Papers by Li Liang
Verified Critical Step Optimization for LLM Agents (2026.findings-acl)
Copied to clipboard
| Challenge: | Critical Step Optimization (CSO) focuses preference learning on verified critical steps where alternative actions demonstrably flip task outcomes from failure to success. |
| Approach: | They propose a method which focuses preference learning on verified critical steps where alternative actions demonstrably flip task outcomes from failure to success. |
| Outcome: | The proposed method outperforms the existing methods on GAIA-Text-103 and XBench-DeepSearch while requiring supervision at only 16% of trajectory steps. |
OOP: Object-Oriented Programming Evaluation Benchmark for Large Language Models (2024.findings-acl)
Copied to clipboard
| 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. |
Plan-then-Seam: Towards Efficient Table-to-Text Generation (2023.findings-eacl)
Copied to clipboard
| 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. |
AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders (2025.findings-emnlp)
Copied to clipboard
| 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 . |
CACL: Community-Aware Heterogeneous Graph Contrastive Learning for Social Media Bot Detection (2024.findings-acl)
Copied to clipboard
| 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. |
How Do Humans Write Code? Large Models Do It the Same Way Too (2024.emnlp-main)
Copied to clipboard
| 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. |
Too Long, Do Re-weighting for Efficient LLM Reasoning Compression (2026.acl-long)
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
| 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. |
A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos (2025.findings-acl)
Copied to clipboard
| 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. |
DentalGPT: Incentivizing Multimodal Reasoning in Dentistry (2026.findings-acl)
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
| 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. |
Composable Text Controls in Latent Space with ODEs (2023.emnlp-main)
Copied to clipboard
Guangyi Liu, Zeyu Feng, Yuan Gao, Zichao Yang, Xiaodan Liang, Junwei Bao, Xiaodong He, Shuguang Cui, Zhen Li, Zhiting Hu
| 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. |
Dual-Axis Generative Reward Model Toward Semantic and Turn-taking Robustness in Interactive Spoken Dialogue Models (2026.acl-long)
Copied to clipboard
Yifu Chen, Shengpeng Ji, Zhengqing Liu, Qian Chen, Wen Wang, Ziqing Wang, Yangzhuo Li, Tianle Liang, Zhou Zhao
| 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. |
PivotAttack: Rethinking the Search Trajectory in Hard-Label Text Attacks via Pivot Words (2026.findings-acl)
Copied to clipboard
| 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. |
Human-Inspired Obfuscation for Model Unlearning: Local and Global Strategies with Hyperbolic Representations (2025.findings-emnlp)
Copied to clipboard
| 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. |
Reason-KE++: Aligning the Process, Not Just the Outcome, for Faithful LLM Knowledge Editing (2026.findings-acl)
Copied to clipboard
| 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. |
Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations (2026.acl-long)
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
| 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. |
Zero-shot Sharpness-Aware Quantization for Pre-trained Language Models (2023.emnlp-main)
Copied to clipboard
| 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. |
JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance Detection (2022.acl-long)
Copied to clipboard
| 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. |
GroupToM-Bench: Benchmarking Group Theory of Mind and Nonlinear Social Emergence in MLLMs (2026.acl-long)
Copied to clipboard
Weidong Tang, Jierui Li, Yueling Hou, Zihan Mei, Can Zhang, Xinyan Wan, Zhiyuan Liang, Pengfei Zhou, Yang You, Wangbo Zhao
| 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. |
Multi-Stage Pre-training Enhanced by ChatGPT for Multi-Scenario Multi-Domain Dialogue Summarization (2023.findings-emnlp)
Copied to clipboard
| 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. |
Large Language Models are not Fair Evaluators (2024.acl-long)
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
| 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. |
RTQA : Recursive Thinking for Complex Temporal Knowledge Graph Question Answering with Large Language Models (2025.emnlp-main)
Copied to clipboard
| 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. |
Consecutive Batch Model Editing with HooK Layers (2024.emnlp-main)
Copied to clipboard
| 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. |
Revisiting Knowledge Distillation for Autoregressive Language Models (2024.acl-long)
Copied to clipboard
| 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. |
Multi-modal Stance Detection: New Datasets and Model (2024.findings-acl)
Copied to clipboard
| 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 . |
CLHA: A Simple Yet Effective Contrastive Learning Framework for Human Alignment (2024.lrec-main)
Copied to clipboard
Feiteng Fang, Liang Zhu, Xi Feng, Jinchang Hou, Qixuan Zhao, Chengming Li, Xiping Hu, Ruifeng Xu, Min Yang
| 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" |
MolRAG: Unlocking the Power of Large Language Models for Molecular Property Prediction (2025.acl-long)
Copied to clipboard
| 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. |
Reason from Fallacy: Enhancing Large Language Models’ Logical Reasoning through Logical Fallacy Understanding (2024.findings-naacl)
Copied to clipboard
| 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. |
PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit (2022.naacl-demo)
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
| 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. |
VET: Verifiable Execution Tracing for Reliable Text-to-SQL Generation (2026.findings-acl)
Copied to clipboard
| 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. |
SAC: Neural Speech Codec with Semantic-Acoustic Dual-Stream Quantization (2026.acl-long)
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
| 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. |
Are Large Language Models Reliable Reviewers? A Benchmark for Error Detection in Financial Documents (2026.findings-acl)
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
| 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. |
Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration (2022.acl-long)
Copied to clipboard
| 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. |
Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories (2026.acl-long)
Copied to clipboard
| 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. |
UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generation (2024.acl-long)
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
| 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. |
SEGMENT+: Long Text Processing with Short-Context Language Models (2024.emnlp-main)
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
| 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. |
MegaAgent: A Large-Scale Autonomous LLM-based Multi-Agent System Without Predefined SOPs (2025.findings-acl)
Copied to clipboard
| 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. |
Neutralizing Bias in LLM Reasoning using Entailment Graphs (2025.findings-acl)
Copied to clipboard
| 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. |
LM-Lexicon: Improving Definition Modeling via Harmonizing Semantic Experts (2026.eacl-long)
Copied to clipboard
| 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%. |
MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows (2026.acl-long)
Copied to clipboard
| 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. |
Sources of Hallucination by Large Language Models on Inference Tasks (2023.findings-emnlp)
Copied to clipboard
| 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. |
ToxiTrace: Gradient-Aligned Training for Explainable Chinese Toxicity Detection (2026.findings-acl)
Copied to clipboard
| 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. |
Universal Semantic Tagging for English and Mandarin Chinese (2021.naacl-main)
Copied to clipboard
| 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 . |
Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models (2026.findings-acl)
Copied to clipboard
| 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%. |
The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit (2025.acl-long)
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
| 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. |
Multiple Knowledge-Enhanced Interactive Graph Network for Multimodal Conversational Emotion Recognition (2024.findings-emnlp)
Copied to clipboard
| 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. |
Temp-R1: A Unified Autonomous Agent for Complex Temporal KGQA via Reverse Curriculum Reinforcement Learning (2026.acl-long)
Copied to clipboard
Zhaoyan Gong, Zhiqiang Liu, Songze Li, Xiaoke Guo, Yuanxiang Liu, Xinle Deng, Zhizhen Liu, Lei Liang, Huajun Chen, Wen Zhang
| 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. |
Enhancing Dialogue Summarization with Topic-Aware Global- and Local- Level Centrality (2023.eacl-main)
Copied to clipboard
| 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. |
Knowledge-Guided Dynamic Modality Attention Fusion Framework for Multimodal Sentiment Analysis (2024.findings-emnlp)
Copied to clipboard
| 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. |
It’s Not Bragging If You Can Back It Up: Can LLMs Understand Braggings? (2025.acl-long)
Copied to clipboard
| 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. |
Dynamic and Efficient Inference for Text Generation via BERT Family (2023.acl-long)
Copied to clipboard
| 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. |
Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Exploration (2026.findings-acl)
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
| 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. |
Ask-and-Verify: Span Candidate Generation and Verification for Attribute Value Extraction (2022.emnlp-industry)
Copied to clipboard
| 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. |
Data Interpreter: An LLM Agent for Data Science (2025.findings-acl)
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
| 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. |
Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability (2026.acl-long)
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
| 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]. |
L4: Mutual Learning Helps Lifelong Language Learning (2025.emnlp-industry)
Copied to clipboard
| 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. |
PEDANTS: Cheap but Effective and Interpretable Answer Equivalence (2024.findings-emnlp)
Copied to clipboard
| 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. |
MMA: Cross-Domain Knowledge Integration via Mixture of Multi-Domain Agents (2025.findings-emnlp)
Copied to clipboard
| 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. |
MathMixup: Boosting LLM Mathematical Reasoning with Difficulty-Controllable Data Synthesis and Curriculum Learning (2026.findings-acl)
Copied to clipboard
| 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. |
LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offline (2025.findings-acl)
Copied to clipboard
| 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. |
Intrinsic Mutual Information as a Modulator for Preference Optimization (2026.findings-acl)
Copied to clipboard
| 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
| 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. |
RealChart2Code: Bridging the Gap in Real-World Chart-to-Code Generation via Multi-Task Evaluation (2026.acl-long)
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
| 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. |
Multi-Modal Knowledge Graph Transformer Framework for Multi-Modal Entity Alignment (2023.findings-emnlp)
Copied to clipboard
| 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. |
Context-aware Watermark with Semantic Balanced Green-red Lists for Large Language Models (2024.emnlp-main)
Copied to clipboard
| 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 . |
HELENE: Hessian Layer-wise Clipping and Gradient Annealing for Accelerating Fine-tuning LLM with Zeroth-order Optimization (2025.emnlp-main)
Copied to clipboard
| 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. |
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing (2026.acl-industry)
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
| 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. |
Hyperspherical Multi-Prototype with Optimal Transport for Event Argument Extraction (2024.acl-long)
Copied to clipboard
| 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. |
Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm (2024.findings-acl)
Copied to clipboard
Yuanzhen Xie, Xinzhou Jin, Tao Xie, Matrixmxlin Matrixmxlin, Liang Chen, Chenyun Yu, Cheng Lei, Chengxiang Zhuo, Bo Hu, Zang Li
| 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. |
TMFN: A Target-oriented Multi-grained Fusion Network for End-to-end Aspect-based Multimodal Sentiment Analysis (2024.lrec-main)
Copied to clipboard
| 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. |
Just Like a Human Would, Direct Access to Sarcasm Augmented with Potential Result and Reaction (2023.acl-long)
Copied to clipboard
| 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. |
EXPLAIN: Enhancing Retrieval-Augmented Generation with Entity Summary (2025.acl-industry)
Copied to clipboard
Yaozhen Liang, Xiao Liu, Jiajun Yu, Zhouhua Fang, Qunsheng Zou, Linghan Zheng, Yong Li, Zhiwei Liu, Haishuai Wang
| 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. |
CSMCIR: CoT-Enhanced Symmetric Alignment with Memory Bank for Composed Image Retrieval (2026.findings-acl)
Copied to clipboard
Zhipeng Qian, Zihan Liang, Yufei Ma, Ben Chen, Huangyu Dai, Yiwei Ma, Jiayi Ji, Chenyi Lei, Han Li, Xiaoshuai Sun
| 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. |
Infinity-Parser: Layout-Aware Reinforcement Learning with High-quality Document Parsing Dataset (2026.findings-acl)
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
| 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. |
A Self-Attentive Model with Gate Mechanism for Spoken Language Understanding (D18-1)
Copied to clipboard
| 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. |
VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment (2024.emnlp-main)
Copied to clipboard
Lei Li, Zhihui Xie, Mukai Li, Shunian Chen, Peiyi Wang, Liang Chen, Yazheng Yang, Benyou Wang, Lingpeng Kong, Qi Liu
| 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. |
Graph Reasoning Paradigm: Structured and Symbolic Reasoning with Topology-Aware Reinforcement Learning for Large Language Models (2026.acl-long)
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
| 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. |
Towards Debiasing Sentence Representations (2020.acl-main)
Copied to clipboard
Paul Pu Liang, Irene Mengze Li, Emily Zheng, Yao Chong Lim, Ruslan Salakhutdinov, Louis-Philippe Morency
| 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. |
Fact-Tree Reasoning for N-ary Question Answering over Knowledge Graphs (2022.findings-acl)
Copied to clipboard
| 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. |
A Multi-Agent Framework with Automated Decision Rule Optimization for Cross-Domain Misinformation Detection (2025.emnlp-main)
Copied to clipboard
| 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. |
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
| 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. |
AutoScraper: A Progressive Understanding Web Agent for Web Scraper Generation (2024.emnlp-main)
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. |
Beyond Semantic Similarity: Appraisal-Guided Chain-of-Thought Reasoning and Retrieval for Multimodal Emotional Support Conversations (2026.findings-acl)
Copied to clipboard
| 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. |
Concept2Box: Joint Geometric Embeddings for Learning Two-View Knowledge Graphs (2023.findings-acl)
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
| 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. |
LLM-based Conversational Recommendation Agents with Collaborative Verbalized Experience (2025.findings-emnlp)
Copied to clipboard
| 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. |
Think Beyond Words: Exploring Context-Relevant Visual Commonsense for Diverse Dialogue Generation (2022.findings-emnlp)
Copied to clipboard
| 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. |
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models (2024.acl-long)
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
| 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. |
Revisiting Catastrophic Forgetting in Large Language Model Tuning (2024.findings-emnlp)
Copied to clipboard
| 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. |
Retrieval Augmented Instruction Tuning for Open NER with Large Language Models (2025.coling-main)
Copied to clipboard
| 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. |
MemeReaCon: Probing Contextual Meme Understanding in Large Vision-Language Models (2025.emnlp-main)
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
| 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. |
MCS: An In-battle Commentary System for MOBA Games (2022.coling-1)
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. |
Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data (2026.acl-long)
Copied to clipboard
Shiping Yang, Jie Wu, Wenbiao Ding, Ning Wu, Shining Liang, Ming Gong, Hongzhi Li, Hengyuan Zhang, Angel X. Chang, Dongmei Zhang
| 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. |
Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Tracking (2023.acl-long)
Copied to clipboard
| 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. |
Past Meets Present: Creating Historical Analogy with Large Language Models (2025.acl-long)
Copied to clipboard
Nianqi Li, Siyu Yuan, Jiangjie Chen, Jiaqing Liang, Feng Wei, Zujie Liang, Deqing Yang, Yanghua Xiao
| 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. |
Leveraging Social Context for Humor Recognition and Sense of Humor Evaluation in Social Media with a New Chinese Humor Corpus - HumorWB (2024.lrec-main)
Copied to clipboard
| 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 . |
Diachronic Sense Modeling with Deep Contextualized Word Embeddings: An Ecological View (P19-1)
Copied to clipboard
| 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. |
Circuit Complexity Bounds for RoPE-based Transformer Architecture (2025.emnlp-main)
Copied to clipboard
| 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. |
DUAL RM: Beyond Rule-based Preference Reward Modeling via Meta-Reward (2026.acl-long)
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. |
Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch (2025.acl-long)
Copied to clipboard
| 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. |
Context-aware Embedding for Targeted Aspect-based Sentiment Analysis (P19-1)
Copied to clipboard
| 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. |
EGSS: Entropy-guided Stepwise Scaling for Reliable Software Engineering (2026.acl-long)
Copied to clipboard
Chenhui Mao, Yuanting Lei, Zhixiang Wei, Ming Liang, Zhixiang Wang, Jingxuan Xu, Dajun Chen, Wei Jiang, Yong Li
| 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% . |
POMP: Probability-driven Meta-graph Prompter for LLMs in Low-resource Unsupervised Neural Machine Translation (2024.acl-long)
Copied to clipboard
| 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. |
Musical Score Understanding Benchmark: Evaluating Large Language Models’ Comprehension of Complete Musical Scores (2026.acl-long)
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
| 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. |
STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework (P19-1)
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
| 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. |
A Middle Path for On-Premises LLM Deployment: Preserving Privacy Without Sacrificing Model Confidentiality (2025.emnlp-main)
Copied to clipboard
| 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. |
Act-Adaptive Margin: Dynamically Calibrating Reward Models for Subjective Ambiguity (2026.acl-long)
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. |
Mind Reader: Latent User Demand-Guided Content Optimization for Generative Search Engine (2026.acl-long)
Copied to clipboard
Tong Chen, JiaWei Guo, Yuxi Li, Baiming Chen, Houxing Ren, Zhang Zhiwei, Yunxiang Zhang, Hanyang Xia, Kun Liang, Zhaoran Fan
| 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). |
Can Language Models Follow Multiple Turns of Entangled Instructions? (2025.findings-emnlp)
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
| 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. |
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
| 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. |
CARL: Constraint-Aware Reinforcement Learning for Planning with LLMs (2026.findings-acl)
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
| 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. |
Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (2023.emnlp-main)
Copied to clipboard
| 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. |
SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training (2025.findings-acl)
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
| 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
| 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. |
CogEvolve: A Multimodal Benchmark for Evaluating Relational Reasoning in Semantic Extension (2026.acl-long)
Copied to clipboard
| 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. |
Neural Relation Classification with Text Descriptions (C18-1)
Copied to clipboard
| 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. |
MedQPA-Gen: Medical Question Proposing and Answering for Report Generation (2026.findings-acl)
Copied to clipboard
Weijie Liang, Xiyue Zhu, Ruike Zhu, Chenhao Li, Cheng Tang, Zhiyu Liu, Zhihua Gong, Shirui Luo, Yudu Li, Volodymyr Kindratenko
| 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. |
Context-aware Stand-alone Neural Spelling Correction (2020.findings-emnlp)
Copied to clipboard
| 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. |
Semantic Relation-aware Difference Representation Learning for Change Captioning (2021.findings-acl)
Copied to clipboard
| 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. |
VulLibGen: Generating Names of Vulnerability-Affected Packages via a Large Language Model (2024.acl-long)
Copied to clipboard
Tianyu Chen, Lin Li, ZhuLiuchuan ZhuLiuchuan, Zongyang Li, Xueqing Liu, Guangtai Liang, Qianxiang Wang, Tao Xie
| 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. |
Universally Empowering Zeroth-Order Optimization via Adaptive Layer-wise Sampling (2026.findings-acl)
Copied to clipboard
| 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. |
CLUE: A Chinese Language Understanding Evaluation Benchmark (2020.coling-main)
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
| 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
| 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. |
MKT: A Multi-Stage Knowledge Transfer Framework to Mitigate Catastrophic Forgetting in Multi-Domain Chinese Spelling Correction (2025.emnlp-industry)
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
| 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. |
FinTextQA: A Dataset for Long-form Financial Question Answering (2024.acl-long)
Copied to clipboard
| 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. |
TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models (2023.emnlp-main)
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
| 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. |
Dual-Reasoner: Bridging Interleaved Atomicity and Streaming Latency via Thinking-while-Talking (2026.findings-acl)
Copied to clipboard
Yangzhuo Li, Shengpeng Ji, Yifu Chen, Tianle Liang, Haoyu Yang, null Junboli, Jun Fang, Lin Li, Qingyang Hong
| 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. |
Prefix-Tuning: Optimizing Continuous Prompts for Generation (2021.acl-long)
Copied to clipboard
| 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. |
NarGINA: Towards Accurate and Interpretable Children’s Narrative Ability Assessment via Narrative Graphs (2025.findings-acl)
Copied to clipboard
| 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. |
Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion (2025.acl-long)
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
| 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. |
Student Guides Teacher: Weak-to-Strong Inference via Spectral Orthogonal Exploration (2026.acl-long)
Copied to clipboard
| 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. |
UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model (2023.findings-emnlp)
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
| 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. |
A Study of Implicit Ranking Unfairness in Large Language Models (2024.findings-emnlp)
Copied to clipboard
| 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. |
PsychEval: A Multi-Session and Multi-Therapy Benchmark for High-Realism AI Psychological Counselor (2026.findings-acl)
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. |
Investigating and Mitigating the Multimodal Hallucination Snowballing in Large Vision-Language Models (2024.acl-long)
Copied to clipboard
Weihong Zhong, Xiaocheng Feng, Liang Zhao, Qiming Li, Lei Huang, Yuxuan Gu, Weitao Ma, Yuan Xu, Bing Qin
| 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. |
Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning (2022.emnlp-main)
Copied to clipboard
| 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. |
SEE: Signal Embedding Energy for Quantifying Noise Interference in Large Audio Language Models (2026.acl-long)
Copied to clipboard
| 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. |
CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models (2024.findings-acl)
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
| 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. |
Original Content Is All You Need! an Empirical Study on Leveraging Answer Summary for WikiHowQA Answer Selection Task (2022.coling-1)
Copied to clipboard
Liang Wen, Juan Li, Houfeng Wang, Yingwei Luo, Xiaolin Wang, Xiaodong Zhang, Zhicong Cheng, Dawei Yin
| 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. |
Beyond Rejection Sampling: Trajectory Fusion for Scaling Mathematical Reasoning (2026.findings-acl)
Copied to clipboard
| 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. |
Is There a One-Model-Fits-All Approach to Information Extraction? Revisiting Task Definition Biases (2024.findings-emnlp)
Copied to clipboard
| 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. |
Tracing the Light of Thought: A Probabilistic Self- and Cross-Consistency Verification Mechanism Improving Mathematical Reasoning in LLMs (2026.findings-acl)
Copied to clipboard
| 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. |
Towards Unifying Multi-Lingual and Cross-Lingual Summarization (2023.acl-long)
Copied to clipboard
| 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. |
Contrastive Decoding: Open-ended Text Generation as Optimization (2023.acl-long)
Copied to clipboard
Xiang Lisa Li, Ari Holtzman, Daniel Fried, Percy Liang, Jason Eisner, Tatsunori Hashimoto, Luke Zettlemoyer, Mike Lewis
| 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. |
COCOGEC: Counterfactual Generation for Robust Grammatical Error Correction (2026.findings-acl)
Copied to clipboard
| 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. |
Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs (2024.findings-acl)
Copied to clipboard
| 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. |
Change Entity-guided Heterogeneous Representation Disentangling for Change Captioning (2025.findings-acl)
Copied to clipboard
| 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. |
OCNLI: Original Chinese Natural Language Inference (2020.findings-emnlp)
Copied to clipboard
| 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. |
DCT-Centered Temporal Relation Extraction (2022.coling-1)
Copied to clipboard
| 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. |
“Yes, My LoRD.” Guiding Language Model Extraction with Locality Reinforced Distillation (2025.acl-long)
Copied to clipboard
| 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 . |
Boundary-Driven Table-Filling for Aspect Sentiment Triplet Extraction (2022.emnlp-main)
Copied to clipboard
| 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. |
Your Reasoning Model is Secretly a Reward Model - Optimization-Free Verification from Experience (2026.acl-long)
Copied to clipboard
| 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. |
Towards Modeling Role-Aware Centrality for Dialogue Summarization (2022.aacl-short)
Copied to clipboard
| 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. |
S2LPP: Small-to-Large Prompt Prediction across LLMs (2025.findings-emnlp)
Copied to clipboard
| 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. |
Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modeling (2025.emnlp-industry)
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
| 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. |
s1: Simple test-time scaling (2025.emnlp-main)
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
| 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). |
UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression (2022.emnlp-main)
Copied to clipboard
| 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. |
AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents (2025.findings-acl)
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 . |
ACROSS: An Alignment-based Framework for Low-Resource Many-to-One Cross-Lingual Summarization (2023.findings-acl)
Copied to clipboard
| 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. |
Explicit Inductive Inference using Large Language Models (2024.findings-emnlp)
Copied to clipboard
| 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. |
EduBench: A Comprehensive Benchmarking Dataset for Evaluating Large Language Models in Diverse Educational Scenarios (2026.acl-long)
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
| 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. |
Generative Reward Modeling via Synthetic Criteria Preference Learning (2025.acl-long)
Copied to clipboard
| 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. |
MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning (2026.findings-acl)
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
| 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. |
Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuning (2025.findings-acl)
Copied to clipboard
| 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. |
Dynamic Generation of Multi LLM Agents Communication Topologies with Graph Diffusion Models (2026.acl-long)
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
| 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. |
Robust Knowledge Editing via Explicit Reasoning Chains for Distractor-Resilient Multi-Hop QA (2025.findings-emnlp)
Copied to clipboard
| 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. |
DeepPlanner: Scaling Planning Capability for Deep Research Agents via Advantage Shaping (2026.findings-acl)
Copied to clipboard
| 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. |
A Contrastive Cross-Channel Data Augmentation Framework for Aspect-Based Sentiment Analysis (2022.coling-1)
Copied to clipboard
| 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 . |
Improving Semantic Matching through Dependency-Enhanced Pre-trained Model with Adaptive Fusion (2022.findings-emnlp)
Copied to clipboard
| 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. |
C-LLM: Learn to Check Chinese Spelling Errors Character by Character (2024.emnlp-main)
Copied to clipboard
| 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. |
ChatMusician: Understanding and Generating Music Intrinsically with LLM (2024.findings-acl)
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
| 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. |
Improving Unsupervised Extractive Summarization with Facet-Aware Modeling (2021.findings-acl)
Copied to clipboard
| 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. |
A3: Android Agent Arena for Mobile GUI Agents with Essential-State Procedural Evaluation (2026.findings-acl)
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
| 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. |
MIND Your Reasoning: A Meta-Cognitive Intuitive-Reflective Network for Dual-Reasoning in Multimodal Stance Detection (2026.acl-long)
Copied to clipboard
| 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. |
WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning (2025.emnlp-main)
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. |
On the Complementarity between Pre-Training and Random-Initialization for Resource-Rich Machine Translation (2022.coling-1)
Copied to clipboard
| 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. |
Controllable Contamination Detection for Reliable LLM Evaluation with Statistical Guarantees (2026.acl-long)
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
| 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. |
Modeling Multi-Granularity Hierarchical Features for Relation Extraction (2022.naacl-main)
Copied to clipboard
| 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. |
NL ⇒ Schedule: Evaluate Multitask Scheduling Capability of Large Language Models (2026.acl-long)
Copied to clipboard
| 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. |
ChemAmp: Amplified Chemistry Tools via Composable Agents (2026.findings-acl)
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
| 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. |
GLA: Grounding Large Language Models in Molecular Hierarchy for Chemical Understanding (2026.findings-acl)
Copied to clipboard
| 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. |
TAG : Type Auxiliary Guiding for Code Comment Generation (2020.acl-main)
Copied to clipboard
| 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. |
DORM: Preference Data Weights Optimization for Reward Modeling in LLM Alignment (2025.findings-emnlp)
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. |
ATG: Benchmarking Automated Theorem Generation for Generative Language Models (2024.findings-naacl)
Copied to clipboard
| 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. |
EventWeave: A Dynamic Framework for Capturing Core and Supporting Events in Dialogue Systems (2026.acl-long)
Copied to clipboard
Zhengyi Zhao, Shubo Zhang, Yiming Du, Bin Liang, Baojun Wang, Zhongyang Li, Binyang Li, Kam-Fai Wong
| 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. |
Self-Evolution Learning for Mixup: Enhance Data Augmentation on Few-Shot Text Classification Tasks (2023.emnlp-main)
Copied to clipboard
Haoqi Zheng, Qihuang Zhong, Liang Ding, Zhiliang Tian, Xin Niu, Changjian Wang, Dongsheng Li, Dacheng Tao
| 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. |
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code (2022.emnlp-demos)
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
| 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. |
Can MLLMs Understand the Deep Implication Behind Chinese Images? (2025.acl-long)
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
| 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. |
DT-Solver: Automated Theorem Proving with Dynamic-Tree Sampling Guided by Proof-level Value Function (2023.acl-long)
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
| 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. |
Advancing SMoE for Continuous Domain Adaptation of MLLMs: Adaptive Router and Domain-Specific Loss (2025.acl-long)
Copied to clipboard
| 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 . |
Breaking the Reasoning Barrier A Survey on LLM Complex Reasoning through the Lens of Self-Evolution (2025.findings-acl)
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
| 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). |
Mechanistic Insights into Deferred Semantic Drift in LLMs (2026.findings-acl)
Copied to clipboard
| 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
| 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. |
T2: An Adaptive Test-Time Scaling Strategy for Contextual Question Answering (2025.emnlp-main)
Copied to clipboard
Zhengyi Zhao, Shubo Zhang, Zezhong Wang, Huimin Wang, Yutian Zhao, Bin Liang, Yefeng Zheng, Binyang Li, Kam-Fai Wong, Xian Wu
| 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%. |
Does it Make Sense? And Why? A Pilot Study for Sense Making and Explanation (P19-1)
Copied to clipboard
| 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. |
Hypernetwork-Assisted Parameter-Efficient Fine-Tuning with Meta-Knowledge Distillation for Domain Knowledge Disentanglement (2024.findings-naacl)
Copied to clipboard
| 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. |
Novel Slot Detection With an Incremental Setting (2023.findings-emnlp)
Copied to clipboard
| 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. |
EfficientLLM: Unified Pruning-Aware Pretraining for Auto-Designed Compact Language Models (2026.acl-long)
Copied to clipboard
Xingrun Xing, Zheng Liu, Shitao Xiao, Boyan Gao, Yiming Liang, Haokun Lin, Xianlin Zeng, Guoqi Li, Jiajun Zhang
| 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. |
Set Learning for Generative Information Extraction (2023.emnlp-main)
Copied to clipboard
| 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. |
Edit Once, Update Everywhere: A Simple Framework for Cross-Lingual Knowledge Synchronization in LLMs (2025.findings-acl)
Copied to clipboard
| 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. |
Sequential-NIAH: A Needle-In-A-Haystack Benchmark for Extracting Sequential Needles from Long Contexts (2025.emnlp-main)
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
| 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. |
MaXIFE: Multilingual and Cross-lingual Instruction Following Evaluation (2025.acl-long)
Copied to clipboard
| 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. |
Curriculum Prompt Learning with Self-Training for Abstractive Dialogue Summarization (2022.emnlp-main)
Copied to clipboard
| 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. |
StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models (2024.findings-acl)
Copied to clipboard
Zhicheng Guo, Sijie Cheng, Hao Wang, Shihao Liang, Yujia Qin, Peng Li, Zhiyuan Liu, Maosong Sun, Yang Liu
| 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. |
Unsupervised Keyphrase Extraction by Jointly Modeling Local and Global Context (2021.emnlp-main)
Copied to clipboard
| 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. |
OneEE: A One-Stage Framework for Fast Overlapping and Nested Event Extraction (2022.coling-1)
Copied to clipboard
| 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. |
Training Verifier to Assessing Complex Real-World Tool-Use Trajectories (2026.findings-acl)
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. |
Context-aware Difference Distilling for Multi-change Captioning (2024.acl-long)
Copied to clipboard
| 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. |
ReasonRec: A Reasoning-Augmented Multimodal Agent for Unified Recommendation (2026.findings-acl)
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
| 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. |
VoxMind: An End-to-End Agentic Spoken Dialogue System (2026.acl-long)
Copied to clipboard
Tianle Liang, Yifu Chen, Shengpeng Ji, Yijun Chen, Zhiyang Jia, Jingyu Lu, Fan Zhuo, Xueyi Pu, Yangzhuo Li, Zhou Zhao
| 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. |
Rˆ3Net:Relation-embedded Representation Reconstruction Network for Change Captioning (2021.emnlp-main)
Copied to clipboard
| 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. |
JANUS: Joint Autoregressive and Non-autoregressive Training with Auxiliary Loss for Sequence Generation (2022.emnlp-main)
Copied to clipboard
| 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. |
ESC-Eval: Evaluating Emotion Support Conversations in Large Language Models (2024.emnlp-main)
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
| 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. |
HearSay Benchmark: Do Audio LLMs Leak What They Hear? (2026.findings-acl)
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
| 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. |
Giving Control Back to Models: Enabling Offensive Language Detection Models to Autonomously Identify and Mitigate Biases (2024.findings-emnlp)
Copied to clipboard
| 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. |
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
| 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. |
FRVA: Fact-Retrieval and Verification Augmented Entailment Tree Generation for Explainable Question Answering (2024.findings-acl)
Copied to clipboard
| 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. |
COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values (2026.findings-eacl)
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
| 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. |
FedSpaLLM: Federated Pruning of Large Language Models (2025.naacl-long)
Copied to clipboard
| 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. |
Self-Critique Guided Iterative Reasoning for Multi-hop Question Answering (2025.findings-acl)
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
| 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. |
Do Large Language Models have Problem-Solving Capability under Incomplete Information Scenarios? (2024.findings-acl)
Copied to clipboard
| 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. |
WatME: Towards Lossless Watermarking Through Lexical Redundancy (2024.acl-long)
Copied to clipboard
| 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. |
Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pre-training (2026.findings-eacl)
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
| 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. |
Improving Encoder by Auxiliary Supervision Tasks for Table-to-Text Generation (2021.acl-long)
Copied to clipboard
| 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. |
An Examination of the Compositionality of Large Generative Vision-Language Models (2024.naacl-long)
Copied to clipboard
| 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. |
3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset (2024.lrec-main)
Copied to clipboard
Xinyu Ma, Xuebo Liu, Derek F. Wong, Jun Rao, Bei Li, Liang Ding, Lidia S. Chao, Dacheng Tao, Min Zhang
| 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. |
EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving (2026.acl-long)
Copied to clipboard
| 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. |
ReasMark: A Robust Watermark for Attributing LLM Reasoning Under Knowledge Distillation Attacks (2026.acl-long)
Copied to clipboard
Peizhuo Lv, Ruihua Zhou, Yunpeng Li, Ruigang Liang, Xingshuo Han, XiaoFeng Wang, Wei Dong, Yuling Liu
| 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. |
Dynamic Heterogeneous-Graph Reasoning with Language Models and Knowledge Representation Learning for Commonsense Question Answering (2023.acl-long)
Copied to clipboard
| 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. |
SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval (2024.findings-acl)
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
| 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. |
Making Long-Context Language Models Better Multi-Hop Reasoners (2024.acl-long)
Copied to clipboard
| 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. |
JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse (2025.findings-acl)
Copied to clipboard
| 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. |
H-MAS: Hierarchical Multi-Agent Scheduling for Multi-Tenant LLM Serving (2026.findings-acl)
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 . |
Flexibly Utilize Memory for Long-Term Conversation via a Fragment-then-Compose Framework (2025.emnlp-main)
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
| 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 . |
Actively Learn from LLMs with Uncertainty Propagation for Generalized Category Discovery (2024.naacl-long)
Copied to clipboard
| 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
| 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. |
A Data-Centric Framework for Composable NLP Workflows (2020.emnlp-demos)
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 . |
Decide less, communicate more: On the construct validity of end-to-end fact-checking in medicine (2026.findings-acl)
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
| 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 . |
Tool learning via Inference-time Scaling and Cycle Verifier (2025.findings-acl)
Copied to clipboard
| 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. |
QAEncoder: Towards Aligned Representation Learning in Question Answering Systems (2025.acl-long)
Copied to clipboard
Zhengren Wang, Qinhan Yu, Shida Wei, Zhiyu Li, Feiyu Xiong, Xiaoxing Wang, Simin Niu, Hao Liang, Wentao Zhang
| 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. |
A Survey of Inductive Reasoning for Large Language Models (2026.acl-long)
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
| 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. |
DABERT: Dual Attention Enhanced BERT for Semantic Matching (2022.coling-1)
Copied to clipboard
| 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. |
Unlocking Recursive Thinking of LLMs: Alignment via Refinement (2025.findings-acl)
Copied to clipboard
| 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
| 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. |
A Survey on Cross-Lingual Summarization (2022.tacl-1)
Copied to clipboard
| 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. |
Multiview Identifiers Enhanced Generative Retrieval (2023.acl-long)
Copied to clipboard
| 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. |
Graph-to-Text Generation with Dynamic Structure Pruning (2022.coling-1)
Copied to clipboard
| 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. |
MultiLingPoT: Boosting Mathematical Reasoning in LLMs through Multilingual Program Integration (2025.findings-emnlp)
Copied to clipboard
| 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%. |
CoreEval: Automatically Building Contamination-Resilient Datasets with Real-World Knowledge toward Reliable LLM Evaluation (2025.acl-long)
Copied to clipboard
| 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. |
Fast-R2D2: A Pretrained Recursive Neural Network based on Pruned CKY for Grammar Induction and Text Representation (2022.emnlp-main)
Copied to clipboard
| 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. |
InfoGain-RAG: Boosting Retrieval-Augmented Generation through Document Information Gain-based Reranking and Filtering (2025.emnlp-main)
Copied to clipboard
Zihan Wang, Zihan Liang, Zhou Shao, Yufei Ma, Huangyu Dai, Ben Chen, Lingtao Mao, Chenyi Lei, Yuqing Ding, Han Li
| 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. |
InstructEd: Soft-Instruction Tuning for Model Editing with Hops (2024.findings-acl)
Copied to clipboard
| 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 . |
Curriculum Learning based Hierarchical Scoring and Analysis Framework for Question Answering Task Evaluation (2026.findings-acl)
Copied to clipboard
| 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. |
Jiuge: A Human-Machine Collaborative Chinese Classical Poetry Generation System (P19-3)
Copied to clipboard
Guo Zhipeng, Xiaoyuan Yi, Maosong Sun, Wenhao Li, Cheng Yang, Jiannan Liang, Huimin Chen, Yuhui Zhang, Ruoyu Li
| 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. |
ProMedTS: A Self-Supervised, Prompt-Guided Multimodal Approach for Integrating Medical Text and Time Series (2025.findings-acl)
Copied to clipboard
Shuai Niu, Jing Ma, Hongzhan Lin, Liang Bai, Zhihua Wang, V. W., Richard Yi Da Xu, Guo Li, Xian Yang
| 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. |
Adaptive Ordered Information Extraction with Deep Reinforcement Learning (2023.findings-acl)
Copied to clipboard
| 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. |
Getting More Juice Out of Your Data: Hard Pair Refinement Enhances Visual-Language Models Without Extra Data (2025.naacl-long)
Copied to clipboard
Haonan Wang, Minbin Huang, Runhui Huang, Lanqing Hong, Hang Xu, Tianyang Hu, Xiaodan Liang, Zhenguo Li, Hong Cheng, Kenji Kawaguchi
| Challenge: | Contrastive Language-Image Pre-training (CLIP) is a standard for cross-modal image-text representation learning. |
| Approach: | They propose a framework that enhances pre-trained CLIP models by exploiting challenging text-image pairs within existing datasets. |
| Outcome: | The proposed framework improves CLIP models by exploiting text-image pairs in training. |
Understanding Translationese in Cross-Lingual Summarization (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing datasets involve translation, but translationese is distinguished from original text . previous studies have shown that translationeses in CLS are not a problem in training sets . |
| Approach: | They propose to use cross-lingual summarization to generate a concise summary in a target language from a document in . existing datasets typically involve translation in their creation, but the translated text is distinguished from the original written in that language. |
| Outcome: | The proposed method systematically investigates how translationese affects CLS model evaluation and performance when it appears in source documents or target summaries. |
MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification (2025.acl-long)
Copied to clipboard
| Challenge: | MM-Verifier and MM Reasoner are a powerful multimodal reasoning model . large language models (LLMs) have demonstrated exceptional performance across tasks spanning myriad domains. |
| Approach: | They propose a method which combines tree search and verification to generate high-quality chain-of-thought data. |
| Outcome: | The proposed method outperforms all larger models on the MathCheck, MathVista, and MathVerse benchmarks. |
HCRE: LLM-based Hierarchical Classification for Cross-Document Relation Extraction with a Prediction-then-Verification Strategy (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to cross-document relation extraction (RE) focus on identifying relations between head and tail entities from single sentence or document. |
| Approach: | They propose a hierarchical relation tree-based LLM-based hierarchic classification model for cross-document relation extraction (HCRE) based on predefined relations, the model can perform hierarchically classification level by level. |
| Outcome: | The proposed model outperforms existing baselines and validates its effectiveness. |
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models (2026.acl-long)
Copied to clipboard
Xin Cheng, Wangding Zeng, Damai Dai, Qinyu Chen, Bingxuan Wang, Zhenda Xie, Kezhao Huang, Xingkai Yu, Zhewen Hao, Han Zhang, Yu-Kun Li, Huishuai Zhang, Dongyan Zhao, Wenfeng Liang
| Challenge: | Mixture-of-Experts (MoE) scales capacity via conditional computation, but lacks knowledge lookup primitive. |
| Approach: | They propose a conditional memory instantiated via Deep Sparse Embedding (DSE) they propose 'u-shaped scaling law' that identifies optimal balance between MoE experts and DSE memory . |
| Outcome: | The proposed model outperforms an iso-parameter and isoFLOPs MoE baseline across knowledge and reasoning benchmarks and is infrastructure-efficient. |
Generative Entity Typing with Curriculum Learning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Entity typing fails to assign an entity to the types beyond the predefined type set. |
| Approach: | They propose a generative entity typing paradigm that assigns types to entities . traditional classification-based approaches fail to assign entities to the types beyond the predefined set . they employ curriculum learning to train the model on heterogeneous data . |
| Outcome: | The proposed model outperforms the state-of-the-art model on heterogeneous training data. |
OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use (2025.acl-long)
Copied to clipboard
Xueyu Hu, Tao Xiong, Biao Yi, Zishu Wei, Ruixuan Xiao, Yurun Chen, Jiasheng Ye, Meiling Tao, Xiangxin Zhou, Ziyu Zhao, Yuhuai Li, Shengze Xu, Shenzhi Wang, Xinchen Xu, Shuofei Qiao, Zhaokai Wang, Kun Kuang, Tieyong Zeng, Liang Wang, Jiwei Li, Yuchen Eleanor Jiang, Wangchunshu Zhou, Guoyin Wang, Keting Yin, Zhou Zhao, Hongxia Yang, Fan Wu, Shengyu Zhang, Fei Wu
| Challenge: | a new generation of (M)LLMs is enabling the creation of superintelligent AI assistants . OS Agents can complete tasks autonomously and have the potential to significantly enhance the lives of billions of users worldwide. |
| Approach: | They propose to build OS Agents that operate within operating systems' GUIs and GUIs . they examine evaluation metrics and benchmarks to identify promising directions . |
| Outcome: | The proposed agents are based on operating systems (OS) and operating systems frameworks. |
Quantification of Large Language Model Distillation (2025.acl-long)
Copied to clipboard
Sunbowen Lee, Junting Zhou, Chang Ao, Kaige Li, Xeron Du, Sirui He, Haihong Wu, Tianci Liu, Jiaheng Liu, Hamid Alinejad-Rokny, Min Yang, Yitao Liang, Zhoufutu Wen, Shiwen Ni
| Challenge: | Existing studies have revealed the robustness degra-dation caused by data distillation. |
| Approach: | They propose a framework to evaluate and quantify model distillation . they aim to identify identity cognition contradictions and analyse multi-granularity response similarities across models to measure the extent of homogenization. |
| Outcome: | The proposed framework addresses two key aspects: (1) Identifying identity cognition contradictions to assess discrepancies in how models perceive and represent identity-related information; (2) Analyzing multi-granularity response similarities across models to measure the extent of homogenization. |
Denoising based Sequence-to-Sequence Pre-training for Text Generation (D19-1)
Copied to clipboard
| Challenge: | PoDA pre-trains encoders and decoders by denoising noise-corrupted text . Unlike encoder-only or decode-only methods, it can be used for text generation tasks without using any task-specific techniques. |
| Approach: | They propose a sequence-to-sequence (seq2sequ) pre-training method PoDA which denoises autoencoders by denoising noise-corrupted text. |
| Outcome: | The proposed method improves model performance over strong baselines without using any task-specific techniques and significantly speed up convergence. |
LongEmbed: Extending Embedding Models for Long Context Retrieval (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing embedding models support only 512 input tokens, hindering their application in scenarios requiring long inputs. |
| Approach: | They evaluate the performance of existing embedding models by using a new benchmark and a training-free context window extension strategy. |
| Outcome: | The proposed model extends the input window of existing models by several folds. |
WavAlign: Enhancing Intelligence and Expressiveness in Spoken Dialogue Models via Adaptive Hybrid Post-Training (2026.findings-acl)
Copied to clipboard
Yifu Chen, Shengpeng Ji, Qian Chen, Tianle Liang, Yangzhuo Li, Ziqing Wang, Wen Wang, Jingyu Lu, Haoxiao Wang, Xueyi Pu, Fan Zhuo, Zhou Zhao
| Challenge: | End-to-end spoken dialogue models have higher potential ceiling in expressiveness and perceptual ability than cascaded systems. |
| Approach: | They propose a modality-aware adaptive post-training recipe that constrains preference updates to the semantic channel and improves acoustic behavior via explicit anchoring. |
| Outcome: | The proposed model improves speech quality and expressiveness across spoken dialogue benchmarks and architectures. |
Stance Detection on Social Media with Background Knowledge (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies of stance detection focus on learning stance information about specific targets from context, but in real-world scenarios, we usually have a certain understanding of a target when we express our stance on it. |
| Approach: | They propose to take the background knowledge of the target into account for better stance detection by categorizing it into episodic and discourse knowledge categories and a heuristic retrieval algorithm based on the topic to retrieve the Wikipedia documents relevant to the sample. |
| Outcome: | The proposed framework achieves state-of-the-art on four benchmark datasets showing that the proposed framework is able to detect stances in-target and zero-shot scenarios. |
Plot Retrieval as an Assessment of Abstract Semantic Association (2024.acl-srw)
Copied to clipboard
| Challenge: | Existing information retrieval datasets cannot capture abstract semantic associations well. |
| Approach: | They propose a task that retrieves relevant plots from the book for a query using a labeled dataset. |
| Outcome: | The proposed task can be used to evaluate the performance of IR models on the novel task Plot Retrieval. |
DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing KV cache compression methods enforce a fixed pattern, neglecting task-specific characteristics, which hampers the effective retention of essential information while discarding less important tokens. |
| Approach: | They propose a Task-Aware KV cache mechanism that dynamically adjusts the KV caching size across different layers based on the characteristics of the tasks. |
| Outcome: | The proposed method surpasses state-of-the-art methods by 11% on the LongBench dataset even under extreme compression (0.9%) |
GuiLoMo: Allocating Experts and Ranks for LoRA-MoE via Bilevel Optimization with GuidedSelection Vectors (2025.findings-emnlp)
Copied to clipboard
Xinrong Chen, Hengyuan Zhang, Yingmin Qiu, Xiao Liang, Ziyue Li, Guanyu Wang, Weiping Li, Tong Mo, Hayden Kwok-Hay So, Ngai Wong
| Challenge: | Low-Rank Adaptation (LoRA) methods are efficient for a large language model with reduced computational costs. |
| Approach: | They propose a layer-wise expert numbers and ranks allocation strategy with GuidedSelection Vectors. |
| Outcome: | The proposed method achieves superior or comparable performance to all baselines on three backbone models. |
An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint (2025.emnlp-main)
Copied to clipboard
Yi Sun, Han Wang, Jiaqiang Li, Jiacheng Liu, Xiangyu Li, Hao Wen, Yizhen Yuan, Huiwen Zheng, Yan Liang, Yuanchun Li, Yunxin Liu
| Challenge: | Large Language Models (LLMs) are a powerful tool for test-time scaling, but they are often used under time constraints. |
| Approach: | They propose to use LLMs to make models think before answering questions . they also use self-correction and best-of-N decoding to encourage deeper thinking . |
| Outcome: | The proposed models are able to achieve higher inference accuracy with extra inference computation under time constraints. |
LOTUS: Evolving Multimodal Unlearning via Hyperbolic Entailment and Lorentz Transport (2026.acl-long)
Copied to clipboard
| Challenge: | Existing unlearning methods suffer from a geometric mismatch, causing catastrophic forgetting or unsafe substitution. |
| Approach: | They propose a framework for surgical semantic pruning within the Lorentz manifold. |
| Outcome: | Experiments on MLLMU-Bench show that LOTUS significantly outperforms baselines while maintaining general utility. |
StyleDGPT: Stylized Response Generation with Pre-trained Language Models (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for generating responses following a desired style are lacking of parallel data for training. |
| Approach: | They propose a KL loss and a style classifier to fine-tune response generation . they show that their model can significantly outperform state-of-the-art methods . |
| Outcome: | The proposed model outperforms state-of-the-art models in style consistency and contextual coherence with two public datasets. |
Delete, Retrieve, Generate: a Simple Approach to Sentiment and Style Transfer (N18-1)
Copied to clipboard
| Challenge: | Previous work using adversarial methods has struggled to produce high-quality outputs. |
| Approach: | They propose a method that transforms a sentence to alter a specific attribute while preserving its attribute-independent content. |
| Outcome: | The proposed method generates grammatical and appropriate responses on 22% more inputs than the best previous system, averaged over three attribute transfer datasets. |
Dice Loss for Data-imbalanced NLP Tasks (2020.acl-main)
Copied to clipboard
| Challenge: | Using dice loss, we find that data imbalance is a common issue in many NLP tasks . data imbalance affects the performance of many tasks, such as tagging and machine reading comprehension . |
| Approach: | They propose to use dice loss to replace the standard cross-entropy objective for data-imbalanced NLP tasks. |
| Outcome: | The proposed training objective achieves significant performance boost on a wide range of data imbalanced tasks. |
StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing (2024.findings-acl)
Copied to clipboard
Gaoxiang Cong, Yuankai Qi, Liang Li, Amin Beheshti, Zhedong Zhang, Anton Hengel, Ming-Hsuan Yang, Chenggang Yan, Qingming Huang
| Challenge: | Existing methods for movie dubbing break phonemes in scripts, resulting in incomplete phoneme pronunciation and poor identity stability. |
| Approach: | They propose a method that switches dubbing learning from frame level to phoneme level . it uses a multimodal style adaptor to learn pronunciation style from audio . |
| Outcome: | The proposed method improves on two benchmarks, V2C and Grid, and is available on github. |
AGR: Reinforced Causal Agent-Guided Self-explaining Rationalization (2024.acl-short)
Copied to clipboard
| Challenge: | Existing rationalization approaches are susceptible to degeneration due to lack of effective control over the learning direction of the model during training. |
| Approach: | They propose an agent-guided rationalization approach that guides the next step of the model based on its current training state. |
| Outcome: | The proposed approach outperforms state-of-the-art methods on BeerAdvocate and HotelReview datasets. |
CATS: A Pragmatic Chinese Answer-to-Sequence Dataset with Large Scale and High Quality (2023.acl-long)
Copied to clipboard
Liang Li, Ruiying Geng, Chengyang Fang, Bing Li, Can Ma, Rongyu Cao, Binhua Li, Fei Huang, Yongbin Li
| Challenge: | Current datasets bias in the English language while leaving other languages underexplored. |
| Approach: | They propose a Chinese answer-to-sequence dataset with high quality and large scale . they propose encoding space for two hybrid knowledge resources to convert this task to a graph-totext problem. |
| Outcome: | The proposed method is effective in generating textual descriptions for the Chinese answer-to-sequence dataset. |
CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark (2022.acl-long)
Copied to clipboard
Ningyu Zhang, Mosha Chen, Zhen Bi, Xiaozhuan Liang, Lei Li, Xin Shang, Kangping Yin, Chuanqi Tan, Jian Xu, Fei Huang, Luo Si, Yuan Ni, Guotong Xie, Zhifang Sui, Baobao Chang, Hui Zong, Zheng Yuan, Linfeng Li, Jun Yan, Hongying Zan, Kunli Zhang, Buzhou Tang, Qingcai Chen
| Challenge: | a new benchmark for biomedical language understanding is being developed in Chinese . most benchmarks are limited to English, which makes it difficult to replicate success in other languages. |
| Approach: | They propose to use Chinese biomedical language understanding evaluation benchmarks to evaluate Chinese models. |
| Outcome: | The proposed benchmarks show that the current models perform worse than the human ceiling. |
How Does the Disclosure of AI Assistance Affect the Perceptions of Writing? (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in generative AI technologies like large language models have boosted the incorporation of AI assistance in writing workflows. |
| Approach: | They conduct an experimental study to determine whether disclosure of AI assistance in the writing process would affect people's evaluation on the quality of the writing and ranking of different writings. |
| Outcome: | The disclosure of AI assistance decreases the average quality ratings for argumentative essays and creative stories, and increases the quality of the writings. |
Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning pretrained language models suffer from poor generalization . however, they add a perturbation to each model parameter equally, which is sub-optimal . |
| Approach: | They propose a sharpness-aware minimization optimization procedure that introduces a Fisher mask to improve the efficiency of SAM. |
| Outcome: | The proposed method outperforms the vanilla sharpness-aware minimization method on GLUE and SuperGLUE benchmarks. |
Towards Making the Most of ChatGPT for Machine Translation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Prior studies have shown that ChatGPT achieves comparable results to commercial systems for high-resource languages, but lags behind in complex tasks, e.g., low-resourced and distant-language-pairs translation. |
| Approach: | They propose task-specific prompts and domain-specific prompts which are based on task information and domain information and a task-specific prompt. |
| Outcome: | The proposed prompts improve the performance of ChatGPT in complex tasks and generate hallucinations for non-English-centric tasks. |
Compositional Generalization for Primitive Substitutions (D19-1)
Copied to clipboard
| Challenge: | Existing approaches to encoding compositional generalization are lacking . et al., 2017) argue that neural networks lack compositional ability . |
| Approach: | They propose a method to encode compositionality in neural networks using two representations . they reduce the entropy in each representation to improve generalization . |
| Outcome: | The proposed approach improves performance on five NLP tasks including instruction learning and machine translation. |
Multi-level Adaptive Contrastive Learning for Knowledge Internalization in Dialogue Generation (2023.emnlp-main)
Copied to clipboard
Chenxu Yang, Zheng Lin, Lanrui Wang, Chong Tian, Liang Pang, Jiangnan Li, Qirong Ho, Yanan Cao, Weiping Wang
| Challenge: | Existing knowledge-grounded dialogue generation models struggle with dull and repetitive outputs, a problem commonly termed as text degeneration. |
| Approach: | They propose a framework that allows the model to "cheat" the objective by duplicating knowledge segments in a superficial pattern matching based on overlap. |
| Outcome: | The proposed framework can be applied to a WoW dataset and shows that it works across models and decoding strategies. |
Unified Hallucination Detection for Multimodal Large Language Models (2024.acl-long)
Copied to clipboard
Xiang Chen, Chenxi Wang, Yida Xue, Ningyu Zhang, Xiaoyan Yang, Qiang Li, Yue Shen, Lei Liang, Jinjie Gu, Huajun Chen
| Challenge: | despite significant strides in multimodal tasks, MLLMs are plagued by the critical issue of hallucination. |
| Approach: | They propose a meta-evaluation benchmark to facilitate evaluation of advancements in hallucination detection methods. |
| Outcome: | The proposed framework validates hallucinations robustly and provides strategic insights . MHaluBench is a meta-evaluation benchmark designed to facilitate evaluation . |
Label-Enhanced Hierarchical Contextualized Representation for Sequential Metaphor Identification (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent approaches to identify metaphors ignore extra information from data, such as contextual information and broader discourse information. |
| Approach: | They propose a model augmented with hierarchical contextualized representation to extract more information from both sentence-level and discourse-level. |
| Outcome: | The proposed model outperforms state-of-the-art methods on two tasks using a VUA dataset. |
Route Sparse Autoencoder to Interpret Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Sparse autoencoders (SAEs) extract interpretable and monosemantic features in large language models . prior work focused on feature extraction from a single layer, failing to capture activations that span multiple layers. |
| Approach: | They propose a framework that integrates a routing mechanism with a shared SAE to efficiently extract features from multiple layers. |
| Outcome: | The proposed framework extracts features from multiple layers while incurring minimal parameter overhead while achieving high interpretability and flexibility. |
Discovering Representation Sprachbund For Multilingual Pre-Training (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models perform poorly on many languages and cross-lingual tasks due to typological differences and contradictions between some languages. |
| Approach: | They propose to pre-train multilingual pre-trained models to handle cross-lingual tasks in one model. |
| Outcome: | The proposed model improves performance on cross-lingual tasks compared to baselines on multiple languages . |
MGCL: Multi-Granularity Clue Learning for Emotion-Cause Pair Extraction via Cross-Grained Knowledge Distillation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Traditional methods often rely on coarse-grained clause-level annotations, which overlook valuable fine-grain clues. |
| Approach: | They propose a method that captures fine-grained clues from a weakly-supervised perspective efficiently by using a teacher model to give sub-clause clues without needing fine-grain annotations. |
| Outcome: | The proposed method achieves state-of-the-art performance while offering improved interpretability. |
VenusFactory: An Integrated System for Protein Engineering with Data Retrieval and Language Model Fine-Tuning (2025.acl-demo)
Copied to clipboard
Yang Tan, Chen Liu, Jingyuan Gao, Wu Banghao, Mingchen Li, Ruilin Wang, Lingrong Zhang, Huiqun Yu, Guisheng Fan, Liang Hong, Bingxin Zhou
| Challenge: | Pre-trained protein language models have been used in protein engineering, but their adoption is limited due to data collection, task benchmarking, and application challenges. |
| Approach: | They propose a versatile engine that integrates biological data retrieval, standardized task benchmarking, and modular fine-tuning of PLMs. |
| Outcome: | The proposed engine integrates biological data retrieval, task benchmarking, and modular fine-tuning of PLMs. |
Escaping the Echo Trap: On Credit Assignment Failure in Multi-turn LLM Self-Reflection (2026.acl-long)
Copied to clipboard
Linxuan Du, Guangquan Xue, Xiaobo Liang, Qipeng Huang, Yuyang Ding, Xinyu Shi, Zhang Yijun, Ji Qi, Wenpeng Zhu, Juntao Li, Min Zhang
| Challenge: | Existing methods for multi-turn self-reflection are limited by the Echo Trap problem . the model is limited by its inherent capabilities and repeats earlier reflections to preserve reward signals . |
| Approach: | They propose a tree-structured extension of GRPO for multi-turn self-reflection which enables more accurate advantage estimation. |
| Outcome: | The proposed method mitigates behavior collapse and improves performance across benchmarks. |
From Awareness to Adaptability: Enhancing Tool Utilization for Scientific Reasoning (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches enhance reasoning through Chain-of-Thought, Program-ofThough, and Tool-Integration. |
| Approach: | They propose a tool-awareness training method that leverages both forward and backward data generation strategies to strengthen the model’s conscious and selective tool utilization in multi-step reasoning tasks. |
| Outcome: | The proposed method improves the model's tool utilization capabilities, including proactivity and execution success rates. |
Target-to-Source Augmentation for Aspect Sentiment Triplet Extraction (2023.emnlp-main)
Copied to clipboard
| Challenge: | Aspect Sentiment Triplet Extraction (ASTE) is an important task in sentiment analysis, but data scarcity limits performance of existing methods. |
| Approach: | They propose a target-to-source augmentation approach to alleviate the issue of data scarcity in Aspect Sentiment Triplet Extraction (ASTE) they use fluency and alignment discriminators to provide feedback and use this feedback to optimize the generator. |
| Outcome: | The proposed approach significantly improves the performance of existing methods. |
RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter (2024.findings-acl)
Copied to clipboard
Meng Cao, Haoran Tang, Jinfa Huang, Peng Jin, Can Zhang, Ruyang Liu, Long Chen, Xiaodan Liang, Li Yuan, Ge Li
| Challenge: | Text-Video Retrieval (TVR) aims to align relevant video content with natural language queries. |
| Approach: | They propose to conduct efficient text-video Retrieval with a salient-and-correlated AdaPter . they propose a low-rank modulation module to refine per-image features from frozen CLIP backbone . |
| Outcome: | Experiments on four TVR datasets show that the proposed method performs better than other methods. |
CogSteer: Cognition-Inspired Selective Layer Intervention for Efficiently Steering Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) achieve excellent performance through pretraining on extensive data. |
| Approach: | They propose an efficient selective layer intervention based on parameter-efficient fine-tuning methods to select the optimal steering layer to modulate LLM semantics. |
| Outcome: | The proposed approach is based on a model-agnostic framework and is safe to deploy. |
SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model (2025.acl-long)
Copied to clipboard
Xun Liang, Simin Niu, Zhiyu Li, Sensen Zhang, Hanyu Wang, Feiyu Xiong, Zhaoxin Fan, Bo Tang, Jihao Zhao, Jiawei Yang, Shichao Song, Mengwei Wang
| Challenge: | Existing approaches to integrating external knowledge into large language models (LLMs) however, the incorporation of external knowledge increases the vulnerability of LLMs . |
| Approach: | They propose a benchmark to evaluate the RAG security using a dataset . they classify attack tasks into silver noise, inter-context conflict, soft ad, and white Denial-of-Service . |
| Outcome: | The proposed benchmark evaluates the security of RAG against 14 representative RAG components. |
MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL (2025.coling-main)
Copied to clipboard
Bing Wang, Changyu Ren, Jian Yang, Xinnian Liang, Jiaqi Bai, LinZheng Chai, Zhao Yan, Qian-Wen Zhang, Di Yin, Xing Sun, Zhoujun Li
| Challenge: | Recent LLM-based Text-to-SQL methods suffer from performance degradation on “huge” databases and complex user questions that require multi-step reasoning. |
| Approach: | They propose a framework that integrates a decomposer agent and auxiliary agents to generate SQL queries from natural language text. |
| Outcome: | The proposed framework achieves comparable execution accuracy on SQL-Llama tasks compared to the baseline model. |
An Efficient Coarse-to-Fine Facet-Aware Unsupervised Summarization Framework Based on Semantic Blocks (2022.coling-1)
Copied to clipboard
| Challenge: | Existing unsupervised summarization methods fail to consider efficiency and effectiveness when the input document is extremely long. |
| Approach: | They propose an efficient Coarse-to-Fine Facet-Aware Ranking framework for unsupervised long document summarization based on the semantic block. |
| Outcome: | The proposed framework can achieve new state-of-the-art unsupervised summarization results on Gov-Report, billSum, arXiv, and PubMed. |
Multi-Modal Sarcasm Detection via Cross-Modal Graph Convolutional Network (2022.acl-long)
Copied to clipboard
| Challenge: | Existing studies on multimodal sarcasm detection using textual and visual information have been limited to text-only approaches. |
| Approach: | They propose to construct a cross-modal graph for each multi-modal instance to explicitly draw the ironic relations between textual and visual modalities. |
| Outcome: | The proposed model achieves state-of-the-art in multi-modal sarcasm detection. |
Free your mouse! Command Large Language Models to Generate Code to Format Word Documents (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent LLMs have significantly improved code generation, making it increasingly accessible to users. |
| Approach: | They propose an automatic document formatting method, Text-to-Format, driven by various prompting strategies and a high-quality dataset DocFormEval data. |
| Outcome: | The proposed method improves the efficiency and experience of users in formatting the document and improves document formatting task. |
Scaling Law for Multimodal Large Language Model Supervised Fine-Tuning (2026.acl-long)
Copied to clipboard
YiFan Zhang, Tao Yu, Feng Li, Chaoyou Fu, Yibo Hu, Kun Wang, Qingsong Wen, Zhang Zhang, Liang Wang, Rong Jin
| Challenge: | supervised fine-tuning (SFT) is crucial for multimodal large language models, yet a comprehensive scaling law is lacking . et al.: scaling laws focus on model size, pre-training tokens, and MLLM SFT data volumes . |
| Approach: | They propose two scaling laws to guide optimal model-data configuration . they propose one applicable when training data volumes are well defined by researchers . |
| Outcome: | The proposed scaling laws provide valuable recommendations for optimal resource allocation . they show that the proposed laws are more accurate than existing models . |
Multi-Perspective Context Aggregation for Semi-supervised Cloze-style Reading Comprehension (C18-1)
Copied to clipboard
| Challenge: | Recent studies have shown that cloze-style reading comprehension is a popular task for measuring the progress of natural language understanding. |
| Approach: | They propose a multi-perspective framework which can be seen as joint training of heterogeneous experts and aggregate context information from different perspectives. |
| Outcome: | The proposed framework achieves new state-of-the-art over previous strong baselines on a recently released cloze-test dataset. |
Open-ended Long Text Generation via Masked Language Modeling (2023.acl-long)
Copied to clipboard
| Challenge: | Pre-trained autoregressive language models have dominated OPen-ended Long Text Generation (Open-LTG) however, the low inference efficiency of AR impedes their usability. |
| Approach: | They propose a representative iterative non-autoregressive (NAR) decoding strategy to improve inference efficiency for Open-LTG. |
| Outcome: | The proposed model can generate short text and collapse for long text modeling. |
Mitigating Biases of Large Language Models in Stance Detection with Counterfactual Augmented Calibration (2025.naacl-long)
Copied to clipboard
Ang Li, Jingqian Zhao, Bin Liang, Lin Gui, Hui Wang, Xi Zeng, Xingwei Liang, Kam-Fai Wong, Ruifeng Xu
| Challenge: | Large language models generate biased stances due to spurious correlations and preference towards certain individuals and topics. |
| Approach: | They propose a counterfactual Augmented Calibration Network to calibrate potential bias in stance detection of large language models. |
| Outcome: | The proposed calibration network can mitigate biases of large language models, achieving state-of-the-art results. |
Generalizable and Stable Finetuning of Pretrained Language Models on Low-Resource Texts (2024.naacl-long)
Copied to clipboard
| Challenge: | Pretrained language models have advanced natural language processing tasks significantly, but finetuning them on low-resource datasets presents significant challenges such as instability and overfitting. |
| Approach: | They propose a regularization method based on attention-guided weight mixup for finetuning PLMs on low-resource datasets. |
| Outcome: | The proposed method improves generalization and combats overfitting on two splits of the training dataset. |
Large Margin Neural Language Model (D18-1)
Copied to clipboard
| Challenge: | Conventionally, neural language models are trained by minimizing perplexity (PPL) on grammatical sentences. |
| Approach: | They propose a large margin criterion for training neural language models by minimizing perplexity on grammatical sentences and propose enlarged margins for task-specific training. |
| Outcome: | The proposed method gains up to 1.1 WER reduction for speech recognition and 1.0 BLEU increase for machine translation. |
FuseSearch: Learning Adaptive Parallel Execution for Efficient Code Localization (2026.findings-acl)
Copied to clipboard
Ke Xu, Siyang Xiao, Ming Liang, Yichen Yu, Zhixiang Wang, Jingxuan Xu, Dajun Chen, Wei Jiang, Yong Li
| Challenge: | Existing parallel code localization agents suffer from a 34.9% redundant tool invocation rate . specialized localization agent that operate as dedicated search components is needed to achieve high localization accuracy. |
| Approach: | They propose a parallel code localization system that reframes parallel code execution as a quality–efficiency co-optimization problem. |
| Outcome: | The proposed method matches SOTA performance while being 93.6% faster. |
Enhancing Agentic Textual Graph Retrieval with Synthetic Stepwise Supervision (2026.acl-long)
Copied to clipboard
Ge Chang, Jinbo Su, Jiacheng Liu, Pengfei Yang, Yuhao Shang, Huiwen Zheng, Hongli Ma, Yan Liang, Yuanchun Li, Yunxin Liu
| Challenge: | Existing methods for integrating textual graphs with LLMs are limited by symbolic inference and high annotation costs. |
| Approach: | They propose a textual graph reasoning framework that integrates textual diagrams with large language models. |
| Outcome: | The proposed approach achieves 15.6% accuracy and 17.2% in F1 score on three common datasets. |