between them.
Approach:	They propose a multistage fusion network which decomposes the fusion problem into multiple stages, each focused on a subset of multimodal signals for specialized, effective fusion.
Outcome:	The proposed model performs state-of-the-art across three datasets relating to multimodal sentiment analysis, emotion recognition, and speaker traits recognition.

Copied to clipboard

Yushan Zhu, Wen Zhang, Zhiqiang Liu, Mingyang Chen, Lei Liang, Huajun Chen

Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment (2025.emnlp-main)

Challenge:	Knowledge Graph Embedding (KGE) is a common approach for Knowledge Grasse (KGs) in AI tasks.
Approach:	They propose a new KGE training framework MED that allows one training to obtain a croppable KGE model for multiple scenarios with different dimensional needs.
Outcome:	The proposed framework improves low-dimensional sub-models and makes high-dimensional models retain the low-dimension sub-modells’ capacity.

Copied to clipboard

Jingcheng Deng, Zhongtao Jiang, Liang Pang, Zihao Wei, Liwei Chen, Kun Xu, Yang Song, Huawei Shen, Xueqi Cheng

When KV Cache Reuse Fails in Multi-Agent Systems: Cross-Candidate Interaction is Crucial for LLM Judges (2026.acl-long)

Challenge:	Experimental results demonstrate that our method significantly outperforms traditional contrastive learning approaches when using the same amount of data.
Approach:	They propose a new contrastive learning method built on embedding conditional probability distributions that integrates two tasks: information compression and conditional distribution alignment.
Outcome:	The proposed method outperforms traditional contrastive learning approaches and achieves comparable performance to state-of-the-art models when using the same amount of data.

Copied to clipboard

Sichu Liang, Zhenglin Wang, null Chujiajia, Pengfei Xia, Hui Zang, Deyu Zhou

Challenge:	Multi-agent LLMs generate multiple candidate responses that are aggregated by an LLM judge.
Approach:	They propose to advocate KV cache reuse across partially shared contexts and report substantial speedups for generation agents.
Outcome:	The proposed reuse strategies weaken cross-candidate attention, especially for later candidate blocks, and highlight judge-centric inference as a distinct regime that requires dedicated, risk-aware system design.

Fast-R2D2: A Pretrained Recursive Neural Network based on Pruned CKY for Grammar Induction and Text Representation (2022.emnlp-main)

Copied to clipboard

Xiang Hu, Haitao Mi, Liang Li, Gerard de Melo

InfoGain-RAG: Boosting Retrieval-Augmented Generation through Document Information Gain-based Reranking and Filtering (2025.emnlp-main)

Challenge:	Chart-based models have shown great potential in unsupervised grammar induction, running recursively and hierarchically, but requiring O(n3) time-complexity.
Approach:	They propose a model-guided pruning method that scales to large language model pretraining by introducing a heuristic pruning method.
Outcome:	The proposed method significantly improves grammar induction quality and achieves competitive results in downstream tasks.

Copied to clipboard

Zihan Wang, Zihan Liang, Zhou Shao, Yufei Ma, Huangyu Dai, Ben Chen, Lingtao Mao, Chenyi Lei, Yuqing Ding, Han Li

InstructEd: Soft-Instruction Tuning for Model Editing with Hops (2024.findings-acl)

Challenge:	Retrieval-Augmented Generation (RAG) frameworks struggle with identifying whether retrieved documents meaningfully contribute to answer generation.
Approach:	They propose a document-related metric to quantify the contribution of retrieved documents to correct answer generation.
Outcome:	The proposed framework outperforms existing approaches on both single and multiple retrieval paradigms.

Copied to clipboard

XiaoQi Han, Ru Li, Xiaoli Li, Jiye Liang, Zifang Zhang, Jeff Pan

Modeling Intra- and Inter-Modal Relations: Hierarchical Graph Contrastive Learning for Multimodal Sentiment Analysis (2022.coling-1)

Challenge:	Existing methods for model editing are limited due to excessive memorization and knowledge conflict issues.
Approach:	They propose to insert soft instructions into the attention module to facilitate interactions between instructions and questions and to understand and utilize new facts.
Outcome:	The proposed method achieves 10% improvement in one-hop (multi-hop) model editing on three datasets with LLaMAs and GPT2 .

Copied to clipboard

Zijie Lin, Bin Liang, Yunfei Long, Yixue Dang, Min Yang, Min Zhang, Ruifeng Xu

Take Its Essence, Discard Its Dross! Debiasing for Toxic Language Detection via Counterfactual Causal Effect (2024.lrec-main)

Challenge:	Existing studies in Multimodal Sentiment Analysis lack a mechanism to understand complex relations between different modalities.
Approach:	They propose a hierarchical graph contrastive learning framework for multimodal sentiment analysis that explores the relationships between modality representations.
Outcome:	The proposed framework outperforms the state-of-the-art in multimodal sentiment analysis on two benchmark datasets.

Copied to clipboard

Junyu Lu, Bo Xu, Xiaokun Zhang, Kaiyuan Liu, Dongyu Zhang, Liang Yang, Hongfei Lin

ATRI: Mitigating Multilingual Audio Text Retrieval Inconsistencies by Reducing Data Distribution Errors (2025.acl-long)

Challenge:	Existing methods to mitigate lexical bias in toxic language detection (TLD) do not exploit the “useful” and “misleading” impact of the bias.
Approach:	They propose a counterfactual Causal Debiasing Framework to mitigate lexical bias in toxic language detection (TLD) it preserves the “useful impact” of lexical bias and eliminates the "misleading impact" they propose to use the same framework to analyze the causal effect of a sentence and bias tokens .
Outcome:	The proposed framework preserves the “useful impact” of lexical bias and eliminates the ‘misleading impact’ Empirical evaluations show that the proposed model outperforms current debiased models for out-of-distribution data.

Copied to clipboard

Yuguo Yin, Yuxin Xie, Wenyuan Yang, Dongchao Yang, Jinghan Ru, Xianwei Zhuang, Liming Liang, Yuexian Zou

Learning from Imperfect Data: Towards Efficient Knowledge Distillation of Autoregressive Language Models for Text-to-SQL (2024.findings-emnlp)

Challenge:	Existing multilingual audio-text retrieval schemes suffer from inconsistencies for instance similarity matching across languages.
Approach:	They propose a multilingual audio-text retrieval scheme that mitigates the impact of data distribution error on recall and consistency.
Outcome:	The proposed scheme achieves state-of-the-art performance on recall and consistency metrics for eight mainstream languages, including English.

Copied to clipboard

Qihuang Zhong, Kunfeng Chen, Liang Ding, Juhua Liu, Bo Du, Dacheng Tao

Curriculum Learning based Hierarchical Scoring and Analysis Framework for Question Answering Task Evaluation (2026.findings-acl)

Challenge:	Existing text-to-SQL LLMs are computationally expensive and difficult to deploy in real-world applications.
Approach:	They propose to distill a larger teacher model into a smaller student model by using imperfect data to improve the KD.
Outcome:	The proposed method achieves the best tradeoff between performance and efficiency on 5 text-to-SQL benchmarks.

Copied to clipboard

Qiong Wu, Tan Yue, Jianxin Liang, Zhen Li, Kai He, Shuai Zhao, Dongyan Zhao

Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environments (2025.findings-emnlp)

Challenge:	Existing evaluation methods rely on rule-based matching with shallow semantic understanding or adopt LLM-as-a-Judge approaches that incur high cost and latency while offering limited error interpretability.
Approach:	They propose a curriculum learning based hierarchical framework for QA task evaluation that supports quick scoring and fine-grained error analysis.
Outcome:	The proposed framework outperforms baseline methods on quick scoring and error analysis tasks while being 25 faster.

Copied to clipboard

Qingyu Lu, Liang Ding, Siyi Cao, Xuebo Liu, Kanjian Zhang, Jinxia Zhang, Dacheng Tao

Jiuge: A Human-Machine Collaborative Chinese Classical Poetry Generation System (P19-3)

Challenge:	Experiments with 4 different LLMs across 5 embodied environments show significant efficiency improvements, with only minor drops in agent performance.
Approach:	They propose an intrinsic method that injects exit instructions during generation and an extransic system that verifies task completion to determine when to halt an agent’s trial.
Outcome:	The proposed method injects exit instructions during generation and an exit method verifies task completion to determine when to halt an agent’s trial.

Copied to clipboard

Guo Zhipeng, Xiaoyuan Yi, Maosong Sun, Wenhao Li, Cheng Yang, Jiannan Liang, Huimin Chen, Yuhui Zhang, Ruoyu Li

Evaluating Verifiability in Generative Search Engines (2023.findings-emnlp)

Challenge:	Existing systems for automatic poetry generation are model-oriented, resulting in poor user participation.
Approach:	They propose a human-machine collaborative Chinese classical poetry generation system called Jiuge . Jiuge allows users to revise unsatisfied parts of a generated poem draft repeatedly .
Outcome:	The proposed system allows users to revise unsatisfied parts of a generated poem draft repeatedly.

Copied to clipboard

Nelson Liu, Tianyi Zhang, Percy Liang

What Makes an Ideal Quote? Recommending “Unexpected yet Rational” Quotations via Novelty (2026.acl-long)

Challenge:	Existing generative search engines are rapidly gaining users, according to a new study . existing systems are poorly cited and lack reliability, a study finds .
Approach:	They conduct human evaluations of four popular generative search engines . they find that existing generative engines are fluent and appear informative .
Outcome:	The results show that existing generative search engines are not reliable and often contain unsupported statements and inaccurate citations.

Copied to clipboard

Powei Chang, Jin Xiao, Guanglei Yue, Qianyu He, Yanghua Xiao, Deqing Yang, Jiaqing Liang

Challenge:	Prior systems focus on topical relevance and overlook what makes quotes memorable.
Approach:	They propose a system that maps quotations and contexts into deep-meaning labels for label-enhanced retrieval.
Outcome:	The proposed system can recommend quotations that are contextually novel while semantically coherent.

SymbolicThought: Integrating Language Models and Symbolic Reasoning for Consistent and Interpretable Human Relationship Understanding (2026.acl-demo)

Copied to clipboard

Runcong Zhao, Qinglin Zhu, Hainiu Xu, Bin Liang, Lin Gui, Yulan He

QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering (2021.naacl-main)

Challenge:	Existing methods for constructing character relationships from plain text are time-consuming and low in coverage.
Approach:	They propose a human-in-the-loop framework that combines LLM-based extraction with symbolic reasoning.
Outcome:	The proposed framework improves annotation accuracy and consistency while significantly reducing time cost.

Copied to clipboard

Michihiro Yasunaga, Hongyu Ren, Antoine Bosselut, Percy Liang, Jure Leskovec

Chain of Methodologies: Scaling Test Time Computation without Training (2025.findings-acl)

Challenge:	Existing question answering systems lack the ability to access relevant knowledge and reason over it.
Approach:	They propose a model that uses KGs to identify relevant knowledge in QA contexts and perform joint reasoning over them.
Outcome:	The proposed model improves on the CommonsenseQA and OpenBookQA datasets and performs interpretable and structured reasoning.

Copied to clipboard

Cong Liu, Jie Wu, Weigang Wu, Xu Chen, Liang Lin, Wei-Shi Zheng

An Alignment-Agnostic Model for Chinese Text Error Correction (2021.findings-emnlp)

Challenge:	Existing prompts for complex reasoning tasks are limited to specific tasks with few-shot examples due to constraints like context length and information extraction accuracy.
Approach:	They propose a method to build structured reasoning processes by injecting human insights into LLMs' training data.
Outcome:	The proposed framework outperforms baselines in the analysis of large language models.

Copied to clipboard

Liying Zheng, Yue Deng, Weishun Song, Liang Xu, Jing Xiao

ProMedTS: A Self-Supervised, Prompt-Guided Multimodal Approach for Integrating Medical Text and Time Series (2025.findings-acl)

Challenge:	Existing models for Chinese text error correction can correct mistaken, missing and redundant characters, but they cannot handle missing or redundant characters.
Approach:	They propose an alignment-agnostic framework to correct Chinese text errors . framework detects missing and redundant characters and can be used as a cold start model .
Outcome:	The proposed framework can handle both text aligned and non-aligned situations and can serve as a cold start model when no annotation data are provided.

Copied to clipboard

Shuai Niu, Jing Ma, Hongzhan Lin, Liang Bai, Zhihua Wang, V. W., Richard Yi Da Xu, Guo Li, Xian Yang

mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data (2025.findings-acl)

Challenge:	Large language models excel at processing unstructured data, but integrating time series data with text remains a challenge.
Approach:	They propose a self-supervised multimodal framework that uses prompt-guided learning to unify heterogeneous data types.
Outcome:	The proposed framework outperforms state-of-the-art approaches on disease diagnosis tasks using real-world datasets.

Copied to clipboard

Haonan Chen, Liang Wang, Nan Yang, Yutao Zhu, Ziliang Zhao, Furu Wei, Zhicheng Dou

SAS: Dialogue State Tracking via Slot Attention and Slot Information Sharing (2020.acl-main)

Challenge:	Multimodal embedding models encode multimedia inputs into latent vector representations.
Approach:	They propose to synthesize multimodal multilingual data using a multimodal large language model . they identify three criteria for high-quality synthetic multimodal data .
Outcome:	The proposed model outperforms existing models on the MMEB Benchmark and the XTD benchmark.

Copied to clipboard

Jiaying Hu, Yan Yang, Chencai Chen, Liang He, Zhou Yu

Maria: A Visual Experience Powered Conversational Agent (2021.acl-long)

Challenge:	Existing models with excessive information are inefficient and costly .
Approach:	They propose to integrate a Dialogue State Tracker with Slot Attention and Slot Information Sharing to reduce redundant information’s interference and improve long dialogue context tracking.
Outcome:	The proposed model significantly outperforms existing models on the MultiWOZ dataset.

Copied to clipboard

Zujie Liang, Huang Hu, Can Xu, Chongyang Tao, Xiubo Geng, Yining Chen, Fan Liang, Daxin Jiang

Adaptive Ordered Information Extraction with Deep Reinforcement Learning (2023.findings-acl)

Challenge:	Existing studies focus on grounding conversational agents on text-only corpora, but they lack the perception ability to our physical world.
Approach:	They propose to ground conversational agents on images retrieved from large-scale image indexes . they propose to use visual knowledge to generate informative responses based on the extracted knowledge .
Outcome:	The proposed agent outperforms state-of-the-art methods on automatic metrics and human evaluation.

Copied to clipboard

Wenhao Huang, Jiaqing Liang, Zhixu Li, Yanghua Xiao, Chuanjun Ji

Conditional probing: measuring usable information beyond a baseline (2021.emnlp-main)

Challenge:	Existing methods for information extraction follow a fixed extraction order for complex tasks with multiple elements to be extracted in one instance.
Approach:	They propose an adaptive ordered IE paradigm to find optimal element extraction order for different instances and a reinforcement learning framework to generate optimal order dynamically.
Outcome:	The proposed method beats existing methods and improves on several public datasets.

Copied to clipboard

John Hewitt, Kawin Ethayarajh, Percy Liang, Christopher Manning

Designing and Interpreting Probes with Control Tasks (D19-1)

Challenge:	Existing methods for probing representations are limited to predicting part-of-speech . current methods cannot detect when a representation is predictive of just aspects of part- of-seech not explainable by the word identity.
Approach:	They propose to condition on the information in a baseline representation to test whether it is predictive of part-of-speech.
Outcome:	The proposed method is based on a theory of usable information called V-information and conditions on the information in the baseline.

Copied to clipboard

John Hewitt, Percy Liang

Light Up the Shadows: Enhance Long-Tailed Entity Grounding with Concept-Guided Vision-Language Models (2024.findings-acl)

Challenge:	Existing studies on supervised models to predict properties from representations have shown high accuracy on a range of linguistic tasks.
Approach:	They propose control tasks which associate word types with random outputs to complement linguistic tasks by construction . they find that popular probes on ELMo representations are not selective .
Outcome:	The proposed tasks associate word types with random outputs to complement linguistic tasks.

Copied to clipboard

Yikai Zhang, Qianyu He, Xintao Wang, Siyu Yuan, Jiaqing Liang, Yanghua Xiao

AdaTag: Multi-Attribute Value Extraction from Product Profiles with Adaptive Decoding (2021.acl-long)

Challenge:	Multi-Modal Knowledge Graphs (MMKGs) are knowledge graphs that integrate and align information from diverse modalities (e.g., text and images).
Approach:	They propose a framework that integrates image-text pairs of long-tailed entities and a concept guidance module that offers explainability and enables human verification.
Outcome:	The proposed framework improves the accuracy of recognizing long-tailed image-text pairs compared to baselines and also offers flexibility and explainability.

Copied to clipboard

Jun Yan, Nasser Zalmout, Yan Liang, Christan Grant, Xiang Ren, Xin Luna Dong

Linear-time Constituency Parsing with RNNs and Dynamic Programming (P18-2)

Challenge:	Existing approaches to extract product attribute values are limited by knowledge sharing across different attributes.
Approach:	They propose to use adaptive decoding to handle extraction of product attribute values by parameterizing the decoder with pretrained attribute embeddings, through a hypernetwork and a Mixture-of-Experts module.
Outcome:	The proposed model is able to handle multiple attributes without sharing the entire network parameters across all attributes.

Copied to clipboard

Juneki Hong, Liang Huang

InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents (2024.findings-acl)

Challenge:	Existing span-based constituency parsers are too slow for longer sentences and for applications beyond sentence boundaries.
Approach:	They propose a linear-time constituency parser with RNNs and dynamic programming using graph-structured stack and beam search.
Outcome:	The proposed parser is faster for long sentences and faster for discourse parsing.

Copied to clipboard

Qiusi Zhan, Zhixiang Liang, Zifan Ying, Daniel Kang