Papers by Wei Wang

Set Generation Networks for End-to-End Knowledge Base Population (2021.emnlp-main)

Challenge:	Existing benchmarks focus more on end-to-end performance, but neglect the underlying principles of knowledge acquisition and generalization.
Approach:	They propose a benchmark specifically designed to explore the problem-solving principles by decomposing 6.5K visual math problems into 10.9K step-level questions for evaluation.
Outcome:	The proposed benchmark covers 6.5K visual math problems and 10.9K step-level questions spanning 5 layers of knowledge granularity and 67 hierarchical knowledge concepts.

Copied to clipboard

Dianbo Sui, Chenhao Wang, Yubo Chen, Kang Liu, Jun Zhao, Wei Bi

Discovering Better Model Architectures for Medical Query Understanding (2021.naacl-industry)

Challenge:	Existing knowledge base population systems require a machine translation task to generate multiple facts, but the fact order is not considered.
Approach:	They propose a knowledge base population task that aims to discover facts about entities from texts and expand a KB with these facts.
Outcome:	The proposed networks achieve state-of-the-art (SoTA) performance on two benchmark datasets.

Copied to clipboard

Wei Zhu, Yuan Ni, Xiaoling Wang, Guotong Xie

Challenge:	Neural architecture search (NAS) has attracted intense attention in computer vision and NLP.
Approach:	They propose to use neural architecture search to optimize model architectures for medical questions . they propose to modify the ENAS method to accelerate and stabilize the search results .
Outcome:	The proposed approach outperforms baseline models on two medical questions . it is compared with other NAS methods and shows that it provides the best results .

Mask-then-Fill: A Flexible and Effective Data Augmentation Framework for Event Extraction (2022.findings-emnlp)

Copied to clipboard

Jun Gao, Changlong Yu, Wei Wang, Huan Zhao, Ruifeng Xu

Reinforcement Tuning for Detecting Stances and Debunking Rumors Jointly with Large Language Models (2024.findings-acl)

Challenge:	Existing data augmentation methods for event extraction are costly and time-consuming.
Approach:	They propose a data augmentation framework that randomly masks out an adjunct sentence fragment and infills a variable-length text span with a fine-tuned infilling model.
Outcome:	The proposed framework can generate more diverse data while keeping the original structure unchanged . it can replace a fragment of arbitrary length in the text with another fragment of variable length .

Copied to clipboard

Ruichao Yang, Wei Gao, Jing Ma, Hongzhan Lin, Bo Wang

A Survey of Large Language Models in Psychotherapy: Current Landscape and Future Directions (2025.findings-acl)

Challenge:	Social media has become a fertile ground for nurturing rumors and misinformation due to its lack of systematic moderation.
Approach:	They propose a framework to enhance the joint predictive capabilities of LLMs for stance detection and rumor verification tasks.
Outcome:	The proposed framework outperforms state-of-the-art methods and generalizes to non-LLMs accommodated as task models.

Copied to clipboard

Hongbin Na, Yining Hua, Zimu Wang, Tao Shen, Beibei Yu, Lilin Wang, Wei Wang, John Torous, Ling Chen

Harvesting and Refining Question-Answer Pairs for Unsupervised QA (2020.acl-main)

Challenge:	Large language models (LLMs) can handle extensive context and multi-turn reasoning.
Approach:	They propose a taxonomy dividing psychotherapy into stages of assessment, diagnosis, and treatment to examine LLM advancements and challenges.
Outcome:	The proposed taxonomy reveals imbalances in current research, such as a focus on common disorders, linguistic biases, fragmented methods, and limited theoretical integration.

Copied to clipboard

Zhongli Li, Wenhui Wang, Li Dong, Furu Wei, Ke Xu

Multi-Source Cross-Lingual Model Transfer: Learning What to Share (P19-1)

Challenge:	Recent research attempts to extend unsupervised question answering to settings with few or no labeled data available.
Approach:	They propose two approaches to improve unsupervised question answering . first, they harvest lexically and syntactically divergent Wikipedia questions to automatically construct a corpus of question-answer pairs . second, they take advantage of the QA model to extract more appropriate answers .
Outcome:	The proposed approach outperforms previous unsupervised approaches by a large margin and is competitive with early supervised models.

Copied to clipboard

Xilun Chen, Ahmed Hassan Awadallah, Hany Hassan, Wei Wang, Claire Cardie

Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning (2025.findings-acl)

Challenge:	Cross-lingual transfer learning (CLTL) is a viable method for building NLP models for a low-resource target language . however, many languages lack the labeled training data necessary for training deep neural nets for varying NLP tasks.
Approach:	They propose a cross-lingual transfer learning method that leverages annotated data from other languages to build NLP models for a target language.
Outcome:	The proposed model achieves significant performance gains over prior art over multiple text classification and sequence tagging tasks including a large-scale industry dataset.

Copied to clipboard

Huimin Xu, Xin Mao, Feng-Lin Li, Xiaobao Wu, Wang Chen, Wei Zhang, Anh Tuan Luu

Unsupervised Neural Machine Translation with Weight Sharing (P18-1)

Challenge:	Existing approaches to improve long-chain mathematical reasoning focus on the first erroneous step, but ignore all other steps and rely heavily on external signals.
Approach:	They propose a DPO framework that leverages step-wise rewards from the entire reasoning chain instead of optimizing only the first erroneous step.
Outcome:	The proposed framework improves on in-domain and out-of-domain mathematical reasoning benchmarks.

Copied to clipboard

Zhen Yang, Wei Chen, Feng Wang, Bo Xu

Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent Discovery (2022.emnlp-main)

Challenge:	Unsupervised neural machine translation (NMT) is a new approach for machine translation . the model uses only one shared encoder to map pairs of sentences from different languages to a shared-latent space .
Approach:	They propose an unsupervised approach which trains the model without labeling data . they propose two independent encoders but share some partial weights to extract high-level representations of input sentences.
Outcome:	The proposed approach achieves significant improvements on English-German, English-French and Chinese-to-English translation tasks.

Copied to clipboard

Yutao Mou, Keqing He, Pei Wang, Yanan Wu, Jingang Wang, Wei Wu, Weiran Xu

HAF-RM: A Hybrid Alignment Framework for Reward Model Training (2025.acl-long)

Challenge:	Existing methods for finding out-of-domain intents suffer from in-domain overfitting problem . previous methods fail to transfer prior knowledge to downstream clustering .
Approach:	They propose a unified K-nearest neighbor contrastive learning framework to discover OOD intents . they propose IND pre-training objective to learn discriminative features while maintaining intra-class diversity .
Outcome:	The proposed framework improves on three benchmark datasets.

Copied to clipboard

Shujun Liu, Xiaoyu Shen, Yuhang Lai, Siyuan Wang, Shengbin Yue, Zengfeng Huang, Xuanjing Huang, Zhongyu Wei

Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language Models (2025.acl-long)

Challenge:	Recent studies have focused on enhancing reward models through data improvements, following the conventional training framework for reward models that directly optimizes the predicted rewards.
Approach:	They propose a hybrid alignment framework HAF-RM that incorporates additional constraint on token-level policy probabilities in addition to the reward score.
Outcome:	The proposed framework can supervise the internal preference model at the token level and optimize the mapping layer of the reward model at sequence level.

Copied to clipboard

Xinlin Zhuang, Jiahui Peng, Ren Ma, Yinfan Wang, Tianyi Bai, Xingjian Wei, Qiu Jiantao, Chi Zhang, Ying Qian, Conghui He

Mixture of Diverse Size Experts (2024.emnlp-industry)

Challenge:	composition of pre-training datasets for large language models remains undisclosed . current methods for evaluating data quality are limited by single-dimensional evaluation or redundancy-focused strategies.
Approach:	They propose a multi-dimensional data selection method that integrates dimensions with existing quality metrics through learned optimal weightings.
Outcome:	The proposed method doubles convergence speed for 1.3B model models and improves downstream task performance by 3.23%.

Copied to clipboard

Manxi Sun, Wei Liu, Jian Luan, Pengzhi Gao, Bin Wang

Challenge:	Recent large language models (LLMs) have shown superior performance in a variety of tasks due to the sub-linearly increasing computational costs.
Approach:	They propose a new MoE architecture with designed layers where experts have different sizes to mitigate this defect.
Outcome:	The proposed architecture surpasses existing MoEs by adaptively assigning the parameter budget to experts while maintaining the same total parameter size and number of experts.

HiCoLoRA: Addressing Context-Prompt Misalignment via Hierarchical Collaborative LoRA for Zero-Shot DST (2026.findings-acl)

Copied to clipboard

Shuyu Zhang, Yifan Wei, Xinru Wang, Yanmin Zhu, Yangfan He, Yixuan Weng, Yujie Liu, Bin Li

Detecting Conversational Mental Manipulation with Intent-Aware Prompting (2025.coling-main)

Challenge:	Existing approaches to zero-shot Dialog State Tracking (zs-DST) are inadequate to generalize to new domains without extensive training.
Approach:	They propose a framework that enhances zero-shot slot inference through robust prompt alignment.
Outcome:	Experiments on multi-domain datasets show that HiCoLoRA outperforms baselines, achieving SOTA in zs-DST.

Copied to clipboard

Jiayuan Ma, Hongbin Na, Zimu Wang, Yining Hua, Yue Liu, Wei Wang, Ling Chen

MTA:A Merge-then-Adapt Framework for Personalized Large Language Models (2026.acl-long)

Challenge:	Existing approaches to detect mental manipulations are limited due to complexity of detecting subtle, covert tactics in conversations.
Approach:	They propose an approach to detect mental manipulations using large language models using intent-aware prompting by capturing the intents of participants.
Outcome:	The proposed approach significantly reduces false negatives, helping detect more instances of mental manipulation with minimal misjudgment of positive cases.

Copied to clipboard

Xiaopeng Li, Yuanjin Zheng, Wanyu Wang, Wenlin Zhang, Pengyue Jia, Yingyi Zhang, Haiying He, Mengyang Ma, Yiqi Wang, Maolin Wang, Xuetao Wei, Xiangyu Zhao

When Evolution Strategy Meets Language Models Tuning (2025.coling-main)

Challenge:	Personalized Large Language Models (PLLMs) aim to align outputs with individual user preferences . current methods of fine-tuning a separate module for each user are unscalable .
Approach:	They propose a Merge-then-Adapt framework for Personalized Large Language Models . they construct a shared Meta-LoRA bank and propose an Adaptive LoRA Fusion stage .
Outcome:	The proposed framework outperforms existing SOTA methods on the LaMP benchmark.

Copied to clipboard

Bo Huang, Yuxin Jiang, Mingyang Chen, Yi Wang, Hongyang Chen, Wei Wang

M3Seg: A Maximum-Minimum Mutual Information Paradigm for Unsupervised Topic Segmentation in ASR Transcripts (2023.emnlp-main)

Challenge:	Autoregressive language models with pretraining often display limited capability in effectively following instructions.
Approach:	They propose an on-policy approach to optimize models by harnessing the principle of biological evolution, namely survival of the fittest.
Outcome:	The proposed method can achieve superior performance in various tasks and comparable performance in the human alignment task.

Copied to clipboard

Ke Wang, Xiutian Zhao, Yanghui Li, Wei Peng

LightSeq: A High Performance Inference Library for Transformers (2021.naacl-industry)

Challenge:	Topic segmentation aims to split automatic speech recognition transcriptions into segments that are bounded by thematic meanings.
Approach:	They propose a Maximum-Minimum Mutual information paradigm for linear topic segmentation without using any parallel data.
Outcome:	The proposed paradigm outperforms the state-of-the-art methods by a significant margin.

Copied to clipboard

Xiaohui Wang, Ying Xiong, Yang Wei, Mingxuan Wang, Lei Li

RE-Matching: A Fine-Grained Semantic Matching Method for Zero-Shot Relation Extraction (2023.acl-long)

Challenge:	Existing inference frameworks for natural language processing are not the best choice for online service of sequence processing problems.
Approach:	They propose a highly efficient inference library for Transformer models that includes GPU optimization techniques to streamline computation and reduce memory footprint.
Outcome:	The proposed library achieves 14x speedup compared with TensorFlow and 1.4x speed up compared to a concurrent CUDA implementation.

Copied to clipboard

Jun Zhao, WenYu Zhan, Xin Zhao, Qi Zhang, Tao Gui, Zhongyu Wei, Junzhe Wang, Minlong Peng, Mingming Sun

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

Challenge:	Existing methods for zero-shot relation extraction lack explicit modeling of matching pattern . et al. (2018) show that our method achieves higher matching accuracy and faster inference speed .
Approach:	They propose a fine-grained semantic matching method tailored for zero-shot relation extraction . they decompose sentence-level similarity score into entity matching score and context matching score .
Outcome:	The proposed method achieves higher matching accuracy and faster inference speed than state-of-the-art methods.

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

ESGenius: Benchmarking LLMs on Environmental, Social, and Governance (ESG) and Sustainability Knowledge (2025.emnlp-main)

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

Copied to clipboard

Chaoyue He, Xin Zhou, Yi Wu, Xinjia Yu, Yan Zhang, Lei Zhang, Di Wang, Shengfei Lyu, Hong Xu, Wang Xiaoqiao, Wei Liu, Chunyan Miao

UnifiedMLLM: Enabling Unified Representation for Multi-modal Multi-tasks With Large Language Model (2025.findings-naacl)

Challenge:	ESGenius is a comprehensive benchmark for evaluating Large Language Models on ESG and sustainability knowledge.
Approach:	They introduce ESGenius, a benchmark for evaluating and enhancing ESG proficiency . they use a rigorous two-stage evaluation protocol and a repository of foundational frameworks .
Outcome:	ESGenius is a benchmark for evaluating and enhancing the proficiency of Large Language Models (LLMs) in ESG and sustainability-focused question answering.

Copied to clipboard

Zhaowei Li, Wei Wang, YiQing Cai, Qi Xu, Pengyu Wang, Dong Zhang, Hang Song, Botian Jiang, Zhida Huang, Tao Wang

Beyond the Textual: Generating Coherent Visual Options for MCQs (2025.findings-emnlp)

Challenge:	Representative models like LLaVA and MiniGPT-4 have great capabilities in various tasks.
Approach:	They propose a unified model to represent various multi-modal tasks using a single representation.
Outcome:	The proposed model outperforms existing models in a variety of tasks while maintaining generality and scalability.

Copied to clipboard

Wanqiang Wang, Longzhu He, Wei Zheng

USB: A COMPREHENSIVE AND UNIFIED SAFETY EVALUATION BENCHMARK FOR MULTIMODAL LARGE LANGUAGE MODELS (2026.acl-long)

Challenge:	Multiple choice questions (MCQs) are crucial for deep thinking and knowledge integration in education.
Approach:	They propose a cross-modal options synthesis framework for generating MCQs with visual options.
Outcome:	The proposed framework produces a plausible and visually similar answer and distractor . it also includes a discrimination module to identify content suitable for visual options .

Copied to clipboard

Baolin Zheng, Guanlin Chen, Qingyang Teng, Hongqiong Zhong, Yingshui Tan, Zhendong Liu, Weixun Wang, Jiaheng Liu, Jian Yang, Huiyun Jing, Jincheng Wei, Wenbo Su, Xiaoyong Zhu, Bo Zheng, Kaifu Zhang

Mirroring Users: Towards Building Preference-aligned User Simulator with User Feedback in Recommendation (2026.acl-long)

Challenge:	Existing safety benchmarks fail to provide reliable assessments due to limited risk coverage, insufficient scale and the oversight of complex modality combinations.
Approach:	They propose a framework that covers 61 risk categories across four modality interactions to address this gap.
Outcome:	The proposed framework covers 61 risk categories across four distinct modality interactions.

Copied to clipboard

Tianjun Wei, Huizhong Guo, Yingpeng Du, Zhu Sun, Huang Chen, Dongxia Wang, Jie Zhang

LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing (2024.emnlp-main)

Challenge:	Large Language Models lack specific task alignment and large-scale simulations are challenging due to their ambiguity, noise and massive volume.
Approach:	They propose a framework that leverages user feedback in RSs with advanced LLM capabilities to generate high-quality simulation data.
Outcome:	The proposed framework boosts the alignment with human preferences and in-domain reasoning capabilities of the fine-tuned LLMs.

Copied to clipboard

Jiangshu Du, Yibo Wang, Wenting Zhao, Zhongfen Deng, Shuaiqi Liu, Renze Lou, Henry Zou, Pranav Narayanan Venkit, Nan Zhang, Mukund Srinath, Haoran Zhang, Vipul Gupta, Yinghui Li, Tao Li, Fei Wang, Qin Liu, Tianlin Liu, Pengzhi Gao, Congying Xia, Chen Xing, Cheng Jiayang, Zhaowei Wang, Ying Su, Raj Shah, Ruohao Guo, Jing Gu, Haoran Li, Kangda Wei, Zihao Wang, Lu Cheng, Surangika Ranathunga, Meng Fang, Jie Fu, Fei Liu, Ruihong Huang, Eduardo Blanco, Yixin Cao, Rui Zhang, Philip Yu, Wenpeng Yin

Challenge:	a comparative analysis of paper (meta-)reviews by large language models (LLMs) aims to identify and distinguish LLMs from human activities .
Approach:	They present a comparative analysis to identify and distinguish LLM activities from human activities.
Outcome:	The proposed analysis aims to improve recognition of instances when someone implicitly uses LLMs for reviewing activities.

Learning from Mistakes: Negative Reasoning Samples Enhance Out-of-Domain Generalization (2026.acl-long)

Copied to clipboard

Tian Xueyun, MingHua Ma, Bingbing Xu, Nuoyan Lyu, Wei Li, Heng Dong, Zheng Chu, Yuanzhuo Wang, Huawei Shen

Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs (2021.acl-long)

Challenge:	Recent studies show that supervised fine-tuning (SFT) is a common approach for reasoning in large language models.
Approach:	They propose to use supervised fine-tuning (SFT) on chain-of-thought trajectories demonstrations . they find that incorporating negative traxories yields substantial OOD generalization gains .
Outcome:	The proposed scheme yields 5.51% OOD gain over positive-only training.

Copied to clipboard

Zixuan Li, Xiaolong Jin, Saiping Guan, Wei Li, Jiafeng Guo, Yuanzhuo Wang, Xueqi Cheng

Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification (2022.acl-long)

Challenge:	Temporal Knowledge Graphs (TKGs) are used in many different areas of research.
Approach:	They propose to use a beam search policy to induce multiple clues from historical facts . they propose to adopt a graph convolution network based sequence method to deduce answers from clues .
Outcome:	The proposed model can predict future facts in two stages, Clue Searching and Temporal Reasoning.

Copied to clipboard

Shengding Hu, Ning Ding, Huadong Wang, Zhiyuan Liu, Jingang Wang, Juanzi Li, Wei Wu, Maosong Sun

Detoxifying Large Language Models via the Diversity of Toxic Samples (2025.emnlp-main)

Challenge:	Recent studies suggest that pre-trained language models have gained rich knowledge during pre-training.
Approach:	They propose to tune pre-trained language models with task-specific prompts to improve and stabilize prompttuning.
Outcome:	Extensive experiments on zero and few-shot text classification tasks show that prompt-tuning improves and stabilizes prompttun-ing.

Copied to clipboard

Ying Zhao, Yuanzhao Guo, Xuemeng Weng, Yuan Tian, Wei Wang, Yi Chang

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

Challenge:	Existing methods for analyzing and utilizing toxic samples are limited . current methods fail to fully harness their potential .
Approach:	They propose a diverse detoxification framework that leverages toxic samples' diversity . they propose MPSG strategy and SC-DPO approach to elicit personalized toxic responses .
Outcome:	The proposed framework could be used to optimize large language models for user safety . it incorporates two components: MPSG strategy and SC-DPO approach .

Copied to clipboard

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

CPT-Agent: A Cognitive Process Theory-driven Framework for Student Simulation in Writing Development (2026.acl-long)

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

Copied to clipboard

Yuhan Chen, Zizhuo Shen, Miaomiao Cheng, Xu Han, Jiefu Gong, Shijin Wang, Wei Song

Linguistics & Cognitive NLP

Challenge:	Existing LLMs model overly capable learners who over-apply feedback, resulting in pedagogically implausible behavior.
Approach:	They propose a framework that decouples cognitive ability from writing proficiency and models their interaction during writing and revision.
Outcome:	The proposed model produces distinguishable proficiency levels and is consistent with instructional theories.

Adaptive Policy with Wait-k Model for Simultaneous Translation (2023.emnlp-main)

Copied to clipboard

Libo Zhao, Kai Fan, Wei Luo, Wu Jing, Shushu Wang, Ziqian Zeng, Zhongqiang Huang

What Makes AI Research Replicable? Executable Knowledge Graphs as Scientific Knowledge Representations (2026.acl-short)

Challenge:	Existing approaches to simultaneous machine translation require a robust read/write policy . a standalone multi-path wait-k model performs competitively with adaptive policies .
Approach:	They propose a more flexible approach by decoupling the adaptive policy model from the translation model.
Outcome:	The proposed approach outperforms baseline approaches in translation tasks.

Copied to clipboard

Yujie Luo, Zhuoyun Yu, Xuehai Wang, Yuqi Zhu, Ningyu Zhang, Lanning Wei, Lun Du, Da Zheng, Huajun Chen

AROMA: Augmented Reasoning Over a Multimodal Architecture for Virtual Cell Genetic Perturbation Modeling (2026.findings-acl)

Challenge:	Existing approaches to replicate AI research are limited by insufficient background knowledge and the limitations of retrieval-augmented generation methods.
Approach:	They propose a pluggable, paper-centric knowledge base that integrates code snippets and technical insights extracted from scientific literature into a verifiable, executable representation.
Outcome:	The proposed knowledge base shows significant performance gains on paperBench when integrated into three agent frameworks with two different LLMs.

Copied to clipboard

Wang Zhenyu, Geyan Ye, Wei Liu, Man Tat Alexander Ng

v-HUB: A Benchmark for Video Humor Understanding from Vision and Sound (2026.acl-long)

Challenge:	Existing methods for virtual cell genetic perturbation modeling suffer from unconstrained reasoning, uninterpretable predictions, and retrieval signals that are weakly aligned with regulatory topology.
Approach:	They propose an Augmented Reasoning Over a Multimodal Architecture for virtual cell genetic perturbation modeling.
Outcome:	The proposed model outperforms existing methods across multiple cell lines and remains robust under zero-shot evaluation on unseen cells.

Copied to clipboard

Zhengpeng Shi, Yanpeng Zhao, Jianqun Zhou, Yuxuan Wang, Qinrong Cui, Wei Bi, Song-Chun Zhu, Bo Zhao, Zilong Zheng

Enhancing Self-Attention with Knowledge-Assisted Attention Maps (2022.naacl-main)

Challenge:	Humor enriches our daily lives and appears in many forms, from jokes and cartoons to comedies and viral videos.
Approach:	They introduce a video humor understanding benchmark to test their ability to understand humor from visual cues.
Outcome:	The proposed video humor understanding benchmark is based on a collection of short videos . it features rich annotations and a study of environmental sound that can enhance humor .

Copied to clipboard

Jiangang Bai, Yujing Wang, Hong Sun, Ruonan Wu, Tianmeng Yang, Pengfei Tang, Defu Cao, Mingliang Zhang1, Yunhai Tong, Yaming Yang, Jing Bai, Ruofei Zhang, Hao Sun, Wei Shen

Encode Errors: Representational Retrieval of In-Context Demonstrations for Multilingual Grammatical Error Correction (2025.findings-acl)

Challenge:	Existing works of knowledge infusion depend on multi-task learning frameworks, which are inefficient and require large-scale retraining when new knowledge is considered.
Approach:	They propose a method which integrates knowledge-generated attention maps into the self-attention mechanism and integrates it into the model.
Outcome:	The proposed model outperforms existing methods on academic datasets and industry-scale ad relevance applications.

Copied to clipboard

Guangyue Peng, Wei Li, Wen Luo, Houfeng Wang

Capturing Event Argument Interaction via A Bi-Directional Entity-Level Recurrent Decoder (2021.acl-long)

Challenge:	a novel method for encoding fine-grained error patterns improves performance on GEC.
Approach:	They propose a method for encoding grammatical errors from LLMs' internal states using a GER method.
Outcome:	The proposed method significantly boosts performance in ICL settings on multilingual GEC datasets.

Copied to clipboard

Xi Xiangyu, Wei Ye, Shikun Zhang, Quanxiu Wang, Huixing Jiang, Wei Wu

Beyond Token Length: Step Pruner for Efficient and Accurate Reasoning in Large Language Models (2026.findings-acl)

Challenge:	Existing efforts to capture event argument interactions are limited by the argument role type information of contextual entities.
Approach:	They propose to capture event argument interactions as a Seq2Seq-like learning problem where a sentence with a specific event trigger is mapped to a sequence of event argument roles.
Outcome:	The proposed neural architecture generates argument roles by incorporating contextual entities’ argument role predictions, like a word-by-word text generation process, thereby distinguishing implicit argument distribution patterns within an event more accurately.

Copied to clipboard

Canhui Wu, Qiong Cao, Chang Li, Zhenfang Wang, Chao Xue, Yuwei Fan, Wei Xi, Xiaodong He

Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models (2024.findings-emnlp)

Challenge:	Existing reinforcement learning methods for large reasoning models suffer from excessive verbosity, known as "overthinking." Existing models penalize generated tokens to promote conciseness, but these methods encounter two challenges: they may develop hacking behavior in later stages of training by discarding reasoning steps.
Approach:	They propose a framework that steers large reasoning models toward more efficient reasoning . they prioritize correctness while imposing penalties for redundant steps .
Outcome:	The proposed framework reduces token usage by 69.7% on AIME24.

Copied to clipboard

Kai Yao, Penglei Gao, Lichun Li, Yuan Zhao, Xiaofeng Wang, Wei Wang, Jianke Zhu

Distilled Dual-Encoder Model for Vision-Language Understanding (2022.emnlp-main)

Challenge:	Parameter-Efficient Fine-Tuning (PEFT) methods have gained popularity for adapting pre-trained Large Language Models (LLMs) to downstream tasks.
Approach:	They propose a method to optimize the importance of full layers with layer-wise importance scoring by leveraging the estimated importance scores.
Outcome:	The proposed method is compatible with PEFT methods that operate on a per-layer basis and achieves better performance.

Copied to clipboard

Zekun Wang, Wenhui Wang, Haichao Zhu, Ming Liu, Bing Qin, Furu Wei

Rethinking Smoothness for Fast and Adaptable Entity Alignment Decoding (2025.findings-naacl)

Challenge:	Experimental results show that the proposed cross-modal attention distillation is crucial to the success of our framework.
Approach:	They propose a framework that distills knowledge of fusion-encoder teacher into dual-encoding student model.
Outcome:	The proposed model is competitive with the fusion-encoder teacher model in performance, but suffers from a lack of deep cross-modal interactions.

Copied to clipboard

Yuanyi Wang, Han Li, Haifeng Sun, Lei Zhang, Bo He, Wei Tang, Tianhao Yan, Qi Qi, Jingyu Wang

IFlyEA: A Chinese Essay Assessment System with Automated Rating, Review Generation, and Recommendation (2021.acl-demo)

Challenge:	Existing methods for integrating knowledge graphs rely on entity and relation embeddings . Fig. 1 shows how to decode knowledge graph in under 6 seconds .
Approach:	They propose a framework that only utilizes entity embeddings to decode knowledge graphs.
Outcome:	The proposed framework reconstructs KG representation by maximizing smoothness of entity embeddings.

Copied to clipboard

Jiefu Gong, Xiao Hu, Wei Song, Ruiji Fu, Zhichao Sheng, Bo Zhu, Shijin Wang, Ting Liu

LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin (2024.acl-long)

Challenge:	Automated Essay Assessment (AEA) aims to judge students’ writing proficiency in an automatic way.
Approach:	They propose to use Chinese AEA system IFlyEssayAssess to evaluate essays written by native Chinese students from primary and junior schools.
Outcome:	The proposed system provides application services for essay scoring, review generation, recommendation, and explainable analytical visualization.

Copied to clipboard

Shihan Dou, Enyu Zhou, Yan Liu, Songyang Gao, Wei Shen, Limao Xiong, Yuhao Zhou, Xiao Wang, Zhiheng Xi, Xiaoran Fan, Shiliang Pu, Jiang Zhu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang

Zero-Shot Cross-Lingual Transfer of Neural Machine Translation with Multilingual Pretrained Encoders (2021.emnlp-main)

Challenge:	Experimental results show that, as the instruction data increases, LoRAMoE can significantly improve the ability to process downstream tasks, while maintaining the world knowledge stored in the LLM.
Approach:	They propose a framework that introduces several low-rank adapters and integrates them by using a router network to freeze the backbone model and force a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks.
Outcome:	The proposed framework freezes the backbone model and forces a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks, to alleviate world knowledge forgetting.

Copied to clipboard

Guanhua Chen, Shuming Ma, Yun Chen, Li Dong, Dongdong Zhang, Jia Pan, Wenping Wang, Furu Wei

GAML-BERT: Improving BERT Early Exiting by Gradient Aligned Mutual Learning (2021.emnlp-main)

Challenge:	Existing work on improving cross-lingual transferability of NMT model is under-explored.
Approach:	They propose a model that leverages a multilingual pretrained encoder to improve cross-lingual transferability.
Outcome:	The proposed model outperforms mBART and m2m-100 on a zero-shot cross-lingual transfer task.

Copied to clipboard

Wei Zhu, Xiaoling Wang, Yuan Ni, Guotong Xie

Detection-Correction Structure via General Language Model for Grammatical Error Correction (2024.acl-long)

Challenge:	Existing approaches to improve the early exiting of natural language processing (NLP) are notoriously gigantic and slow in both training and inference.
Approach:	They propose a framework for improving the early exiting of BERT by asking each exit to distill knowledge from each other.
Outcome:	The proposed framework outperforms the state-of-the-art (SOTA) BERT early exiting methods on the GLUE benchmark.

Copied to clipboard

Wei Li, Houfeng Wang

Towards Fast and Accurate Neural Chinese Word Segmentation with Multi-Criteria Learning (2020.coling-main)

Challenge:	Grammatical error correction (GEC) is a task dedicated to rectifying texts with minimal edits.
Approach:	They propose a detection-correction structure based on the general language model which integrates detection and correction into a single model.
Outcome:	The proposed model outperforms the state-of-the-art models on English and Chinese datasets.

Copied to clipboard

Weipeng Huang, Xingyi Cheng, Kunlong Chen, Taifeng Wang, Wei Chu

Personalized Microblog Sentiment Classification via Adversarial Cross-lingual Multi-task Learning (D18-1)

Challenge:	Chinese word segmentation datasets have ambiguous annotation criteria resulting in multi-grained compounds.
Approach:	They propose a domain adaptive segmenter to exploit diverse annotation criteria of datasets . they use bidirectional encoder representations from transformers to introduce open-domain knowledge .
Outcome:	The proposed model outperforms the state-of-the-art models on 10 Chinese word datasets with superior efficiency.

Copied to clipboard

Weichao Wang, Shi Feng, Wei Gao, Daling Wang, Yifei Zhang

Explanation based In-Context Demonstrations Retrieval for Multilingual Grammatical Error Correction (2025.naacl-long)

Challenge:	Existing personalized microblog sentiment classification methods suffer from the insufficiency of discriminative tweets for personalization learning.
Approach:	They propose to use user-attention-based Convolutional Neural Networks to capture individuality and opinion bias in microblog posts and a novel adversarial cross-lingual learning framework to enrich the user post representation.
Outcome:	The proposed method outperforms state-of-the-art baseline algorithms with large margins on English and Chinese microblog datasets.

Copied to clipboard

Wei Li, Wen Luo, Guangyue Peng, Houfeng Wang

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

Challenge:	Grammatical error correction (GEC) aims to correct grammatical, spelling, and semantic errors in natural language text.
Approach:	They propose a retrieval method based on natural language grammatical error explanations to match inputs with pre-constructed databases where explanations for erroneous samples are generated by LLMs.
Outcome:	The proposed method outperforms existing semantic and BM25-based retrieval techniques without additional training or language adaptation.

Copied to clipboard

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

GL-GAN: Perceiving and Integrating Global and Local Styles for Handwritten Text Generation with Mamba (2025.coling-main)

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

Copied to clipboard

Yiming Wang, Hongxi Wei, Heng Wang, Shiwen Sun, Chao He

Mitigating Bias for Question Answering Models by Tracking Bias Influence (2024.naacl-long)

Challenge:	Existing models lack the ability to perceive and integrate handwriting styles, which affects the realism of the synthesized samples.
Approach:	They propose a Hybrid Style Encoder that captures global and local styles and integrates them into a Dynamic Feature Enhancement Module (DFEM).
Outcome:	The proposed model outperforms state-of-the-art models on two widely used handwriting datasets and can provide training data for handwritten text recognition and signature verification.

Copied to clipboard

Mingyu Ma, Jiun-Yu Kao, Arpit Gupta, Yu-Hsiang Lin, Wenbo Zhao, Tagyoung Chung, Wei Wang, Kai-Wei Chang, Nanyun Peng

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

Challenge:	Existing literature observes bias in question answering (QA) models, but there is no method to mitigate it.
Approach:	They propose an approach to mitigate the bias of question answering models by observing the influence of a query instance on another instance.
Outcome:	The proposed method reduces bias level in all 9 bias categories while maintaining comparable QA accuracy.

Copied to clipboard

Liang Chao, Wei Xiang, Bang Wang

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

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

Copied to clipboard

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

OpenHuEval: Evaluating Large Language Model on Hungarian Specifics (2025.findings-acl)

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

Copied to clipboard

Haote Yang, Xingjian Wei, Jiang Wu, Noémi Ligeti-Nagy, Jiaxing Sun, Yinfan Wang, Győző Zijian Yang, Junyuan Gao, Jingchao Wang, Bowen Jiang, Shasha Wang, Nanjun Yu, Zihao Zhang, Shixin Hong, Hongwei Liu, Wei Li, Songyang Zhang, Dahua Lin, Lijun Wu, Gábor Prószéky, Conghui He

Context-DPO: Aligning Language Models for Context-Faithfulness (2025.findings-acl)

Challenge:	Recent advances in Large Language Models (LLMs) represent significant strides toward artificial general intelligence (AGI).
Approach:	They introduce OpenHuEval, the first benchmark for LLMs focusing on the Hungarian language and specifics.
Outcome:	The framework reveals intrinsic patterns and mechanisms of LLMs in non-English languages, with Hungarian serving as an example.

Copied to clipboard

Baolong Bi, Shaohan Huang, Yiwei Wang, Tianchi Yang, Zihan Zhang, Haizhen Huang, Lingrui Mei, Junfeng Fang, Zehao Li, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang, Shenghua Liu

AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories (2024.findings-emnlp)

Challenge:	Context-DPO is the first alignment method specifically designed to enhance contextfaithfulness for large language models.
Approach:	They propose a benchmark that simulates Retrieval-Augmented Generation scenarios with knowledge conflicts to evaluate context-faithfulness.
Outcome:	The proposed method improves LLMs' context-faithfulness by 35% to 280% over open-source models.

Copied to clipboard

Yifan Song, Weimin Xiong, Xiutian Zhao, Dawei Zhu, Wenhao Wu, Ke Wang, Cheng Li, Wei Peng, Sujian Li

Mixture of Ordered Scoring Experts for Cross-prompt Essay Trait Scoring (2025.acl-long)

Challenge:	Existing studies focus on specialized agents designed for particular tasks.
Approach:	They propose to scale annotated interaction trajectories and fine-tune LLMs on AgentBank to get a series of agent models, Samoyed.
Outcome:	The proposed model can scale to get generalized agent capabilities.

Copied to clipboard

Po-Kai Chen, Bo-Wei Tsai, Shao Kuan Wei, Chien-Yao Wang, Jia-Ching Wang, Yi-Ting Huang

Revealing COVID-19’s Social Dynamics: Diachronic Semantic Analysis of Vaccine and Symptom Discourse on Twitter (2024.findings-emnlp)

Challenge:	Existing approaches to automate essay scoring overlook critical information, authors say . evaluators often limit their performance to unseen topics, resulting in incomplete assessment perspectives.
Approach:	They propose a framework that integrates information from prompts and essays into an AES framework.
Outcome:	The proposed framework achieves state-of-the-art in cross-prompt scoring and multi-trait scoring on the ASAP++ dataset.

Copied to clipboard

Zeqiang Wang, Jiageng Wu, Yuqi Wang, Wei Xjtlu, Jie Yang, Nishanth Sastry, Jon Johnson, Suparna De

BSFA: Leveraging the Subspace Dichotomy to Accelerate Neural Network Training (2025.emnlp-main)

Challenge:	Social media data provide a new source for social science and cultural analysis research, but its analysis is challenging due to the semantic shift phenomenon, where word meanings evolve over time.
Approach:	They propose an unsupervised dynamic word embedding method to capture longitudinal semantic shifts in social media data without predefined anchor words.
Outcome:	The proposed method captures longitudinal semantic shifts in social media data without predefined anchor words and leverages word co-occurrence statistics and dynamic updating to adapt embeddings over time.

Copied to clipboard

WenJie Zhou, Bohan Wang, Wei Chen, Xueqi Cheng

MAKAR: a Multi-Agent framework based Knowledge-Augmented Reasoning for Grounded Multimodal Named Entity Recognition (2025.emnlp-main)

Challenge:	Recent studies highlight a fundamental dichotomy in deep learning optimization: parameter updates along the top eigendirections of the loss Hessian (Dom-space) capture most of the update magnitude, while updates in the orthogonal component (Bulk-space), have smaller magnitudes but drive most learning progress.
Approach:	They propose a plug-and-play framework that scales update components projected onto distinct subspaces and a block-wise strategy that applies this estimation on a per-parameter-block basis.
Outcome:	The proposed framework accelerates training by differentially scaling update components projected onto distinct subspaces, while enhancing stability by moderating updates in dominant subspace and boosting convergence speed by amplifying updates in bulk-space.

Copied to clipboard

Xinkui Lin, Yuhui Zhang, Yongxiu Xu, Kun Huang, Hongzhang Mu, Yubin Wang, Gaopeng Gou, Li Qian, Li Peng, Wei Liu, Jian Luan, Hongbo Xu

ShifCon: Enhancing Non-Dominant Language Capabilities with a Shift-based Multilingual Contrastive Framework (2025.acl-long)

Challenge:	Existing methods for GMNER fail to address semantic ambiguity caused by polysemy and long-tail distribution of datasets.
Approach:	They propose a framework for Grounded Multimodal Named Entity Recognition that leverages a Multimodal Large Language Model to address semantic ambiguity.
Outcome:	Extensive experiments show that the proposed framework outperforms existing methods on two benchmark datasets.

Copied to clipboard

Hengyuan Zhang, Chenming Shang, Sizhe Wang, Dongdong Zhang, Yiyao Yu, Feng Yao, Renliang Sun, Yujiu Yang, Furu Wei

MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction (2022.findings-acl)

Challenge:	Experiments show that ShifCon significantly enhances the performance of non-dominant languages due to the imbalance in training data across languages.
Approach:	They propose a Shift-based multilingual Contrastive framework that aligns the internal forward process of other languages toward that of the dominant one.
Outcome:	The proposed framework significantly improves performance of non-dominant languages, particularly for low-resource ones.

Copied to clipboard

Linhan Zhang, Qian Chen, Wen Wang, Chong Deng, ShiLiang Zhang, Bing Li, Wei Wang, Xin Cao

Mitigating Catastrophic Forgetting in Large Language Models with Forgetting-aware Pruning (2025.emnlp-main)

Challenge:	Keyphrase extraction (KPE) extracts phrases in a document that provide a concise summary of the core content.
Approach:	They propose an unsupervised keyphrase extraction method that ranks candidates by similarity between embeddings of source document and masked document.
Outcome:	The proposed method outperforms state-of-the-art methods on six benchmarks . it achieves average 3.53 improvement over the existing method .

Copied to clipboard

Wei Huang, Anda Cheng, Yinggui Wang

Retrieval-guided Dialogue Response Generation via a Matching-to-Generation Framework (D19-1)

Challenge:	Recent advances in large language models (LLMs) have shown impressive capabilities in various downstream tasks but typically face Catastrophic Forgetting (CF) during fine-tuning.
Approach:	They propose a pruning-based approach to balance CF and downstream task performance by integrating the ratio of the task vector to pre-trained model parameters into the pruning criteria.
Outcome:	The proposed pruning-based approach limits CF to just 0.25% while maintaining 99.67% accuracy on downstream tasks.

Copied to clipboard

Deng Cai, Yan Wang, Wei Bi, Zhaopeng Tu, Xiaojiang Liu, Shuming Shi

Hypoformer: Hybrid Decomposition Transformer for Edge-friendly Neural Machine Translation (2022.emnlp-main)

Challenge:	generative models for end-to-end sequence generation have been shown promising for this task . however, how to precisely extract a skeleton and how to effectively train a retrieval-guided response generator is still challenging.
Approach:	They propose a framework where skeleton extraction is made by an interpretable matching model and a retrieval-guided response generator is followed by a separate generator.
Outcome:	The proposed framework outperforms baseline models in a variety of experiments.

Copied to clipboard

Sunzhu Li, Peng Zhang, Guobing Gan, Xiuqing Lv, Benyou Wang, Junqiu Wei, Xin Jiang

Enhancing Retrieval-Augmented Generation via Evidence Tree Search (2025.acl-long)

Challenge:	Existing methods to compress Transformer are limited to sub-components, e.g., selfattention networks or embedding layer.
Approach:	They propose a Hybrid Tensor-Train decomposition which retains full rank and meanwhile reduces operations and parameters.
Outcome:	The proposed model outperforms light-weight SOTA methods on three translation tasks and achieves 7.1 points absolute improvement in BLEU and 1.27 X speedup on IWSLT’14 De-En task.

Copied to clipboard

Hao Sun, Hengyi Cai, Yuchen Li, Xuanbo Fan, Xiaochi Wei, Shuaiqiang Wang, Yan Zhang, Dawei Yin

WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning (2026.acl-long)

Challenge:	Evidence retrieval is used to enhance Large Language Models (LLMs) but in real-world applications, it often returns lengthy documents with redundant or irrelevant content, confusing downstream readers.
Approach:	They propose a framework that reformulates evidence retrieval as a dynamic tree expansion process.
Outcome:	The proposed framework outperforms existing methods on five datasets.

Copied to clipboard

Junjie Wang, Zequn Xie, Dan Yang, Jie Feng, Yue Shen, Duolin Sun, Meixiu Long, Yihan Jiao, Zhehao Tan, Jian Wang, Peng Wei, Jinjie Gu

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

Challenge:	Open-source web agents rely on long tool-call trajectories with cyclic reasoning loops and exploration of unproductive branches.
Approach:	They propose a framework that compresses web agent trajectories via graph-based pruning.
Outcome:	The proposed framework reduces tool-call rounds by 20% while improving accuracy and efficiency while maintaining the same level of performance as existing models.

Copied to clipboard

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

ALaRM: Align Language Models via Hierarchical Rewards Modeling (2024.findings-acl)

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

Copied to clipboard

Yuhang Lai, Siyuan Wang, Shujun Liu, Xuanjing Huang, Zhongyu Wei

IterAlign: Iterative Constitutional Alignment of Large Language Models (2024.naacl-long)

Challenge:	Current alignment approaches struggle with inconsistency and sparsity of human supervision signals.
Approach:	They propose a framework modeling hierarchical rewards in reinforcement learning from human feedback (RLHF) it integrates holistic rewards with aspect-specific rewards to enhance alignment of large language models with human preferences.
Outcome:	The proposed framework improves the alignment of large language models with human preferences by integrating holistic rewards with aspect-specific rewards.

Copied to clipboard

Xiusi Chen, Hongzhi Wen, Sreyashi Nag, Chen Luo, Qingyu Yin, Ruirui Li, Zheng Li, Wei Wang

LoopCoder: Scaling Code Intelligence via Looped Language Models (2026.findings-acl)

Challenge:	Empirical results show that iterAlign improves truthfulness, helpfulness, harmlessness and honesty, improving the LLM alignment by up to 13.5% in harmlessness.
Approach:	They propose a data-driven constitution discovery and self-alignment framework called IterAlign to overcome these drawbacks by leveraging red teaming to uncover weaknesses of an LLM.
Outcome:	Empirical results show that iterAlign improves truthfulness, helpfulness, harmlessness and honesty by up to 13.5%.

Copied to clipboard

Jian Yang, Wei Zhang, Shuyue Guo, Yizhi LI, Linzheng Chai, Zhengmao Ye, Shukai Liu, Yuyang Song, Jiajun Wu, Che Liu, Tianyu Zheng, Siwei Wu, Leo L, Xudong Ma, Chuan Hao, Ran Tao, Yan Xing, Jianzhou Wang, Mingjie Tang, Aishan Liu, Zhoujun Li, Xianglong Liu, Weifeng Lv, Bryan Dai

Turning the Tide: Repository-based Code Reflection (2025.findings-emnlp)

Challenge:	Large language models have mastered syntax-level code generation, but complex algorithmic reasoning remains a challenge.
Approach:	They propose a recurrent inductive bias that aligns with the recursive nature of programming logic.
Outcome:	The proposed model achieves comparable performance to standard dense models with more parameters.

Copied to clipboard

Wei Zhang, Jian Yang, Jiaxi Yang, Ya Wang, Zhoujun Li, Zeyu Cui, Binyuan Hui, Junyang Lin

A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery (2024.emnlp-main)

Challenge:	Code large language models (LLMs) enhance programming by understanding and generating code across languages.
Approach:	a new benchmark evaluates code understanding and generation in repositories using code large language models.
Outcome:	The proposed model improves code understanding and generation in repositories by evaluating 1,888 test cases across 6 programming languages.

Copied to clipboard

Yu Zhang, Xiusi Chen, Bowen Jin, Sheng Wang, Shuiwang Ji, Wei Wang, Jiawei Han

TRAMS: Training-free Memory Selection for Long-range Language Modeling (2023.findings-emnlp)

Challenge:	Existing surveys on scientific LLMs focus on one or two fields or a single modality.
Approach:	They survey 260 scientific LLMs and examine their architectures and pre-training techniques . they also discuss commonalities and differences between LLM architectures .
Outcome:	The proposed model architectures and evaluation techniques are used to improve scientific discovery.

Copied to clipboard

Haofei Yu, Cunxiang Wang, Yue Zhang, Wei Bi

Unified Demonstration Retriever for In-Context Learning (2023.acl-long)

Challenge:	Existing methods like Transformer-XL are plagued by ineffective memory selections due to the high number of tokens involved in attention calculation.
Approach:	They propose a plug-and-play strategy that selects tokens participating in attention calculation based on one simple metric and ignores the other ones.
Outcome:	The proposed strategy keeps tokens with high attention scores and ignores the other ones on word-level and character-level benchmarks without additional training or adding additional parameters.

Copied to clipboard

Xiaonan Li, Kai Lv, Hang Yan, Tianyang Lin, Wei Zhu, Yuan Ni, Guotong Xie, Xiaoling Wang, Xipeng Qiu

Neo-Classic: A Benchmark for Evaluating Linguistic-Aesthetic Reasoning in Classical Chinese Poetry (2026.acl-long)

Challenge:	In-context learning is a new learning paradigm where a language model conditions on a few input-output pairs (demonstrations) and a test input, and directly outputs the prediction.
Approach:	They propose a single model to retrieve demonstrations for a wide range of tasks by combining training signals from various tasks into a unified list-wise ranking formulation by language model’s feedback.
Outcome:	The proposed model outperforms baselines on 30+ tasks across 13 task families and multiple data domains.

Copied to clipboard

Han Zhang, Zihan Gu, Zhiyuan Wang, Tianyi Ma, Jiacheng Lu, Xinyan Zhang, Yuhao Wei, Cheng Hua

Generalized Intent Discovery: Learning from Open World Dialogue System (2022.coling-1)

Challenge:	Large Language Models (LLMs) achieve high accuracy on established Classical Chinese Poetry benchmarks, but it remains challenging to distinguish transferable Linguistic-Aesthetic Reasoning from reliance on familiar pre-training patterns.
Approach:	They propose a benchmark that combines a constructionist Out-of-Sample dataset with reverse understanding probes to evaluate large-scale large-format models.
Outcome:	The proposed model performs well on classical Chinese poetry benchmarks, but a performance gap persists . the model can complete famous couplets and can be used to understand a variety of texts.

Copied to clipboard

Yutao Mou, Keqing He, Yanan Wu, Pei Wang, Jingang Wang, Wei Wu, Yi Huang, Junlan Feng, Weiran Xu

MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning (2025.findings-acl)

Challenge:	Existing intent classification models rely on a pre-defined intent set and supervised labels, which is limited in some practical scenarios.
Approach:	They propose to extend an IND intent classifier to an open-world intent set including IND and OOD intents.
Outcome:	The proposed task can classify IND and OOD intents while discovering new unlabeled OOD types incrementally.

Copied to clipboard

Ke Wang, Junting Pan, Linda Wei, Aojun Zhou, Weikang Shi, Zimu Lu, Han Xiao, Yunqiao Yang, Houxing Ren, Mingjie Zhan, Hongsheng Li

Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoning (2025.findings-emnlp)

Challenge:	Large Language Models (LMMs) struggle with simple tasks such as geometry, e.g., arithmetic, and reasoning.
Approach:	They propose to leverage code as supervision for cross-modal alignment . they propose to use FigCodifier and ImgCode-8.6M to synthesize novel mathematical figures .
Outcome:	The proposed model surpasses GPT-4o and Claude 3.5 Sonnet in the geometry problem-solving subset of MathVista, achieving improvements of 8.9% and 9.2%.

Copied to clipboard

Yihong Tang, Ao Qu, Zhaokai Wang, Dingyi Zhuang, Zhaofeng Wu, Wei Ma, Shenhao Wang, Yunhan Zheng, Zhan Zhao, Jinhua Zhao

Learning by Analogy: Diverse Questions Generation in Math Word Problem (2023.findings-acl)

Challenge:	Currently, vision-language models excel in many downstream tasks but struggle with spatial reasoning, which is crucial for navigation and interaction with physical environments.
Approach:	They propose a framework that generates synthetic data to provide targeted supervision for VLMs across these basic spatial capabilities.
Outcome:	The proposed framework disentangles 2D spatial reasoning into three core components: direction comprehension, distance estimation, and localization.

Copied to clipboard

Zihao Zhou, Maizhen Ning, Qiufeng Wang, Jie Yao, Wei Wang, Xiaowei Huang, Kaizhu Huang

A Survey on Efficient Large Language Model Training: From Data-centric Perspectives (2025.acl-long)

Challenge:	Existing methods for solving math word problem (MWP) use shortcut learning to train solvers based on samples with a single question.
Approach:	They propose to generate diverse yet consistent questions from a common scenario . they then feed the equations to a question generator to obtain the diverse questions . their method leads to performance improvement on the current benchmark Math23K .
Outcome:	The proposed method generates diverse yet consistent questions with a variety of equations and questions . it improves on the current benchmark, which is based on the proposed method .

Copied to clipboard

Junyu Luo, Bohan Wu, Xiao Luo, Zhiping Xiao, Yiqiao Jin, Rong-Cheng Tu, Nan Yin, Yifan Wang, Jingyang Yuan, Wei Ju, Ming Zhang

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

Challenge:	achieving data-efficient post-training of Large Language Models is a key research question.
Approach:	They propose a taxonomy of data-efficient LLM post-training methods from a data-centric perspective.
Outcome:	The proposed methods cover data selection, data quality enhancement, synthetic data generation, data distillation and compression, and self-evolving data ecosystems.

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

Applying BERT to Document Retrieval with Birch (D19-3)

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

Copied to clipboard

Zeynep Akkalyoncu Yilmaz, Shengjin Wang, Wei Yang, Haotian Zhang, Jimmy Lin

Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs (2024.findings-emnlp)

Challenge:	Birch is an open-source document retrieval system that integrates with the Anserini information retrieval toolkit to demonstrate end-to-end search over large document collections.
Approach:	They propose to integrate Anserini with a BERT-based document ranking model that provides an end-to-end open-source search engine.
Outcome:	The proposed system outperforms existing approaches to document retrieval and question answering on standard newswire and social media test collections.

Copied to clipboard

Junjie Wang, Mingyang Chen, Binbin Hu, Dan Yang, Ziqi Liu, Yue Shen, Peng Wei, Zhiqiang Zhang, Jinjie Gu, Jun Zhou, Jeff Pan, Wen Zhang, Huajun Chen

PsyScore: A Psychometrically-Aware Framework for Trait-Adaptive Essay Scoring and ZPD-Scaffolded Feedback (2026.findings-acl)

Challenge:	Recent studies have attempted to enhance the performance of large language models (LLMs) in complex question-answering (QA) tasks by combining step-wise planning with external retrieval.
Approach:	They propose a framework for enhancing LLMs’ planning capabilities by using planning data derived from knowledge graphs (KGs).
Outcome:	The proposed framework improves LLMs’ planning capabilities by using knowledge graphs (KGs) the proposed framework is compared with existing frameworks on multiple datasets and shows that it is effective for large language models.

Copied to clipboard

Wei Xia, Jin Wu, Haoran Shi, Xiangyu Wang, Chanjin Zheng

Make Some Noise: Unlocking Language Model Parallel Inference Capability through Noisy Training (2024.emnlp-main)

Challenge:	Existing approaches to Automated Essay Scoring (AES) treat scoring and feedback as separate components, resulting in fragmentation.
Approach:	They propose a psychometrically-aware framework that integrates diagnostic assessment with instructional scaffolding through a shared latent ability representation.
Outcome:	The proposed framework integrates diagnostic assessment with instructional scaffolding through a shared latent ability representation.

Copied to clipboard

Yixuan Wang, Xianzhen Luo, Fuxuan Wei, Yijun Liu, Qingfu Zhu, Xuanyu Zhang, Qing Yang, Dongliang Xu, Wanxiang Che

Adaptive and Representative Multi-Interest Modeling for Recommendation with Large Language Model (2026.findings-acl)

Challenge:	Existing speculative decoding methods require additional model structure and training processes to assist the model for draft token generation.
Approach:	They propose a make some noise training framework that introduces some noise at the input for the model to learn the denoising task.
Outcome:	The proposed model improves inference speed by 2.3-2.7x times without compromising model performance.

Copied to clipboard

Ziyan Wang, Yingpeng Du, Tianjun Wei, Haoyan Chua, Jieyi Bi, Jie Zhang, Zhu Sun

MinPrompt: Graph-based Minimal Prompt Data Augmentation for Few-shot Question Answering (2024.acl-long)

Challenge:	Existing methods for multi-interest analysis of users rely on heuristic assumptions . however, the granularity of raw generation of LLMs is agnostic, leading to overly fine or coarse interest grouping.
Approach:	They propose an LLM-driven adaptive and representative multi-interest modeling framework that exploits the agnostic granularity of LLMs for multi-interest analysis.
Outcome:	The proposed model outperforms baselines on real-world datasets.

Copied to clipboard

Xiusi Chen, Jyun-Yu Jiang, Wei-Cheng Chang, Cho-Jui Hsieh, Hsiang-Fu Yu, Wei Wang

Title2Event: Benchmarking Open Event Extraction with a Large-scale Chinese Title Dataset (2022.emnlp-main)

Challenge:	Recent advances in few-shot question answering rely on pre-trained large language models and fine-tuning in specific settings.
Approach:	They propose to select the most informative data for fine-tuning to improve efficiency . they use an approximate graph algorithm and unsupervised question generation to generate QA pairs .
Outcome:	The proposed framework improves the performance of the few-shot question answering task on the open-domain QA task.

Copied to clipboard

Haolin Deng, Yanan Zhang, Yangfan Zhang, Wangyang Ying, Changlong Yu, Jun Gao, Wei Wang, Xiaoling Bai, Nan Yang, Jin Ma, Xiang Chen, Tianhua Zhou

Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks (N19-1)

Challenge:	Existing EE datasets define fixed event types and design specific schemas for each of them, failing to cover diverse events emerging from the online text.
Approach:	They propose to use a sentence-level dataset to benchmark Open Event Extraction without restricting event types.
Outcome:	The proposed dataset contains more than 42,000 news titles in 34 topics collected from Chinese web pages.

Copied to clipboard

Ningyu Zhang, Shumin Deng, Zhanlin Sun, Guanying Wang, Xi Chen, Wei Zhang, Huajun Chen

On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions (2025.findings-emnlp)

Challenge:	Existing distance supervised relation extraction models for long-tail data are inadequate for many applications.
Approach:	They propose to leverage implicit relational knowledge among class labels and learn explicit relational knowing using graph convolution networks.
Outcome:	The proposed approach outperforms baselines for long-tail relations on a large-scale dataset.

Copied to clipboard

Weiqi Wang, Tianqing Fang, Haochen Shi, Baixuan Xu, Wenxuan Ding, Liyu Zhang, Wei Fan, Jiaxin Bai, Haoran Li, Xin Liu, Yangqiu Song

ClusterFormer: Neural Clustering Attention for Efficient and Effective Transformer (2022.acl-long)

Challenge:	Conceptualization is a fundamental element of human cognition and plays a pivotal role in generalizable reasoning.
Approach:	They propose to categorize different types of conceptualizations into four levels based on the types of instances being conceptualized.
Outcome:	The proposed categorization of different types of conceptualizations into four levels based on the types of instances being conceptualized .

Copied to clipboard

Ningning Wang, Guobing Gan, Peng Zhang, Shuai Zhang, Junqiu Wei, Qun Liu, Xin Jiang

SPEED++: A Multilingual Event Extraction Framework for Epidemic Prediction and Preparedness (2024.emnlp-main)

Challenge:	Existing sparse attention methods use fixed patterns to select words without considering similarities between words.
Approach:	They propose a neural clustering method which integrates into the Self-Attention Mechanism in Transformer and integrates it into the target task.
Outcome:	The proposed method outperforms two typical sparse attention methods on translation, text classification, and text matching tasks while having a comparable or even better time and memory efficiency.

Copied to clipboard

Tanmay Parekh, Jeffrey Kwan, Jiarui Yu, Sparsh Johri, Hyosang Ahn, Sreya Muppalla, Kai-Wei Chang, Wei Wang, Nanyun Peng

A Multi-Agent Framework for High-Interaction Terminal Simulation (2026.acl-long)

Challenge:	Prior studies focused on English posts to provide early warnings for epidemic prediction, but these work focused on non-English posts.
Approach:	They propose a multilingual event extraction framework for extracting epidemic event information for any disease and language using 5.1K tweets in four languages.
Outcome:	The proposed framework can provide epidemic warnings for COVID-19 in its earliest stages in Dec 2019 (3 weeks before global discussions) and aggregate community epidemic discussions like symptoms and cure measures, aiding misinformation detection and public attention monitoring.

Copied to clipboard

Kai Wei, Yuwen Cui, Kehan Shen, Hua Wei, Guangjing Wang

A Neural Transition-based Model for Nested Mention Recognition (D18-1)

Challenge:	Terminal simulation is a problem of symbolic language generation in dialogue and interactive systems.
Approach:	They propose a terminal command-level Turing test framework that improves realism, consistency and robustness in command-language generation.
Outcome:	The proposed framework outperforms state-of-the-art benchmarks by more than 9% on multi-turn terminal simulation.

Copied to clipboard

Bailin Wang, Wei Lu, Yu Wang, Hongxia Jin

Challenge:	Existing methods to recognize nested mentions are based on Stack-LSTM . nesting mentions can be used for downstream tasks like question answering and relation extraction.
Approach:	They propose a scalable transition-based method to model the nested structure of mentions.
Outcome:	The proposed method gets the state-of-the-art performance in ACE datasets showing its effectiveness in detecting nested mentions.

Modeling Temporal-Modal Entity Graph for Procedural Multimodal Machine Comprehension (2022.acl-long)

Copied to clipboard

Huibin Zhang, Zhengkun Zhang, Yao Zhang, Jun Wang, Yufan Li, Ning Jiang, Xin Wei, Zhenglu Yang

When Inverse Data Outperforms: Exploring the Pitfalls of Mixed Data in Multi-Stage Fine-Tuning (2025.findings-emnlp)

Challenge:	Procedural Multimodal Documents organize textual instructions and corresponding images step by step.
Approach:	They propose a novel temporal-modal entity Graph for comprehending PMDs . they propose encoding and reasoning modules to capture textual and visual entities .
Outcome:	The proposed model can capture textual and visual entities and trace their temporal-modal evolution.

Copied to clipboard

Mengyi Deng, Xin Li, Tingyu Zhu, Zhicheng Yang, Zhijiang Guo, Wei Wang

Squrve: A Unified and Modular Framework for Complex Real-World Text-to-SQL Tasks (2026.acl-demo)

Challenge:	Existing methods for o1-level performance focus on unidirectional supervised fine-tuning (SFT), overlooking the intricate interplay between diverse reasoning patterns.
Approach:	They construct a reverse reasoning dataset and examine how it is supervised . they find that naively mixing forward and reverse data during SFT weakens the directional distinction .
Outcome:	The proposed model improves accuracy by 1.6%–6.8% over a standard model.

Copied to clipboard

Yihan Wang, Peiyu Liu, Runyu Chen, Jiaxing Pu, Wei Xu

Learning a Multi-Domain Curriculum for Neural Machine Translation (2020.acl-main)

Challenge:	Existing methods are designed for specific settings, each with its own set of challenges.
Approach:	They propose a unified, modular, and extensive Text-to-SQL framework . it proposes a universal execution paradigm and a multi-actor collaboration mechanism .
Outcome:	Squrve proposes a unified, modular, and extensive Text-to-SQL framework . the framework outperforms existing methods on widely adopted benchmarks .

Copied to clipboard

Wei Wang, Ye Tian, Jiquan Ngiam, Yinfei Yang, Isaac Caswell, Zarana Parekh

CSTree-SRI: Introspection-Driven Cognitive Semantic Tree for Multi-Turn Question Answering over Extra-Long Contexts (2025.acl-long)

Challenge:	Existing data selection methods do not work well for multiple domains . multiple aspects need to be considered for training a multi-domain model .
Approach:	They propose a dynamic data selection method to multi-domain NMT that incorporates instance-level domain-relevance features and a curriculum to gradually focus on multi- domain relevant data batches.
Outcome:	The proposed model outperforms no-curriculum training on multiple domains and reaches or outperformed individual performance.

Copied to clipboard

Zhaowen Wang, Xiang Wei, Kangshao Du, Yiting Zhang, Libo Qin, Yingjie Xia, Li Kuang

Latent Suicide Risk Detection on Microblog via Suicide-Oriented Word Embeddings and Layered Attention (D19-1)

Challenge:	Large Language Models (LLMs) have achieved remarkable success in natural language processing (NLP), particularly in single-turn question answering (QA) on short-text.
Approach:	They propose a framework that captures logical correlations across chunks of ELC and maintains coherence of multi-turn Questions.
Outcome:	The proposed framework is able to capture logical correlations across chunks of ELC and maintain coherence of multi-turn Questions.

Copied to clipboard

Lei Cao, Huijun Zhang, Ling Feng, Zihan Wei, Xin Wang, Ningyun Li, Xiaohao He

NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning (2025.emnlp-main)

Challenge:	Existing approaches to detect suicidal ideation on social media are limited to a small group of people.
Approach:	They propose to use tree holes to embed words into microblogs to strengthen the sensibility of suicide-related lexicons and to use a two-layered attention mechanism to grasp intermittently changing points from individual's open blog streams.
Outcome:	The proposed approach can achieve over 91% accuracy with the use of suicide-oriented word embeddings and attention on a large-scale well-labelled suicide data set.

Copied to clipboard

Wei Liu, Siya Qi, Xinyu Wang, Chen Qian, Yali Du, Yulan He

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

Challenge:	Recent advances in reinforcement learning, such as DeepSeek R1-Zero, highlight the effectiveness of incentive training, but these methods rely on external verifiers, which limits their applicability to domains like mathematics and coding, where such verifier is readily available.
Approach:	They propose a general reinforcement learning framework that requires only standard supervised fine-tuning data with no need for an external verifier.
Outcome:	The proposed framework outperforms the model of the same size distilled from large reasoning models such as DeepSeek R1 671B by 7.7%.

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

Modeling Adversarial Attack on Pre-trained Language Models as Sequential Decision Making (2023.findings-acl)

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

Copied to clipboard

Xuanjie Fang, Sijie Cheng, Yang Liu, Wei Wang

InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning (2026.acl-long)

Challenge:	Pre-trained language models (PLMs) have shown strong potential in various downstream tasks.
Approach:	They propose to model adversarial attack task as a sequential decision-making problem where the whole attack process is sequential with two decision- making problems, i.e., word finder and word substitution.
Outcome:	The proposed approach achieves the highest attack success rate with a comparable modification rate and semantic similarity to attack fine-tuned BERT.

Copied to clipboard

Qihang Ai, Pi Bu, Yue Cao, Yingyao Wang, Jihao Gu, Jingxuan Xing, Zekun Zhu, Wei Jiang, Zhicheng Zheng, Jun Song, Yuning Jiang

ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs (2025.acl-long)

Challenge:	Recent advances in Vision-Language Models (VLMs) have enabled mobile agents to perceive and interact with real-world mobile environments based on human instructions.
Approach:	They propose a vision-language model that actively seeks human confirmation at critical decision points and a model inspired by reinforcement learning.
Outcome:	The proposed model achieves an improvement of 46.8% in inquiry success rate and the best overall success rate among existing baselines on InquireBench.

Copied to clipboard

Yan Yang, Yixia Li, Hongru Wang, Xuetao Wei, James Jianqiao Yu, Yun Chen, Guanhua Chen

Counterfactual Adversarial Learning with Representation Interpolation (2021.findings-emnlp)

Challenge:	Recent approaches to reduce resource requirements for task-specific large language models have been developed.
Approach:	They propose a delta compression approach that optimizes for importance of a model . they use SVD to dynamically adjust the sparsity ratios of different vectors based on their importance .
Outcome:	The proposed approach achieves state-of-the-art in retaining task-specific knowledge even at high sparsity ratios.

Copied to clipboard

Wei Wang, Boxin Wang, Ning Shi, Jinfeng Li, Bingyu Zhu, Xiangyu Liu, Rong Zhang

ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning (2025.emnlp-main)

Challenge:	Existing models with statistical bias are prone to memorized correlations . large pre-trained models such as BERT have revolutionized the model development paradigm in natural language processing .
Approach:	They propose a framework to tackle the problem from a causal perspective using a latent space interpolation approach.
Outcome:	Extensive experiments show that CAT achieves substantial performance improvement over SOTA across different downstream tasks, including sentence classification, natural language inference and question answering.

Copied to clipboard

Ziqing Qiao, Yongheng Deng, Jiali Zeng, Dong Wang, Lai Wei, Guanbo Wang, Fandong Meng, Jie Zhou, Ju Ren, Yaoxue Zhang

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

Challenge:	Existing methods for fine-tuning-based compression suffer from verbose outputs, increasing computational overhead.
Approach:	They propose a framework to generate concise reasoning chains using Confidence Injection and Early Stopping.
Outcome:	The proposed framework reduces the length of the model by up to 50% while maintaining high task accuracy.

Copied to clipboard

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

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

Sent2Span: Span Detection for PICO Extraction in the Biomedical Text without Span Annotations (2021.findings-emnlp)

Copied to clipboard

Shifeng Liu, Yifang Sun, Bing Li, Wei Wang, Florence T. Bourgeois, Adam G. Dunn

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM𝛥 Integration into Upcycled MoE (2026.acl-long)

Challenge:	Experiments show that PICO span detection results achieve much higher results for recall when compared to fully supervised methods.
Approach:	They propose to extract and then normalise PICO information from clinical trial articles and use crowdsourced sentence-level annotations to detect spans.
Outcome:	The proposed method achieves much higher results for recall when compared to fully supervised methods with PICO sentence detection at least as good as human annotations.

Copied to clipboard

Hao Zhou, Tianhao Li, Zhijun Wang, Shuaijie She, Linjuan Wu, Hao-Ran Wei, Baosong Yang, Jiajun Chen, Shujian Huang

CoinMath: Harnessing the Power of Coding Instruction for Math LLM (2025.findings-acl)

Challenge:	Large Language Models (LLMs) are expensive and require extensive Continued Pre-Training and data-intensive alignment to expand.
Approach:	They propose a method which upcycles a dense model into a Mixture-of-Experts architecture, allocating different experts to different languages.
Outcome:	Experiments show that the proposed model upcycles a dense model into a Mixture-of-Experts(MoE) architecture, allocating different experts to different languages.

Copied to clipboard

Chengwei Wei, Bin Wang, Jung-jae Kim, Guimei Liu, Nancy F. Chen

Do VLMs Have a Moral Backbone? A Study on the Fragile Morality of Vision-Language Models (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have shown strong performance in solving mathematical problems, with code-based solutions proving particularly effective.
Approach:	They propose a learning strategy to enhance mathematical reasoning by diversifying the coding styles of code-based rationales.
Outcome:	The proposed learning strategy outperforms its baseline model, MAmmoTH, which uses code-based solutions.

Copied to clipboard

Zhining Liu, Tianyi Wang, Xiao Lin, Penghao Ouyang, Gaotang Li, Ze Yang, Hui Liu, Sumit Keswani, Vishwa Pardeshi, Huijun Zhao, Wei Fan, Hanghang Tong

Negative Sample is Negative in Its Own Way: Tailoring Negative Sentences for Image-Text Retrieval (2022.findings-naacl)

Challenge:	Vision-Language Models (VLMs) have advanced multimodal learning, driving progress in cross-modal reasoning.
Approach:	They propose to examine moral robustness of vision-language models by analyzing their moral stances under multimodal perturbations.
Outcome:	The proposed model-agnostic multimodal perturbations expose VLMs to a variety of moral vulnerabilities, including a sycophancy trade-off where stronger instruction-following models are more susceptible to persuasion.

Copied to clipboard

Zhihao Fan, Zhongyu Wei, Zejun Li, Siyuan Wang, Xuanjing Huang, Jianqing Fan

Learning Multi-Step Reasoning by Solving Arithmetic Tasks (2023.acl-short)

Challenge:	Existing approaches to retrieve hard negative sentences are limited in the scale of the dataset thus fail to identify negative samples of high difficulty for every image.
Approach:	They propose to use a model to generate synthetic negative sentences with higher difficulty by masking and refilling the images and performing word discrimination and word correction tasks to improve retrieval and generation.
Outcome:	The proposed model generates synthetic negative sentences with higher difficulty on MS-COCO and Flickr30K and is robust and faithful to state-of-the-art training.

Copied to clipboard

Tianduo Wang, Wei Lu

DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing (2026.findings-acl)

Challenge:	Recent studies have demonstrated large LMs’ impressive performance in solving math problems, but such ability seems only to emerge from models with abundant parameters.
Approach:	They propose to continuously pre-train LMs with the capabilities of multi-step reasoning by continuously pretraining them on a synthetic dataset MsAT.
Outcome:	The proposed method improves LMs' multi-step reasoning abilities on four math word problem datasets.

Copied to clipboard

Hongzhi Zhang, Yuanze Hu, Tinghai Zhang, Jia Fu, Tao Wang, Junwei Jing, Zhaoxin Fan, Wei Bi, Ruiming Tang, Han Li, Guorui Zhou, Kun Gai

Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment (2022.acl-long)

Challenge:	Large Language Models (LLMs) are evolving towards autonomous agents . retrieval capabilities are well-benchmarked, but post-retrieval synthesis is under-evaluated due to open-ended writing.
Approach:	They propose a benchmark to evaluate information consolidation capabilities using survey papers as gold standards.
Outcome:	The proposed benchmark analyzes the post-retrieval synthesis stage of large language models . it leverages high-quality survey papers as gold standards and reverse-engineers research requests . the proposed benchmark outperforms single-turn generation and reduces hallucinations .

Copied to clipboard

Zijie Huang, Zheng Li, Haoming Jiang, Tianyu Cao, Hanqing Lu, Bing Yin, Karthik Subbian, Yizhou Sun, Wei Wang

Towards Fine-Grained and Multi-Granular Contrastive Language-Speech Pre-training (2026.acl-long)

Challenge:	Existing methods to predict missing facts in knowledge graphs are limited in language alignment . SS-AGA uses seed alignment as an edge type to fuses all KGs as a whole graph .
Approach:	They propose a self-supervised adaptive graph alignment method that fuses all KGs as a whole graph by regarding alignment as 'a new edge type' they propose SS-AGA method that uses relation-aware attention weights to capture potential alignment pairs in a new paradigm.
Outcome:	The proposed method can predict missing facts in a knowledge graph (KG) but language alignment is scarce and new alignment identification is noisy.

Copied to clipboard

Yifan Yang, Bing Han, Hui Wang, Wei Wang, Ziyang Ma, Long Zhou, Zengrui Jin, Guanrou Yang, Tianrui Wang, Xu Tan, Xie Chen

MAssistant: A Personal Knowledge Assistant for MOOC Learners (D19-3)

Challenge:	Existing models for fine-grained speaking styles are limited in terms of accuracy, coverage, and naturalness.
Approach:	They propose a model that pre-trains with coarse captions and annotates with a pipeline that grounds captions in audio.
Outcome:	The proposed model outperforms existing models with fine-grained style annotations . it integrates global and fine-granular supervision, enabling unified representations based on the proposed model .

Copied to clipboard

Lan Jiang, Shuhan Hu, Mingyu Huang, Zhichun Wang, Jinjian Yang, Xiaoju Ye, Wei Zheng

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

Challenge:	Massive Open Online Courses (MOOCs) have experienced a rapid development since 2012 . many MOOC platforms have been launched, including Coursera1 , edX2 , and Udacity3 etc.
Approach:	They present a personal knowledge assistant system called MAssistant for MOOC learners . MAsistants has a large-scale concept graph built from open data . it also provides a browser extension which interacts with users during video lectures .
Outcome:	The proposed system helps users trace the concepts they have learned in MOOCs, and to build their own concept graphs.

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

Resilience of Large Language Models for Noisy Instructions (2024.findings-emnlp)

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

Copied to clipboard

Bin Wang, Chengwei Wei, Zhengyuan Liu, Geyu Lin, Nancy Chen

BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem Solving (2025.acl-long)

Challenge:	Large language models (LLMs) are powerful tools for interpreting human commands and generating text.
Approach:	They examine the resilience of large language models against five common types of disruptions including ASR, OCR, grammatical errors, typographical errors and distractive content.
Outcome:	The models show resistance to noise, but their performance suffers . authors evaluated the models against five common types of disruptions based on their results .

Copied to clipboard

Teng Wang, Wing Yin Yu, Zhenqi He, Zehua Liu, HaileiGong HaileiGong, Han Wu, Xiongwei Han, Wei Shi, Ruifeng She, Fangzhou Zhu, Tao Zhong

SAFER: Advancing Safety Alignment via Efficient Ex-Ante Reasoning (2026.findings-acl)

Challenge:	Existing datasets in operations research domain lack detailed annotations of the modeling process, focusing only on objective values.
Approach:	They propose an annotation-based tree-of-thought tree-based reasoning algorithm that integrates reinforcement learning into a tree- of-though.
Outcome:	The proposed algorithm outperforms state-of-the-art methods on StructuredOR, NL4OPT, and MAMO-ComplexLP datasets.

Copied to clipboard

Kehua Feng, Keyan Ding, Yuhao Wang, Menghan Li, Fanjunduo Wei, Xinda Wang, Huajun Chen

Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue (2024.acl-long)

Challenge:	Existing alignment methods struggle to cover diverse safety scenarios and remain vulnerable to adversarial attacks.
Approach:	They propose a framework for 'Safety' alignment via eFficient' Ex-Ante-R**easoning that instantiates structured Ex-Ance reasoning and embeds predefined safety rules.
Outcome:	The proposed framework enhances safety performance while maintaining usefulness and efficiency.

Copied to clipboard

Jian Wang, Chak Tou Leong, Jiashuo Wang, Dongding Lin, Wenjie Li, Xiaoyong Wei

Mitigating Posterior Salience Attenuation in Long-Context LLMs with Positional Contrastive Decoding (2025.acl-short)

Challenge:	Tuning language models for dialogue generation has been a prevalent paradigm for building capable dialogue agents.
Approach:	They propose a multi-round interactive dialogue tuning framework that models the speaker roles of agent and user separately.
Outcome:	The proposed framework performs superior to fine-tuning and improves dialogue consistency.

Copied to clipboard

Zikai Xiao, Ziyang Wang, Wen Ma, Yan Zhang, Wei Shen, WangYan WangYan, Luqi Gong, Zuozhu Liu

Challenge:	Current solutions incur prohibitive training costs, leaving statistical behaviors and cost-effective approaches underexplored.
Approach:	They propose a positional contrast decoding technique that contrasts long-aware attention with designed local-awn attention.
Outcome:	The proposed model achieves state-of-the-art performance on long-context benchmarks.

Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning (2024.acl-long)

Copied to clipboard

Zhaorui Yang, Tianyu Pang, Haozhe Feng, Han Wang, Wei Chen, Minfeng Zhu, Qian Liu

Federated LoRA Fine-Tuning with Pipelined Error-Mitigated Aggregation and Matrix-Wise Freezing (2026.findings-acl)

Challenge:	Experimental results show that fine-tuning of large language models for specific tasks can be challenging . distribution shift during fine-timing can lead to performance degradation in general task capabilities .
Approach:	They propose a new approach that bridges the distribution gap between task datasets and LLMs by guiding fine-tuning with a distilled dataset generated by the model itself.
Outcome:	The proposed approach achieves comparable or superior performance on downstream tasks compared to the vanilla approach.

Copied to clipboard

Haoran Wang, Xiong Wang, Yuqing Li, Jing Chen, Junyi Zhang, Nan Yan, Kun He, Wei Wang

Seen to Unseen: Exploring Compositional Generalization of Multi-Attribute Controllable Dialogue Generation (2023.acl-long)

Challenge:	Existing methods for fine-tuning large language models often suffer from biased model aggregation and are hindered by significant communication and computation burden.
Approach:	They propose a Federated low-rank adaptation system for large language models that leverages pipelined error-mitigated model aggregation and adaptive matrix-wise parameter freezing to mitigate aggregations.
Outcome:	The proposed system improves time-to-target by 2.17-8.48 on real-world datasets.

Copied to clipboard

Weihao Zeng, Lulu Zhao, Keqing He, Ruotong Geng, Jingang Wang, Wei Wu, Weiran Xu

Mitigating the Alignment Tax of RLHF (2024.emnlp-main)

Challenge:	Existing controllable dialogue generation models focus on single attribute and lack generalization capability to out-of-distribution multiple attribute combinations.
Approach:	They propose a compositional generalization model that learns from seen attributes and generalizes to unseen combinations.
Outcome:	The proposed model can learn from seen attribute values and generalize to unseen combinations.

Copied to clipboard

Yong Lin, Hangyu Lin, Wei Xiong, Shizhe Diao, Jianmeng Liu, Jipeng Zhang, Rui Pan, Haoxiang Wang, Wenbin Hu, Hanning Zhang, Hanze Dong, Renjie Pi, Han Zhao, Nan Jiang, Heng Ji, Yuan Yao, Tong Zhang

MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering (2025.findings-acl)

Challenge:	Large Language Models (LLMs) acquire a wide range of abilities during pre-training, but aligning LLMs under Reinforcement Learning with Human Feedback (RLHF) can lead to forgetting pretrained abilities, which is also known as the alignment tax.
Approach:	They propose to use a model averaging technique to find the most powerful alignment-forging Pareto front among RLHF algorithms.
Outcome:	The proposed method achieves the strongest alignment-forging Pareto front among competing methods.

Copied to clipboard

Jingqun Tang, Qi Liu, Yongjie Ye, Jinghui Lu, Shu Wei, An-Lan Wang, Chunhui Lin, Hao Feng, Zhen Zhao, Yanjie Wang, Yuliang Liu, Hao Liu, Xiang Bai, Can Huang

Learning to Ask Unanswerable Questions for Machine Reading Comprehension (P19-1)

Challenge:	Text-Centric Visual Question Answering (TEC-VQA) is a text-centric visual task understanding tool.
Approach:	They introduce a benchmark that features human expert annotations across 9 languages . they prioritize the text in question-answer pairs while disregarding visual text in images .
Outcome:	The proposed benchmarks prioritize the text in question-answer pairs while disregarding visual text in images.

Copied to clipboard

Haichao Zhu, Li Dong, Furu Wei, Wenhui Wang, Bing Qin, Ting Liu

Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generation (2026.findings-acl)

Challenge:	Existing models for extractive reading comprehension are not good at deciding whether no answer is presented in the context.
Approach:	They propose a data augmentation technique by automatically generating relevant unanswerable questions according to an answerable question paired with its corresponding paragraph that contains the answer.
Outcome:	The proposed model performs better on the SQuAD 2.0 dataset than the baseline model and the BERT-large model.

Copied to clipboard

Linfeng Gao, Qinggang Zhang, Baolong Bi, Bo Zeng, Zheng Yuan, Zerui Chen, Zhimin Wei, Shenghua Liu, Linlong Xu, Longyue Wang, Weihua Luo, Jinsong Su

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

Challenge:	Existing approaches to improve contextual faithfulness treat the LLM as a black box, generating responses that are inconsistent with the provided context.
Approach:	They propose a framework for faithful RAG that operates in three stages: (i) fine-grained knowledge pruning to filter irrelevant context, (ii) latent conflict probing to identify hard conflicts in the model’s latent space, and (iv) conflict-aware attention to modulate attention heads toward faithful context integration.
Outcome:	Experiments show that ProbeRAG significantly improves both accuracy and contextual faithfulness.

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

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

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

Copied to clipboard

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

PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation (2020.emnlp-main)

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

Copied to clipboard

Bin Bi, Chenliang Li, Chen Wu, Ming Yan, Wei Wang, Songfang Huang, Fei Huang, Luo Si

Trustworthiness and Self-awareness in Large Language Models: An Exploration through the Think-Solve-Verify Framework (2024.lrec-main)

Challenge:	Existing techniques for natural language understanding and generation use autoencoding and/or autoregressive objectives to train models.
Approach:	They propose a self-supervised pre-training scheme that pre-trains an autoencoding and autoregressive language model on a large unlabeled corpus for generating new text conditioned on context.
Outcome:	The proposed scheme achieves state-of-the-art results on a variety of language generation benchmarks covering generative question answering, abstractive summarization and conversational response generation.

Copied to clipboard

Zhendong Liu, Changhong Xia, Wei He, Chongjun Wang

Low-Resource Generation of Multi-hop Reasoning Questions (2020.acl-main)

Challenge:	Large Language Models (LLMs) are becoming increasingly influential in reasoning tasks, but they lack trustworthiness and introspective self-awareness when subjected to complex reasoning tasks.
Approach:	They propose a framework to explore LLMs’ trustworthiness, introspective self-awareness, and collaborative reasoning by using the Think-Solve-Verify framework.
Outcome:	The proposed approach improves from 67.3% to 72.8% on the AQuA dataset and demonstrates the model’s ability to explain the given answers.

Copied to clipboard

Jianxing Yu, Wei Liu, Shuang Qiu, Qinliang Su, Kai Wang, Xiaojun Quan, Jian Yin

PaT: Planning-after-Trial for Efficient Test-Time Code Generation (2026.acl-long)

Challenge:	Existing methods to generate valid and fluent questions from text are limited and insufficient for training.
Approach:	They propose to generate multi-hop reasoning questions from the raw text in a low resource circumstance by deducing over multiple relations on several sentences in the text.
Outcome:	The proposed model can be applied to the task of machine reading comprehension and achieve significant performance improvements.

Copied to clipboard

Youngsik Yoon, Sungjae Lee, Seockbean Song, Siwei Wang, Wei Chen, Jungseul Ok

Better Simultaneous Translation with Monotonic Knowledge Distillation (2023.acl-long)

Challenge:	Existing methods for scaling test-time computation are rigid and inefficient . a heterogeneous configuration achieves performance comparable to a large homogeneously model .
Approach:	They propose an adaptive planning policy that invokes a planner only upon verification failure.
Outcome:	The proposed model achieves comparable performance to a large homogeneous model while reducing inference cost by approximately 69% across multiple benchmarks and model families.

Copied to clipboard

Shushu Wang, Jing Wu, Kai Fan, Wei Luo, Jun Xiao, Zhongqiang Huang

Pruning Large Language Models to Intra-module Low-rank Architecture with Transitional Activations (2024.findings-acl)

Challenge:	Existing methods to train offline MT models require generating target tokens before source sentence is fully consumed.
Approach:	They propose a method that leverages traditional translation models as teachers to generate monotonic yet accurate reference translations for sequence-level knowledge distillation.
Outcome:	The proposed approach improves on strong baselines and on a monotonic version of the WMT15 De-En test set.

Copied to clipboard

Bowen Shen, Zheng Lin, Daren Zha, Wei Liu, Jian Luan, Bin Wang, Weiping Wang

Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning (2024.acl-long)

Challenge:	Structured pruning is a feasible solution for end-side LLM deployment . however, achieving a high compression ratio for scaled-up LLMs remains a challenge .
Approach:	They propose a task-agnostic structured pruning approach coupled with a compact Transformer architecture to prune LLMs into an intra-module low-rank architecture.
Outcome:	The proposed approach reduces transitional activations inside multi-head attention (MHA) and multi-layer perceptron (MLP) modules while preserving inter-module activations sensitive to perturbations.

Copied to clipboard

Tianduo Wang, Shichen Li, Wei Lu

Learning to Discriminate Perturbations for Blocking Adversarial Attacks in Text Classification (D19-1)

Challenge:	Recent studies focus on enhancing large-scale language models' reasoning abilities, but the research question of how to GSM8K Performance vs. computational cost remains.
Approach:	They propose to train small-scale language models with their own outputs to avoid relying on large models' outputs.
Outcome:	The proposed approach outperforms baseline models with comparable sizes while minimizing the required compute.

Copied to clipboard

Yichao Zhou, Jyun-Yu Jiang, Kai-Wei Chang, Wei Wang

UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning (2021.acl-long)

Challenge:	Existing studies on adversarial attacks on deep learning models focus on generation of adversarials and defense against adversarial attacks.
Approach:	They propose a framework to identify and adjust malicious perturbations and block adversarial attacks for machine learning models.
Outcome:	The proposed framework outperforms baseline methods in blocking adversarial attacks for text classification models.

Copied to clipboard

Wei Li, Can Gao, Guocheng Niu, Xinyan Xiao, Hao Liu, Jiachen Liu, Hua Wu, Haifeng Wang

DeReA: Improving Idiom Translation with Detect-Retrieve-Arbitrate Reasoning (2026.acl-long)

Challenge:	Existing pre-training methods focus on single-modal tasks or multi-modal ones . large-scale pre- training has drawn much attention in both the community of Compute Vision (CV) and Natural Language Processing (NLP).
Approach:	They propose a UNIfied-MOdal pre-training architecture which can adapt to both single-modal and multi-modal understanding and generation tasks.
Outcome:	The proposed model can learn more generalizable representations with rich non-paired single-modal data.

Copied to clipboard

Rongqing Jiang, Xuebo Liu, Shengxin Liu, Yutong Wang, Min Zhang, Shimin Tao, Daimeng Wei, Min Zhang

Incorporating External Knowledge into Machine Reading for Generative Question Answering (D19-1)

Challenge:	Existing approaches to idiom translation are limited by the constraints of static parametric memory and retrieval noise . idiomatic expressions are non-compositional units where figurative meanings diverge from literal interpretations .
Approach:	They propose a detect-retrieve-arbitrate framework that detects idiomatic spans by reasoning over semantic conflicts between literal and contextual meanings.
Outcome:	The proposed framework improves GPT-5-mini and Emerging Slang datasets on various model scales.

Copied to clipboard

Bin Bi, Chen Wu, Ming Yan, Wei Wang, Jiangnan Xia, Chenliang Li

Query Structure Modeling for Inductive Logical Reasoning Over Knowledge Graphs (2023.acl-long)

Challenge:	Existing knowledge-aware QA models do not have commonsense and background knowledge to answer nontrivial questions.
Approach:	They propose a new neural model which exploits external knowledge to generate answers in natural language for a given question with context.
Outcome:	The proposed model improves answer quality over existing models without knowledge and knowledge-aware models, a study shows . state officials in Hawaii confirmed that president Barack Obama was born in the U.S.

Copied to clipboard

Siyuan Wang, Zhongyu Wei, Meng Han, Zhihao Fan, Haijun Shan, Qi Zhang, Xuanjing Huang

AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning (2025.emnlp-demos)

Challenge:	Existing methods for inductive reasoning over knowledge graphs lack the ability to model the logical structures of complex queries.
Approach:	They propose a structure-modeled textual encoding framework for inductive logical reasoning over KGs that encodes linearized query structures and entities using pre-trained language models to find answers.
Outcome:	The proposed framework encodes query structures and entities using pre-trained language models to find answers.

Copied to clipboard

Zhong Zhang, Yaxi Lu, Yikun Fu, Yupeng Huo, Shenzhi Yang, Yesai Wu, Han Si, Xin Cong, Haotian Chen, Yankai Lin, Xie Xie, Wei Zhou, Wang Xu, Zhou Su, Zhongwu Zhai, Xiaoming Liu, null Meiyudong, Jianming Xu, Hongyan Tian, Chongyi Wang, Chi Chen, Yuan Yao, Zhiyuan Liu, Maosong Sun

PCEE-BERT: Accelerating BERT Inference via Patient and Confident Early Exiting (2022.findings-naacl)

Challenge:	Large language model agents have enabled GUI-based automation, but their deployment is limited by noisy data, poor generalization, and lack of support for non-English GUIs.
Approach:	They propose an 8B-parameter GUI agent built for robust and efficient on-device GUI interaction.
Outcome:	The proposed GUI agent achieves promising performance on five public benchmarks and proposed Chinese benchmark CAGUI.

Copied to clipboard

Zhen Zhang, Wei Zhu, Jinfan Zhang, Peng Wang, Rize Jin, Tae-Sun Chung

UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood Learning (2022.emnlp-main)

Challenge:	Pre-trained language models (PLMs) are the state-of-the-art (SOTA) models for natural language processing (NLP).
Approach:	They propose a patient and confident early exiting BERT (PCEE-BERT) that can work with different PLMs and popular model compression methods.
Outcome:	The proposed method outperforms existing models on the GLUE benchmarks and achieves different speed-up ratios.

Copied to clipboard

Yutao Mou, Pei Wang, Keqing He, Yanan Wu, Jingang Wang, Wei Wu, Weiran Xu

HiEdit: Lifelong Model Editing with Hierarchical Reinforcement Learning (2026.acl-long)

Challenge:	Existing methods to detect out-of-domain (OOD) intents ignore alignment between representation learning and scoring function, limiting performance.
Approach:	They propose a unified neighborhood learning framework to detect OOD intents . they propose to align representation learning with scoring function .
Outcome:	The proposed method is able to detect out-of-domain (OOD) intents from user queries.

Copied to clipboard

Yangfan Wang, Tianyang Sun, Chen Tang, Jie Liu, Wei Cai, Jingchi Jiang

Challenge:	Existing approaches to lifelong model editing apply parameter perturbations to static and dense layers for all instances.
Approach:	They propose a hierarchical reinforcement learning framework that identifies the most knowledge-relevant layers for each editing instance.
Outcome:	The proposed framework boosts the performance of the competitive RLEdit by 8.48% with perturbing only half of the layers per edit.

FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation (2024.findings-acl)

Copied to clipboard

Tu Vu, Mohit Iyyer, Xuezhi Wang, Noah Constant, Jerry Wei, Jason Wei, Chris Tar, Yun-Hsuan Sung, Denny Zhou, Quoc Le, Thang Luong

Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs (2026.findings-acl)

Challenge:	Modern large language models often "hallucinate" plausible but factually incorrect information, which reduces their trustworthiness especially in settings where accurate and up-to-date information is critical.
Approach:	They develop a human evaluation procedure to measure correctness and hallucination and use it to benchmark both closed and open-source LLMs.
Outcome:	The proposed method outperforms both competing search engine-augmented prompting methods and commercial systems on search-augmented QA.

Copied to clipboard

Qibin Wang, Pu Zhao, Shaohan Huang, Fangkai Yang, Lu Wang, Furu Wei, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang

AgentGym: Evaluating and Training Large Language Model-based Agents across Diverse Environments (2025.acl-long)

Challenge:	Existing approaches to test-time scaling are limited due to the quality of candidate responses.
Approach:	They propose a new metric to quantify the relative improvement of self-refinement beyond majority voting.
Outcome:	The proposed method achieves state-of-the-art performance across five benchmarks over other methods.

Copied to clipboard

Zhiheng Xi, Yiwen Ding, Wenxiang Chen, Boyang Hong, Honglin Guo, Junzhe Wang, Xin Guo, Dingwen Yang, Chenyang Liao, Wei He, Songyang Gao, Lu Chen, Rui Zheng, Yicheng Zou, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang, Zuxuan Wu, Yu-Gang Jiang

CLEAN–EVAL: Clean Evaluation on Contaminated Large Language Models (2024.findings-naacl)

Challenge:	Large language models (LLMs) are promising foundations to build generally-capable agents . however, the community lacks a unified interactive framework that covers diverse environments for comprehensive evaluation of agents.
Approach:	They propose a framework that features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction.
Outcome:	The proposed framework features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction.

Copied to clipboard

Wenhong Zhu, Hongkun Hao, Zhiwei He, Yun-Ze Song, Jiao Yueyang, Yumeng Zhang, Hanxu Hu, Yiran Wei, Rui Wang, Hongyuan Lu

TRELM: Towards Robust and Efficient Pre-training for Knowledge-Enhanced Language Models (2024.lrec-main)

Challenge:	Existing methods to evaluate large language models are prone to data contamination.
Approach:	They propose a method which parses contaminated data and back-translates it into a candidate set.
Outcome:	The proposed method reduces data contamination and evaluates the LLMs more cleanly.

Copied to clipboard

Junbing Yan, Chengyu Wang, Taolin Zhang, Xiaofeng He, Jun Huang, Wei Zhang, Longtao Huang, Hui Xue

Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of Text (2022.findings-acl)

Challenge:	Existing methods for incorporating external knowledge into language models do not prioritize learning embeddings for entity-related tokens.
Approach:	They propose a framework for incorporating external knowledge into pre-training models that utilize entity-related tokens.
Outcome:	The proposed framework reduces pre-training time by 50% and outperforms other KEPLMs in knowledge probing tasks and multiple knowledge-aware language understanding tasks.

Copied to clipboard

Siyuan Wang, Wanjun Zhong, Duyu Tang, Zhongyu Wei, Zhihao Fan, Daxin Jiang, Ming Zhou, Nan Duan

Multi-Granularity Semantic Revision for Large Language Model Distillation (2026.acl-long)

Challenge:	Existing methods for logical reasoning of text focus on contextual semantics while struggling to explicitly model the logical inference process.
Approach:	They propose a logic-driven context extension framework and a data-driven augmentation algorithm that uses contrastive learning to better capture logical information.
Outcome:	The proposed framework outperforms existing methods on two benchmark datasets, ReClor and LogiQA.

Copied to clipboard

Xiaoyu Liu, Yun Zhang, Wei Li, Simiao Li, Xudong Huang, Hanting Chen, Yehui Tang, Jie Hu, Zhiwei Xiong, Yunhe Wang

Multi-Agent Collaboration via Cross-Team Orchestration (2025.findings-acl)

Challenge:	Existing methods for generating large language models rely on student-generated outputs, which introduce generation errors and misguide the distillation process.
Approach:	They propose a multi-granularity semantic revision method for LLM distillation that corrects errors using teacher-generated tokens and re-generates the sequence to minimize errors.
Outcome:	The proposed method reduces errors and misguides distillation on student models and improves consistency between teacher and student outputs.

Copied to clipboard

Zhuoyun Du, Chen Qian, Wei Liu, Zihao Xie, YiFei Wang, Rennai Qiu, Yufan Dang, Weize Chen, Cheng Yang, Ye Tian, Xuantang Xiong, Lei Han

Challenge:	Large Language Models (LLMs) have significantly impacted various domains, especially through organized LLM-driven autonomous agents.
Approach:	They propose a framework that enables orchestrated teams to jointly propose various task-oriented solutions and interact with their insights in a self-independence while cross-team collaboration environment for superior solutions generation.
Outcome:	Experiments show that the framework can generate better software quality compared to state-of-the-art frameworks.

Inspecting Unification of Encoding and Matching with Transformer: A Case Study of Machine Reading Comprehension (D19-58)

Copied to clipboard

Hangbo Bao, Li Dong, Furu Wei, Wenhui Wang, Nan Yang, Lei Cui, Songhao Piao, Ming Zhou

HIRAG: Hierarchical-Thought Instruction-Tuning Retrieval-Augmented Generation (2025.findings-emnlp)

Challenge:	Experimental results show that unified model outperforms other models that treat encoding and matching separately.
Approach:	They evaluate a unified model with Transformer layers for machine reading comprehension . they find that the model learns different modeling strategies compared with previous models .
Outcome:	The unified model outperforms models with Transformer layers on the machine reading comprehension task.

Copied to clipboard

Yihan Jiao, Zhehao Tan, Dan Yang, Duolin Sun, Jie Feng, Yue Shen, Jian Wang, Peng Wei

How to Best Use Syntax in Semantic Role Labelling (P19-1)

Challenge:	In-depth research on the specific capabilities needed by the RAG generation model is lacking, leading to inconsistent document quality and retrieval system imperfections.
Approach:	They propose that RAG models should possess three progressively hierarchical abilities: (1) Filtering: the ability to select relevant information; (2) Combination: the capability to combine semantic information across paragraphs; (3) RAG-specific reasoning: the capacity to further process external knowledge using internal knowledge.
Outcome:	Experiments show that the proposed method significantly improves the model’s open-book examination capability on datasets such as RGB, PopQA, MuSiQue, HotpotQA, and PubmedQA.

Copied to clipboard

Yufei Wang, Mark Johnson, Stephen Wan, Yifang Sun, Wei Wang

Syntactic Text Processing

Challenge:	Existing studies on integrating external information into NLP tasks focus on word-level shallow features such as POS or chunk tags.
Approach:	They propose to integrate syntactic information into a neural ELMo-based SRL sequence labelling model by using a constituency representation as input features.
Outcome:	The proposed approach improves performance on the in-domain CoNLL’05 and CoNll’12 benchmarks.

MentalGLM Series: Explainable Large Language Models for Mental Health Analysis on Chinese Social Media (2025.emnlp-main)

Copied to clipboard

Wei Zhai, Nan Bai, Qing Zhao, Jianqiang Li, Fan Wang, Hongzhi Qi, Meng Jiang, Xiaoqin Wang, Bing Xiang Yang, Guanghui Fu

BLiMP: The Benchmark of Linguistic Minimal Pairs for English (2020.tacl-1)

Challenge:	Social media is a key platform for emotional expression, yet deep learning lacks flexibility and interpretability.
Approach:	They propose to use Chinese social media to train interpretable mental health instruction datasets to test models' ability to explain their decisions.
Outcome:	The proposed models outperform deep learning and LLMs on three mental health downstream tasks and demonstrate their potential for clinical applications.

Copied to clipboard

Alex Warstadt, Alicia Parrish, Haokun Liu, Anhad Mohananey, Wei Peng, Sheng-Fu Wang, Samuel R. Bowman

NUMINA: A Natural Understanding Benchmark for Multi-dimensional Intelligence and Numerical Reasoning Abilities (2025.findings-emnlp)

Challenge:	Recent studies have examined how linguistic knowledge of language models (LMs) varies across English phenomena.
Approach:	They propose a benchmark to evaluate linguistic knowledge of language models on major grammatical phenomena in English.
Outcome:	The proposed benchmark evaluates the linguistic knowledge of language models on major grammatical phenomena in English.

Copied to clipboard

Changyu Zeng, Yifan Wang, Zimu Wang, Wei Wang, Zhengni Yang, Muyi Bao, Jimin Xiao, Anh Nguyen, Yutao Yue

Rectified Sparse Attention for Efficient Long-Sequence Generation (2026.findings-acl)

Challenge:	Existing 3D benchmarks lack fine-grained numerical reasoning task annotations, limiting MLLMs’ ability to perform precise spatial measurements and complex numerical reasoning.
Approach:	They propose a 3D-based benchmark to enhance indoor perceptual understanding by using multi-scale annotations and question-answer pairs.
Outcome:	The proposed benchmark improves indoor perceptual understanding by incorporating multi-scale annotations and question-answer pairs.

Copied to clipboard

Yutao Sun, Tianzhu Ye, Li Dong, Yuqing Xia, Jian Chen, Yizhao Gao, Shijie Cao, Jianyong Wang, Furu Wei

RACQC: Advanced Retrieval-Augmented Generation for Chinese Query Correction (2025.findings-emnlp)

Challenge:	Recent sparse decoding methods improve efficiency but suffer from KV cache misalignment, resulting in performance degradation.
Approach:	They propose a method that combines block-sparse attention with periodic dense rectification to bound error accumulation and preserve alignment with the pretraining distribution.
Outcome:	Experiments on math reasoning, language modeling, and retrieval tasks show that ReSA achieves near-lossless generation quality with significantly improved efficiency.

Copied to clipboard

Jinbo Su, Lingzhe Gao, Wei Li, Shihao Liu, Haojie Lei, Xinyi Wang, Yuanzhao Guo, Ke Wang, Daiting Shi, Dawei Yin

EX-FEVER: A Dataset for Multi-hop Explainable Fact Verification (2024.findings-acl)

Challenge:	Large language models (LLMs) exhibit remarkable capabilities across many tasks, but face critical challenges in the CSC scenario: (1) poor generalization to rare entities in open-domain searches; and (2) failure to adapt to temporal entity variations due to static parameters, resulting in serious over-correction issues.
Approach:	They propose a Chinese Spelling Check system with RAG and multi-task learning that integrates dynamic knowledge retrieval and entity-centric RAG to address rare entities.
Outcome:	The proposed system outperforms existing baselines in the CSC task and achieves a maximum improvement of +9.92% on the search scenario benchmark and +3.2% on the general-domain dataset.

Copied to clipboard

Huanhuan Ma, Weizhi Xu, Yifan Wei, Liuji Chen, Liang Wang, Qiang Liu, Shu Wu, Liang Wang

SEAD: Self-Evolving Agent for Multi-Turn Service Dialogue (2026.findings-acl)

Challenge:	Existing studies on fact verification lack a high-quality dataset for explainability . existing systems lack evidence retrieval and veracity prediction, limiting the ability to verify a claim .
Approach:	They propose a dataset for multi-hop explainable fact verification that summarises and modifies Wikipedia documents.
Outcome:	The proposed dataset aims to improve the accuracy of multi-hop explainable fact verification systems.

Copied to clipboard

Yuqin Dai, Ning Gao, Wei Zhang, Jie Wang, null Luozichen, Ruiyuan Wu, Jinpeng Wang, Chaozheng Wang

Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning (2022.findings-emnlp)

Challenge:	Large Language Models have demonstrated remarkable capabilities in open-domain dialogues, but their performance in service dialogues remains suboptimal.
Approach:	They propose a framework that enables agents to learn effective strategies without large-scale human annotations.
Outcome:	The proposed framework decouples user modeling into two components that provide adaptive training scenarios rather than acting as an unfair adversary.

Copied to clipboard

Yuxin Jiang, Linhan Zhang, Wei Wang

A Comprehensive Evaluation of Quantization Strategies for Large Language Models (2024.findings-acl)

Challenge:	Existing contrastive methods for learning universal sentence embeddings have limitations due to their over-parameterization and poor performance under domain shift settings.
Approach:	They propose to integrate an Energy-based Hinge loss to enhance the pairwise discriminative power of contrastive learning for sentence embeddings by combining PLMs with energy-based learning.
Outcome:	Empirical results show that the proposed method improves on seven standard semantic textual similarity tasks and a domain-shifted STS task.

Copied to clipboard

Renren Jin, Jiangcun Du, Wuwei Huang, Wei Liu, Jian Luan, Bin Wang, Deyi Xiong

EGSS: Entropy-guided Stepwise Scaling for Reliable Software Engineering (2026.acl-long)

Challenge:	Quantization studies have focused on instruction-tuned LLMs, leaving their performance on other benchmarks unclear.
Approach:	They propose a framework to evaluate quantized large language models using four dimensions . they propose to reduce the bits needed for model weights or activations with minimal performance loss .
Outcome:	The proposed framework can retain comparable performance to non-quantized LLMs on most benchmarks.

Copied to clipboard

Chenhui Mao, Yuanting Lei, Zhixiang Wei, Ming Liang, Zhixiang Wang, Jingxuan Xu, Dajun Chen, Wei Jiang, Yong Li

Language Scaling for Universal Suggested Replies Model (2021.naacl-industry)

Challenge:	Entropy-Guided Stepwise Scaling (EGSS) is a novel TTS framework for software engineering tasks.
Approach:	They propose an entropy-guided stepwise scaling framework that balances efficiency and effectiveness through entropic-guide encoding and robust test-suite augmentation.
Outcome:	EGSS boosts performance by 5–10% across all evaluated models, and reduces inference-time token usage by over 28% . compared to existing methods, EGS reduces token usage and reduce inference time by over 20% .

Copied to clipboard

Qianlan Ying, Payal Bajaj, Budhaditya Deb, Yu Yang, Wei Wang, Bojia Lin, Milad Shokouhi, Xia Song, Yang Yang, Daxin Jiang

AdaDHP: Fine-Grained Fine-Tuning via Dual Hadamard Product and Adaptive Parameter Selection (2025.acl-long)

Challenge:	We consider scaling automated suggested replies (SR) to multiple languages for a commercial email application.
Approach:	They propose a multi-lingual multi-task continual learning framework with auxiliary tasks and language adapters to train universal language representation across regions.
Outcome:	The proposed model reduces catastrophic forgetting and improves cross-lingual transfer across languages while reducing training costs.

Copied to clipboard

Han Liu, Changya Li, Xiaotong Zhang, Feng Zhang, Fenglong Ma, Wei Wang, Hong Yu

Memory-Guided Hard Data Augmentation for Multimodal Named Entity Recognition (2026.findings-acl)

Challenge:	Increasing number of parameters can be challenging under resource-constrained environments.
Approach:	They propose a parameter-efficient fine-tuning method with fewer parameters and finer granularity that can adaptively select important parameters for each task.
Outcome:	The proposed method can fine-tune important parameters for each task, while maintaining the same weights.

Copied to clipboard

Xinyu Liu, Kai fu, Yinghan Shi, Quanyou Chu, Ming Du, Hongya Wang, Xiaojun Meng, Jiansheng Wei, Yanghua Xiao, Bo Xu

AirConcierge: Generating Task-Oriented Dialogue via Efficient Large-Scale Knowledge Retrieval (2020.findings-emnlp)

Challenge:	Existing methods for Named Entity Recognition (NER) ignore the internal state of the target model.
Approach:	They propose a framework to repair model-specific errors by using a model-based approach . they employ cross-validation to identify model- specific Hard Data and a memory tree to induce macro-level error patterns from micro-level failures.
Outcome:	The proposed framework yields significant performance gains on Twitter and other platforms.

Copied to clipboard

Chieh-Yang Chen, Pei-Hsin Wang, Shih-Chieh Chang, Da-Cheng Juan, Wei Wei, Jia-Yu Pan

MMAC: A Multilingual, Multimodal Alignment Framework for Cultural Grounding Evaluation (2026.acl-long)

Challenge:	Existing neural task-oriented dialogue systems cannot be encoded by memory networks, such as memory networks.
Approach:	They propose an end-to-end trainable text-to SQL guided framework to learn a neural agent that interacts with KBs using the generated SQL queries.
Outcome:	The proposed method significantly improves on the AirDialogue dataset, which contains the conversations of customers booking flight tickets from the agent.

Copied to clipboard

Weihua Zheng, Zhengyuan Liu, Tanmoy Chakraborty, Weiwen Xu, Xiaoxue Gao, Bryan Chen Zhengyu Tan, Bowei Zou, Chang Liu, Yujia Hu, Xing Xie, Xiaoyuan Yi, Jing Yao, Chaojun Wang, Long Li, Rui Liu, Huiyao Liu, Koji Inoue, Ryuichi Sumida, Tatsuya Kawahara, Fan Xu, Lingyu Ye, Wei Tian, Dongjun Kim, Jimin Jung, Jaehyung Seo, Nadya Yuki Wangsajaya, Pham Minh Duc, Ojasva Saxena, Palash Nandi, Xiyan Tao, Wiwik Karlina, Tuan Luong, Keertana Arun Vasan, Roy Ka-Wei Lee, Nancy F. Chen

Detoxification for LLM: From Dataset Itself (2026.acl-long)

Challenge:	Existing models lack cultural alignment across modalities and languages . a new framework to assess cultural awareness across linguistics and languages is needed .
Approach:	They propose a framework that integrates tri-modally aligned cultural benchmarks and a five-dimensional evaluation protocol to assess cross-country awareness disparities.
Outcome:	The proposed framework assesses cultural awareness disparities across modalities and languages . it is the first dataset aligned at the input level across text, image, and speech .

Copied to clipboard

Wei Shao, Yihang Wang, Gao yu Zhu, Ziqiang Cheng, Lei Yu, Jiafeng Guo, Xueqi Cheng

Examining False Positives under Inference Scaling for Mathematical Reasoning (2025.emnlp-main)

Challenge:	Existing methods for large language models focus on post-training stage or inference time, while few tackle the source of toxicity, namely, the dataset itself.
Approach:	They propose to localize and rewrite toxic spans in raw corpora with SoCD, which guides an LLM to localized and preserving semantics while preserving toxicity.
Outcome:	The proposed method reduces TP from 0.42 to 0.18 and Expected Maximum Toxicity (EMT) from 0.43 to 0.20 on three LLMs.

Copied to clipboard

Yu Wang, Nan Yang, Liang Wang, Furu Wei, Fuli Feng

Focus-Constrained Attention Mechanism for CVAE-based Response Generation (2020.findings-emnlp)

Challenge:	Recent advances in language models have led to significant improvements in mathematical reasoning across benchmarks.
Approach:	They analyze the prevalence of false positives in language models by using heuristic evaluation methods . they find that false positive models produce correct final answers but with flawed deduction paths .
Outcome:	The proposed model performance improvements are based on the proposed model and its evaluation metrics.

Copied to clipboard

Zhi Cui, Yanran Li, Jiayi Zhang, Jianwei Cui, Chen Wei, Bin Wang

WR-One2Set: Towards Well-Calibrated Keyphrase Generation (2022.emnlp-main)

Challenge:	Existing models generate high-frequency but trivial responses such as "I don't know" or "I'm ok" due to the discrepancy in discourse-level information, standard models generate one-to-many relationships.
Approach:	They propose to transform coarse-grained discourse-level information into fine-grounded word-level knowledge by introducing a fine-grain focus signal and a focus-constrained attention mechanism to take full advantage of focus.
Outcome:	The proposed model can generate more diverse and informative responses compared with state-of-the-art models.

Copied to clipboard

Binbin Xie, Xiangpeng Wei, Baosong Yang, Huan Lin, Jun Xie, Xiaoli Wang, Min Zhang, Jinsong Su

Structural Bias for Aspect Sentiment Triplet Extraction (2022.coling-1)

Challenge:	Experimental results show that keyphrase generation has serious calibration errors . ONE2SET generates short phrases summarizing an input document .
Approach:	They propose a paradigm for keyphrase generation that generates short phrases summarizing an input document.
Outcome:	The proposed model over-estimates tokens and makes it well-calibrated on common datasets.

Copied to clipboard

Chen Zhang, Lei Ren, Fang Ma, Jingang Wang, Wei Wu, Dawei Song

From LLMs to MLLMs: Exploring the Landscape of Multimodal Jailbreaking (2024.emnlp-main)

Challenge:	Existing structural bias adapters for aspect sentiment triplet extraction are under-confident . a large-scale dataset for ASTE shows the adapter is effective and efficient to a larger scale.
Approach:	They propose to use a structural adapter to integrate structural bias into pretrained language models . they propose to add a relative position structure in place of the syntactic dependency structure .
Outcome:	The proposed adapter achieves state-of-the-art performance over strong baselines, but with a light parameter demand and low latency.

Copied to clipboard

Siyuan Wang, Zhuohan Long, Zhihao Fan, Zhongyu Wei

ADEPT-SQL: A High-performance Text-to-SQL Application for Real-World Enterprise-Level Databases (2025.acl-demo)

Challenge:	Recent advances in Large Language Models (LLMs) have demonstrated remarkable performance across various tasks, effectively following instructions to meet diverse user needs.
Approach:	They propose a framework for evaluation benchmarks and attack techniques for LLMs and MLLMs to enhance their security.
Outcome:	The proposed frameworks have been exploited to exploit the weaknesses of LLMs and MLLMs.

Copied to clipboard

Yongnan Chen, Zhuo Chang, Shijia Gu, Yuanhang Zong, Zhang Mei, Shiyu Wang, Hezixiang Hezixiang, Hongzhi Chen, Jin Wei, Bin Cui

Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents (2024.acl-long)

Challenge:	et al., 2017) address domain-specific knowledge barriers, schemas complexity, and computational costs of large LLMs.
Approach:	They propose a domain-adapted Text2SQL system that addresses critical deployment challenges in professional fields.
Outcome:	The proposed system achieves 97% execution accuracy on real-world databases . it is faster than existing systems and has a higher performance than existing ones.

Copied to clipboard

Shihan Deng, Weikai Xu, Hongda Sun, Wei Liu, Tao Tan, Liujianfeng Liujianfeng, Ang Li, Jian Luan, Bin Wang, Rui Yan, Shuo Shang

Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing (2024.emnlp-main)

Challenge:	Existing benchmarks for LLM-based mobile agents are insufficient to evaluate their capabilities.
Approach:	They propose a benchmark to evaluate LLM-based mobile agents' planning capabilities . they expand UI operations by incorporating 103 APIs to accelerate task completion .
Outcome:	The proposed benchmarks are based on 103 collected APIs and real user queries . the data is categorized into three distinct groups: SAST, SAMT, and MAMT .

Copied to clipboard

Weichuan Wang, Zhaoyi Li, Defu Lian, Chen Ma, Linqi Song, Ying Wei

MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving (2022.findings-naacl)

Challenge:	Existing studies have focused on using Large Language Models to improve translation quality . language mismatch and repetition are two of the main problems with LLMs .
Approach:	They propose to leverage model editing methods to reduce language mismatch and repetition . they propose to fetch intersections of locating results under different language settings .
Outcome:	The proposed methods reduce language mismatch and repetition ratios and enhance translation quality in most cases.

Copied to clipboard

Zhenwen Liang, Jipeng Zhang, Lei Wang, Wei Qin, Yunshi Lan, Jie Shao, Xiangliang Zhang

BotChat: Evaluating LLMs’ Capabilities of Having Multi-Turn Dialogues (2024.findings-naacl)

Challenge:	Existing work on math word problem solvers replace real numbers with symbolic placeholders to focus on logic reasoning.
Approach:	They propose to inject numerical properties into symbolic placeholders with contextualized representation learning schema to solve number representation dilemma.
Outcome:	The proposed model can solve MWP problems on English and Chinese benchmarks.

Copied to clipboard

Haodong Duan, Jueqi Wei, Chonghua Wang, Hongwei Liu, Yixiao Fang, Songyang Zhang, Dahua Lin, Kai Chen

ACORD: An Expert-Annotated Retrieval Dataset for Legal Contract Drafting (2025.acl-long)

Challenge:	Modern Large Language Models (LLMs) facilitate high-quality, multi-turn dialogues with humans, but human-based evaluation of such a capability requires substantial manual effort.
Approach:	They propose to evaluate LLMs' ability to emulate human-like, multi-turn conversations using an LLM-centric approach.
Outcome:	The proposed model emulates human-like, multi-turn conversations using an LLM-centric approach.

Copied to clipboard

Steven H Wang, Maksim Zubkov, Kexin Fan, Sarah Harrell, Yuyang Sun, Wei Chen, Andreas Plesner, Roger Wattenhofer

XFUND: A Benchmark Dataset for Multilingual Visually Rich Form Understanding (2022.findings-acl)

Challenge:	Contract clause retrieval is critical to contract drafting because of its high quality and complexity.
Approach:	They propose the first expert-annotated benchmark specifically designed for contract clause retrieval . ACORD focuses on complex contract clauses such as Limitation of Liability, Indemnification, Change of Control .
Outcome:	The atticus clause retrieval dataset shows promising results but needs improvement . the benchmark can be used as an IR benchmark for the NLP community .

Copied to clipboard

Yiheng Xu, Tengchao Lv, Lei Cui, Guoxin Wang, Yijuan Lu, Dinei Florencio, Cha Zhang, Furu Wei

Enhancing the Transferability of Jailbreak Attacks on Large Language Models via Exploiting Reparameterization Invariance (2026.acl-long)

Challenge:	Existing research on multimodal pre-training for visually rich document understanding tasks has focused on the English domain while neglecting the importance of multilingual generalization.
Approach:	They propose a multimodal pre-trained model for multilingual document understanding which bridges the language barriers for visually rich document understanding.
Outcome:	The proposed model outperforms existing cross-lingual pre-trained models on the XFUND dataset on visual document understanding tasks.

Copied to clipboard

Ao Wang, Xinghao Yang, Yongshun Gong, Wei Liu, Bao-di Liu, Weifeng Liu

Neural Response Generation with Meta-words (P19-1)

Challenge:	Existing token-level attacks have shown efficacy on open-source models but suffer from poor cross-model transferability.
Approach:	They propose a framework to improve cross-model transferability by modifying model parameters and generating update directions according to differences in output distributions rather than parameter-space distances.
Outcome:	The proposed framework improves cross-model transferability and success rates on open-source models.

Copied to clipboard

Can Xu, Wei Wu, Chongyang Tao, Huang Hu, Matt Schuerman, Ying Wang

Continual Event Extraction with Semantic Confusion Rectification (2023.emnlp-main)

Challenge:	Experimental results show that meta-words can be used to generate open domain dialogues . human-machine conversation is a fundamental problem in NLP .
Approach:	They propose a goal-tracking memory network that formalizes meta-word expression as a target in response generation and manages the generation process with a state memory panel and a controller.
Outcome:	The proposed model outperforms state-of-the-art generation models in response relevance, response diversity, and accuracy.

Copied to clipboard

Zitao Wang, Xinyi Wang, Wei Hu

SCOPE: Compress Mathematical Reasoning Steps for Efficient Automated Process Annotation (2025.findings-acl)

Challenge:	Existing studies focus on continual event extraction to extract incessantly emerging information . the semantic confusion on event types stems from the annotations of the same text being updated over time .
Approach:	They propose a continual event extraction model with semantic confusion rectification to reduce semantic confusion.
Outcome:	The proposed model outperforms state-of-the-art models and is proficient in imbalanced datasets.

Copied to clipboard

Huimin Xu, Xin Mao, Feng-Lin Li, Xiaobao Wu, Wang Chen, Wei Zhang, Anh Tuan Luu

PathQG: Neural Question Generation from Facts (2020.emnlp-main)

Challenge:	Existing process annotation approaches are computationally expensive.
Approach:	They propose a compression-based approach that transforms reasoning steps into code and normalizes them through Abstract Syntax Tree.
Outcome:	The proposed method outperforms existing methods on Best-of-N strategy and ProcessBench.

Copied to clipboard

Siyuan Wang, Zhongyu Wei, Zhihao Fan, Zengfeng Huang, Weijian Sun, Qi Zhang, Xuanjing Huang

Low-code LLM: Graphical User Interface over Large Language Models (2024.naacl-demo)

Challenge:	Existing research for question generation encodes text as a sequence of tokens without explicitly modeling fact information.
Approach:	They propose to incorporate facts in the input text for question generation in a comprehensive way.
Outcome:	The proposed model outperforms state-of-the-art models and human evaluation shows it generates relevant and informative questions.

Copied to clipboard

Yuzhe Cai, Shaoguang Mao, Wenshan Wu, Zehua Wang, Yaobo Liang, Tao Ge, Chenfei Wu, WangYou WangYou, Ting Song, Yan Xia, Nan Duan, Furu Wei

On-policy Reinforcement Fine-tuning with Offline reward for Multi-step Embodied Planning (2026.acl-long)

Challenge:	Low-code LLM is a visual programming interface that allows users to incorporate their ideas into the process without writing trivial prompts.
Approach:	They propose a human-LLM interaction framework that incorporates low-code visual programming interactions to achieve more controllable and stable responses.
Outcome:	The proposed framework enables users to incorporate ideas into the process without writing trivial prompts.

Copied to clipboard

Di Wu, Jiaxin Fan, Chloe Gu, Guanbo Wang, Wei Yin, Wenhao Li, Bo Jin

Learning Gender-Neutral Word Embeddings (D18-1)

Challenge:	Embodied planning requires agents to make coherent multi-step decisions based on dynamic visual observations and verbal goals.
Approach:	They propose an On-policy Reinforcement fine-tuning framework with offline rewards for Embodied Task Planning that preserves generalization benefits of RFT while addressing costly interaction and sparse rewards.
Outcome:	The proposed framework outperforms closed-source and online-RL methods on EmbodiedBench, a recent benchmark for interactive embodied tasks.

Copied to clipboard

Jieyu Zhao, Yichao Zhou, Zeyu Li, Wei Wang, Kai-Wei Chang

Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety (2026.acl-long)

Challenge:	Word embeddings trained on human-generated corpora inherit strong gender stereotypes . prior studies show such embeddables exhibit social biases, such as gender stereotype .
Approach:	They propose a method to preserve gender information in certain dimensions of word vectors . they propose GN-GloVe, which is a gender-neutral variant of the word embedding model .
Outcome:	The proposed method preserves gender information in certain dimensions of word vectors while compelling other dimensions to be free of gender influence.

Copied to clipboard

Can Jin, Rui Wu, Tong Che, Qixin Zhang, Hongwu Peng, Jiahui Zhao, Zhenting Wang, Wenqi Wei, Ligong Han, Zhao Zhang, Yuan Cao, Ruixiang Tang, Dimitris N. Metaxas

Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models (2021.emnlp-main)

Challenge:	OpenAI introduces deliberative alignment (DA) to enhance safety of its o-series models, but effectiveness of this approach in open-source LLMs is understudied.
Approach:	They propose a case-augmented deliberative alignment method for large language models . they propose to use reinforcement learning on self-generated safety reasoning chains .
Outcome:	The proposed method avoids narrowly enumerated rules and allows broader adaptability.

Copied to clipboard

Kun Zhou, Wayne Xin Zhao, Sirui Wang, Fuzheng Zhang, Wei Wu, Ji-Rong Wen

DGPO: Beyond Pairwise Preferences with Directional Consistent Groupwise Optimization (2026.findings-acl)

Challenge:	Recent studies have shown that powerful pre-trained language models can be fooled by small perturbations or intentional attacks.
Approach:	They propose a framework for fine-tuning PLMs using a masked language model and Gaussian noise to augment semantically relevant examples with sufficient diversity.
Outcome:	The proposed framework improves the robustness of pre-trained language models and alleviates performance degradation under adversarial attacks.

Copied to clipboard

Mengyi Deng, Zhiwei Li, Xin Li, Tingyu Zhu, Yulan Yuan, Zhijiang Guo, Wei Wang

Assessing Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks (2025.acl-long)

Challenge:	Existing methods for directional consistency alignment of large language models are limited . a recent study suggests reverse supervision as a complement to forward reasoning .
Approach:	They propose a framework that aggregates supervision signals at the group level and explicitly models direction-aware alignment through multi-candidate comparisons.
Outcome:	The proposed framework achieves 3.2% accuracy improvement across five benchmarks and multiple datasets.

Copied to clipboard

Fangru Lin, Shaoguang Mao, Emanuele La Malfa, Valentin Hofmann, Adrian de Wynter, Xun Wang, Si-Qing Chen, Michael J. Wooldridge, Janet B. Pierrehumbert, Furu Wei

Global Eye: Breaking the “Fixed Thinking Pattern” during the Instruction Expansion Process (2025.acl-long)

Challenge:	a study aims to assess the fairness and robustness of Large Language Models in dialectal queries . speakers of "non-standard" dialects are known to experience implicit and explicit discrimination .
Approach:	They propose to use a benchmark to assess the fairness of large language models in dialects . they hire speakers with computer science backgrounds to rewrite seven popular benchmarks based on AAVE .
Outcome:	The proposed benchmarks show that most models show significant brittleness and unfairness to queries in AAVE.

Copied to clipboard

Wenxuan Lu, Wei Liu, Jian Luan, Bin Wang, Songhao Jiang, Tianning Zang

Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders (2020.emnlp-main)

Challenge:	Existing methods focus on constructing multi-perspective prompts to expand instructions, overlooking the “Fixed Thinking Pattern” issue of Large Language Models.
Approach:	They propose a method that analyzes the statistical characteristics of newly generated instructions and updates the prompts after a fixed number of instruction expansions.
Outcome:	The proposed method surpasses open-source LLMs and GPT3.5 in several metrics.

Copied to clipboard

Jue Wang, Wei Lu

PROSE: A Pronoun Omission Solution for Chinese-English Spoken Language Translation (2023.emnlp-main)

Challenge:	Named entity recognition and relation extraction are two important fundamental problems.
Approach:	They propose to design two separate encoders to capture two different types of information in the representation learning process.
Outcome:	The proposed methods show significant improvements on standard datasets.

Copied to clipboard

Ke Wang, Xiutian Zhao, Yanghui Li, Wei Peng

Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study (2025.naacl-long)

Challenge:	Pro-drop (‘pronoun-dropping’) language requires NMT systems to recover omitted pronouns, but this task lacks sufficient datasets for benchmarking .
Approach:	They propose a benchmarking method that leverages the semantic embedding of dropped pronouns to augment training pairs to alleviate the negative impact introduced by pro-drop .
Outcome:	The proposed method outperforms existing methods regarding omitted pronoun retrieval and overall translation quality on four Chinese-English translation corpora.

Copied to clipboard

Menglong Cui, Pengzhi Gao, Wei Liu, Jian Luan, Bin Wang

Tackling Modality Heterogeneity with Multi-View Calibration Network for Multimodal Sentiment Detection (2023.acl-long)

Challenge:	Large language models (LLMs) have shown continuously improving multilingual capabilities.
Approach:	They evaluate the ability of open LLMs to handle multilingual machine translation tasks using a parallel-first monolingual-second data mixing strategy.
Outcome:	The proposed model outperforms state-of-the-art models and achieves competitive performance with Google Translate and GPT-4-turbo.

Copied to clipboard

Yiwei Wei, Shaozu Yuan, Ruosong Yang, Lei Shen, Zhangmeizhi Li, Longbiao Wang, Meng Chen

Multi-Objective Forward Reasoning and Multi-Reward Backward Refinement for Product Review Summarization (2024.lrec-main)

Challenge:	Existing studies focus on fusing different features but ignore the challenge of modality heterogeneity.
Approach:	They propose a text-guided fusion module with novel Sparse-Attention to reduce the negative impacts of redundant visual elements and a sentiment-based congruity constraint task to calibrate the feature shift in the representation space.
Outcome:	The proposed model is competitive against existing methods and achieves state-of-the-art results on two public benchmark datasets.

Copied to clipboard

Libo Sun, Siyuan Wang, Meng Han, Ruofei Lai, Xinyu Zhang, Xuanjing Huang, Zhongyu Wei

Compressing then Matching: An Efficient Pre-training Paradigm for Multimodal Embedding (2026.acl-long)

Challenge:	Product review summarization aims to generate a concise summary based on product reviews . factual accuracy, aspect comprehensiveness, and content relevance are challenges .
Approach:	They propose an FB-Thinker framework to improve product review summarization ability . they propose two Chinese product review summary datasets for instruction-tuning and evaluation .
Outcome:	The proposed framework improves product review summarization with forward reasoning and backward refinement.

Copied to clipboard

Da Li, Yuxiao Luo, Keping Bi, Jiafeng Guo, Wei Yuan, Biao Yang, Yan Wang, Fan Yang, Tingting Gao, Guorui Zhou

TermDiffuSum: A Term-guided Diffusion Model for Extractive Summarization of Legal Documents (2025.coling-main)

Challenge:	Recent approaches demonstrate that MLLMs can be adapted into competitive embedding models via large-scale contrastive learning.
Approach:	They propose a compressed pre-training phase which serves as a warm-up stage for contrastive learning.
Outcome:	The proposed model achieves state-of-the-art among MLLMs of comparable size on the MMEB, realizing optimization in both efficiency and effectiveness.

Copied to clipboard

Xiangyun Dong, Wei Li, Yuquan Le, Zhangyue Jiang, Junxi Zhong, Zhong Wang

Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models (2026.acl-long)

Challenge:	Recent studies have explored diffusion models for extractive summarization task, showcasing their remarkable capabilities.
Approach:	They propose a term-guided diffusion model for extractive summarization of legal documents that incorporates legal terminology into the model via a well-designed multifactor fusion noise weighting schedule.
Outcome:	The proposed model outperforms existing models on a self-constructed legal summarization dataset and achieves improvements of 3.10, 2.84, and 2.89 on three public datasets.

Copied to clipboard

Wei Wu, Liyi Chen, Congxi Xiao, Tianfu Wang, Qimeng Wang, Chengqiang Lu, Yan Gao, null Yiwu, Yao Hu, Hui Xiong

See the World, Discover Knowledge: A Chinese Factuality Evaluation for Large Vision Language Models (2025.findings-acl)

Challenge:	Existing efficient reasoning methods rely on explicit length penalties for excessive verbosity on simple queries.
Approach:	They propose a training-time intervention that selectively suppresses redundant tokens . they find length shift occurs when models generate unnecessary reasoning on trivial inputs - a phenomenon that is often unexplored .
Outcome:	The proposed method reduces inference token usage by 78% while increasing accuracy compared to the initial policy and surpasses state-of-the-art efficient reasoning methods.

Copied to clipboard

Jihao Gu, Yingyao Wang, Pi Bu, Chen Wang, Ziming Wang, Tengtao Song, Donglai Wei, Jiale Yuan, Yingxiu Zhao, Yancheng He, Shilong Li, Jiaheng Liu, Meng Cao, Jun Song, Yingshui Tan, Xiang Li, Wenbo Su, Xiaoyong Zhu, Bo Zheng

DREAM: Improving Video-Text Retrieval Through Relevance-Based Augmentation Using Large Foundation Models (2025.naacl-long)

Challenge:	Existing models for large vision language models do not fully reflect their knowledge capacity and reliability, resulting in erroneous outputs that do not align with the image content or provide answers lacking knowledge evidence.
Approach:	They propose a Chinese-based benchmark for visual factuality across 8 major topics and 56 subtopics and a multi-hop question construction.
Outcome:	The proposed model decouples visual factuality into two parts: seeing the world and discovering knowledge.

Copied to clipboard

Yimu Wang, Shuai Yuan, Bo Xue, Xiangru Jian, Wei Pang, Mushi Wang, Ning Yu

CoIR: A Comprehensive Benchmark for Code Information Retrieval Models (2025.acl-long)

Challenge:	Recent advances in video-text retrieval models have limited training data annotations.
Approach:	They propose a Video-Text Retrieval Paradigm with Relevance-based Augmentation which enhances video and text data using large foundation models to learn more generalized features.
Outcome:	The proposed method improves video-text retrieval performance over existing methods.

Copied to clipboard

Xiangyang Li, Kuicai Dong, Yi Quan Lee, Wei Xia, Hao Zhang, Xinyi Dai, Yasheng Wang, Ruiming Tang

Automatic Article Commenting: the Task and Dataset (P18-2)

Challenge:	Existing methods and benchmarks for information retrieval are inadequately representing the diversity of code in various domains and tasks.
Approach:	They propose a benchmark specifically designed to assess code retrieval capabilities.
Outcome:	The proposed benchmark aims to invigorate research in the code retrieval domain . it shares the same data schema as other popular benchmarks like MTEB and BEIR .

Copied to clipboard

Lianhui Qin, Lemao Liu, Wei Bi, Yan Wang, Xiaojiang Liu, Zhiting Hu, Hai Zhao, Shuming Shi

Challenge:	Existing methods to make comments on articles are based on human-annotated subsets, but they are not suitable for online forums.
Approach:	They propose to use a large-scale Chinese corpus with millions of real comments and a human-annotated subset characterizing the comments’ varying quality to generalize a broad set of popular reference-based metrics.
Outcome:	The proposed model incorporates human-annotated subset characterizing the comments’ varying quality and shows that it is more accurate than previous models.

FlashAudio: Rectified Flow for Fast and High-Fidelity Text-to-Audio Generation (2025.acl-long)

Copied to clipboard

Huadai Liu, Jialei Wang, Rongjie Huang, Yang Liu, Heng Lu, Zhou Zhao, Wei Xue

Democratizing Reasoning Ability: Tailored Learning from Large Language Model (2023.emnlp-main)

Challenge:	Recent advances in latent diffusion models (LDMs) have markedly enhanced text-to-audio generation, yet their iterative sampling processes impose substantial computational demands, limiting practical deployment.
Approach:	They propose to learn straight flow for fast simulation by using flashAudio with rectified flows and immiscible flow to minimize the total distance of data-noise pairs in a batch vias assignment.
Outcome:	The proposed method can learn straight flow for fast simulations and reduce noise distribution.

Copied to clipboard

Zhaoyang Wang, Shaohan Huang, Yuxuan Liu, Jiahai Wang, Minghui Song, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang

GNN-encoder: Learning a Dual-encoder Architecture via Graph Neural Networks for Dense Passage Retrieval (2022.findings-emnlp)

Challenge:	Large language models (LLMs) exhibit impressive emergent abilities in natural language processing, but their democratization is hindered due to huge computation requirements and closed-source nature.
Approach:	They propose a tailored learning approach to distill the exclusive reasoning ability to smaller LMs to facilitate democratization.
Outcome:	The proposed approach enables the democratization of the exclusive reasoning ability by leveraging the black-box model as a reasoning teacher.

Copied to clipboard

Jiduan Liu, Jiahao Liu, Yang Yang, Jingang Wang, Wei Wu, Dongyan Zhao, Rui Yan

Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual Enhancement (2026.acl-long)

Challenge:	Existing approaches to perform large-scale query-passage retrieval are term-based, but they lose interaction between query-pastage pairs.
Approach:	They propose to fuse query (passage) information into query representations via graph neural networks that are constructed by queries and their top retrieved passages.
Outcome:	The proposed model outperforms existing models on MSMARCO, Natural Questions and TriviaQA datasets and achieves the new state-of-the-art on these datasets.

Copied to clipboard

Zhenxin Qin, Qiang Li, Qingzhuo Wang, Ruiyang Qin, Zhihua Wei, Wen Shen

ASAP: A Chinese Review Dataset Towards Aspect Category Sentiment Analysis and Rating Prediction (2021.naacl-main)

Challenge:	Existing research has focused on mitigating object hallucinations but often overlooks more complex relation hallucines, especially action relations involving interactions between objects.
Approach:	They propose a framework to locate action-relevant image regions and enhance the LVLM’s attention to those regions by using a Relation-aware Visual Enhancement method.
Outcome:	The proposed method achieves superior performance in mitigating action-relation hallucinations with negligible additional inference cost.

Copied to clipboard

Jiahao Bu, Lei Ren, Shuang Zheng, Yang Yang, Jingang Wang, Fuzheng Zhang, Wei Wu

Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation (2025.coling-main)

Challenge:	Sentiment analysis is a key task in e-commerce to detect fine-to-coarse sentiment polarities.
Approach:	They propose to use a large-scale Chinese restaurant review dataset ASAP to investigate the sentiment polarities underlying user reviews.
Outcome:	The proposed model outperforms state-of-the-art models on both tasks.

Copied to clipboard

Siyuan Wang, Zhuohan Long, Zhihao Fan, Xuanjing Huang, Zhongyu Wei

Odysseus Navigates the Sirens’ Song: Dynamic Focus Decoding for Factual and Diverse Open-Ended Text Generation (2025.acl-long)

Challenge:	Recent advances in Large Language Models have demonstrated remarkable performance across tasks.
Approach:	They propose a benchmark self-evolving framework to dynamically evaluate rapidly advancing Large Language Models.
Outcome:	The proposed framework extends existing benchmarks to extend models across tasks and tasks.

Copied to clipboard

Wen Luo, Feifan Song, Wei Li, Guangyue Peng, Shaohang Wei, Houfeng Wang

GAPO: Robust Advantage Estimation for Real-World Code LLMs (2026.findings-acl)

Challenge:	Existing decoding methods struggle to balance factuality and diversity . Deterministic decoding approaches suffer from degeneration and lack of diversity - a problem that is not addressed by the current literature.
Approach:	They propose a plug-and-play stochastic approach that adjusts decoding focus based on distributional differences across layers, leveraging the modular nature of factual knowledge within LLMs.
Outcome:	Extensive experiments on seven datasets show that DFD significantly improves performance.

Copied to clipboard

Jianqing Zhang, Zhezheng Hao, Wei Xia, Hande Dong, Hong Wang, Chenxing Wei, Yuyan Zhou, Yubin Qi, Qiang Lin, Jian Cao

Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner (2022.findings-naacl)

Challenge:	Reinforcement learning (RL) is widely used for post-training large language models (LLMs) in code editing, but in real-world code editing scenarios, reward distributions are often skewed with unpredictable noise, leading to distorted advantage computation and increased rollout outliers.
Approach:	They propose a group-relative method that finds an interval with the highest SNR and uses the median of that interval as an adaptive Q to replace the group mean in advantage calculation.
Outcome:	The proposed method improves on nine instruction-tuned LLMs while remaining plug-and-play and efficient.

Copied to clipboard

Danilo Neves Ribeiro, Shen Wang, Xiaofei Ma, Rui Dong, Xiaokai Wei, Henghui Zhu, Xinchi Chen, Peng Xu, Zhiheng Huang, Andrew Arnold, Dan Roth

GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models (2025.acl-long)

Challenge:	Large language models have achieved high performance on various natural language benchmarks, but the explainability of their output remains elusive.
Approach:	They propose an architecture called iterative retrieval-generation reasoner that generates an entailment tree that explains a given hypothesis by using premises from C.
Outcome:	The proposed model outperforms existing benchmarks on premise retrieval and entailment tree generation with around 300% gain in overall correctness.

Copied to clipboard

Kai Yao, Zhaorui Tan, Penglei Gao, Lichun Li, Kaixin Wu, Yinggui Wang, Yuan Zhao, Yixin Ji, Jianke Zhu, Wei Wang

ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents (2025.acl-long)

Challenge:	Existing methods for offsite-tuning of large language models require high computational costs and lack theoretical analysis.
Approach:	They propose an offsite-tuning approach that selectively applies compression techniques such as rank compression and channel pruning to preserve the gradients of fine-tuned adapters while ensuring privacy.
Outcome:	The proposed method surpasses existing OT methods in privacy protection and model performance.

Copied to clipboard

Zhigen Li, Jianxiang Peng, Yanmeng Wang, Yong Cao, Tianhao Shen, Minghui Zhang, Linxi Su, Shang Wu, Yihang Wu, YuQian Wang, Ye Wang, Wei Hu, Jianfeng Li, Shaojun Wang, Jing Xiao, Deyi Xiong

AdaSwitch: Adaptive Switching between Small and Large Agents for Effective Cloud-Local Collaborative Learning (2024.emnlp-main)

Challenge:	Existing models that use Large Language Models (LLMs) show superior performance in various tasks, but lack of controllability leads to unfocused conversations or task failure.
Approach:	They propose a standard operating procedure (SOP) framework to regulate dialogue flow by integrating Chain of Thought reasoning and supervised fine-tuning for SOP prediction.
Outcome:	The proposed method achieves a 27.95% improvement in action accuracy compared to baseline models based on GPT-3.5 and also shows notable gains for open-source models.

Copied to clipboard

Hao Sun, Jiayi Wu, Hengyi Cai, Xiaochi Wei, Yue Feng, Bo Wang, Shuaiqiang Wang, Yan Zhang, Dawei Yin

Forget the Token and Pixel: Rethinking Gradient Ascent for Concept Unlearning in Multimodal Generative Models (2025.findings-acl)

Challenge:	Recent advances in large language models have been remarkable . users face a choice between using cloud-based LLMs for generation quality or local-based ones for lower computational cost .
Approach:	They propose a new LLM utilization paradigm that facilitates collaborative operation . they evaluate AdaSwitch across 7 benchmarks and compare it to other LLMs .
Outcome:	The proposed model improves performance of local and cloud agents across 7 benchmarks . it achieves competitive results compared to the cloud agent while utilizing less computational overhead.

Copied to clipboard

Jiaqi Li, Chuanyi Zhang, Miaozeng Du, Hui Zhang, Yongrui Chen, Qianshan Wei, Junfeng Fang, Ruipeng Wang, Sheng Bi, Guilin Qi

Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better (2026.findings-acl)

Challenge:	Gradient Ascent (GA) has emerged as a promising approach for concept unlearning in Multimodal Generative Models (MGMs).
Approach:	They propose a novel approach that selectively applies GA to targeted Conceptual Knowledge while preserving Natural Knowledge through Gradient Descent (GD).
Outcome:	The proposed approach removes Conceptual Knowledge and inadvertently diminishes Natural Knowledge, resulting in utility degradation.

Copied to clipboard

Dianyi Wang, Wei Song, Yikun Wang, Siyuan Wang, Kaicheng Yu, Zhongyu Wei, Jiaqi Wang

CLOWER: A Pre-trained Language Model with Contrastive Learning over Word and Character Representations (2022.coling-1)

Challenge:	Typical large vision-language models emphasize vision-to-language alignment while overlooking fine-grained visual information.
Approach:	They introduce autoregressive semantic visual reconstruction (ASVR) that enables joint learning of visual and textual modalities within a unified autoregression framework.
Outcome:	The proposed model improves baselines and multimodal understanding benchmarks by 2-3%.

Copied to clipboard

Borun Chen, Hongyin Tang, Jiahao Bu, Kai Zhang, Jingang Wang, Qifan Wang, Hai-Tao Zheng, Wei Wu, Liqian Yu

SAMoRA: Semantic-Aware Mixture of LoRA Experts for Task-Adaptive Learning (2026.findings-acl)

Challenge:	Pre-trained language models (PLMs) have achieved remarkable performance gains across numerous downstream tasks in natural language understanding.
Approach:	They propose a Chinese pre-trained language model that implicitly encodes words into characters . they propose 'contrastive learning over word' and 'character' representations to improve learning .
Outcome:	The proposed model can encode words into fine-grained representations without modification of production pipelines.

Copied to clipboard

Boyan Shi, Wei Chen, Shuyuan Zhao, Junfeng Shen, Shengnan Guo, Shaojiang Wang, Huaiyu Wan

PLAWBENCH: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice (2026.acl-long)

Challenge:	Existing methods for multitask learning fail to match input semantics with expert capabilities, leading to weak expert specialization.
Approach:	They propose a parameter-efficient mixture-of-experts framework for task-adaptive learning that aligns textual semantics with the most suitable experts for precise routing.
Outcome:	The proposed framework outperforms the state-of-the-art methods and holds excellent task generalization capabilities.

Copied to clipboard

Yuzhen Shi, Huanghai Liu, Yiran HU, Song Gaojie, Xu Xinran, Yubo Ma, Tianyi Tang, Li Zhang, Qingjing Chen, Feng Di, Wenbo Lv, Weiheng Wu, Kexin Yang, Sen Yang, Wei Wang, Rongyao Shi, Qiu Yuanyang, Yuemeng Qi, Zhang Jingwen, Sui Xiaoyu, Yifan Chen, Zhang Yi, An Yang, Bowen Yu, Dayiheng Liu, Junyang Lin, Weixing Shen, Bing Zhao, Charles L. A. Clarke, HU Wei

GTR-LSTM: A Triple Encoder for Sentence Generation from RDF Data (P18-1)

Challenge:	Existing benchmarks for large language models (LLMs) are coarse, single-dimensional metrics and do not explicitly assess fine-grained legal reasoning.
Approach:	They propose a Practical Law Benchmark to evaluate large language models in real-world legal practice scenarios.
Outcome:	The proposed model is based on 850 questions and 13 scenarios with expert-designed evaluation rubrics.

Copied to clipboard

Bayu Distiawan Trisedya, Jianzhong Qi, Rui Zhang, Wei Wang

Large Language Models and Causal Inference in Collaboration: A Comprehensive Survey (2025.findings-naacl)

Challenge:	Knowledge bases are becoming an enabling resource for many applications including Q&A systems, recommender systems, and summarization tools.
Approach:	They propose a system to translate RDF triples into natural sentences using an encoder-decoder framework.
Outcome:	The proposed model outperforms the baseline model by 17.6%, 6.0%, and 16.4% in terms of BLEU, METEOR, and TER scores.

Copied to clipboard

Xiaoyu Liu, Paiheng Xu, Junda Wu, Jiaxin Yuan, Yifan Yang, Yuhang Zhou, Fuxiao Liu, Tianrui Guan, Haoliang Wang, Tong Yu, Julian McAuley, Wei Ai, Furong Huang

Why Did Apple Fall: Evaluating Curiosity in Large Language Models (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have shown great potential to enhance Natural Language Processing (NLP) models in areas such as predictive accuracy, fairness, robustness, and explainability.
Approach:	They evaluate or improve generative Large Language Models from a causal perspective in areas such as reasoning capacity, fairness and safety issues, explainability, and handling multimodality.
Outcome:	The proposed models can be used to perform causal relationship discovery and causal effect estimation tasks.

Copied to clipboard

Haoyu Wang, Sihang Jiang, Yuyan Chen, Yitong Wang, Xiaojun Meng, Jiansheng Wei, Yanghua Xiao

TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization (2025.findings-acl)

Challenge:	Existing methods for evaluating curiosity-like behaviors in large language models lack curiosity-inspired features.
Approach:	They propose a psychology-inspired framework to evaluate curiosity in large language models . they adapt the Five-Dimensional Curiosity scale Revised (5DCR) to LLMs .
Outcome:	The proposed framework evaluates curiosity in large language models using questionnaires and behavioral studies.

Copied to clipboard

Dingyu Yao, Bowen Shen, Zheng Lin, Wei Liu, Jian Luan, Bin Wang, Weiping Wang

Challenge:	Existing work mitigates memory overhead by offloading or compressing the Key-Value cache.
Approach:	They propose a method that integrates quantization and offloading into a generative large language model by using a hybrid compression method.
Outcome:	The proposed method outperforms the state-of-the-art in long-context evaluations.

Zero-shot Cross-lingual Transfer of Prompt-based Tuning with a Unified Multilingual Prompt (2022.emnlp-main)

Copied to clipboard

Lianzhe Huang, Shuming Ma, Dongdong Zhang, Furu Wei, Houfeng Wang

Beyond Quantity: Trajectory Diversity Scaling for Code Agents (2026.findings-acl)

Challenge:	Existing work focuses on monolingual prompts, but we study multilingual prompt for multilingual models.
Approach:	They propose a model that uses a unified prompt for all languages, called UniPrompt, to alleviate the effort of designing different prompts for multiple languages.
Outcome:	The proposed model outperforms baseline models in the zero-shot cross-lingual setting.

Copied to clipboard

Guhong Chen, Chenghao Sun, Cheng Fu, Qiyao Wang, Zhihong Huang, ChaoPeng Wei, Guangxu Chen, Feiteng Fang, Ahmadreza Argha, Bing Zhao, Xander Xu, Qi Han, Hamid Alinejad-Rokny, Qiang Qu, Binhua Li, Shiwen Ni, Min Yang, HU Wei, Yongbin Li

DeepWell-Adol: A Scalable Expert-Based Dialogue Corpus for Adolescent Positive Mental Health and Wellbeing Promotion (2025.emnlp-main)

Challenge:	Code large language models (LLMs) are becoming tool-interactive agents . quantity-centric scaling exhibits an early bottleneck that underutilizes trajectory data . et al.: a new approach to scale trajectory diversity improves tool-use generalization .
Approach:	They propose a Trajectory Diversity Scaling-based data synthesis framework for code agents that scales performance through diversity rather than raw volume.
Outcome:	Experiments on general tool-use benchmarks and code agent tasks show that TDScaling improves tool-user generalization and inherent coding proficiency.

Copied to clipboard

Wenyu Qiu, Yuxiong Wang, Jiajun Tan, Hanchao Hou, Qinda Liu, Wei Yao, Shiguang Ni

Agent-GWO: Collaborative Agents for Dynamic Prompt Optimization in Large Language Models (2026.findings-acl)

Challenge:	Promoting positive mental health and well-being is a critical yet underexplored area in natural language processing.
Approach:	They propose a Chinese dialogue corpus grounded in positive psychology and coaching that integrates human expert-written seed data with automated data augmentation to ensure high quality and scalability.
Outcome:	The proposed corpus meets general standards for psychological dialogue and emotional support while also showing superior performance across multiple models in promoting positive psychological processes, character strengths, interpersonal relationships, and healthy behaviors.

Copied to clipboard

Xudong Wang, Chaoning Zhang, Chenghao Li, Shuxu Chen, Qigan Sun, Jiaquan Zhang, Fachrina Dewi Puspitasari, Tae-Ho Kim, Jiwei Wei, Malu Zhang, Guoqing Wang, Yang Yang, Heng Tao Shen

Instruction Data Selection via Answer Divergence (2026.acl-long)

Challenge:	Existing automatic prompt optimization methods fail to optimize prompts and decoding hyperparameters within a unified framework to achieve stable global improvements.
Approach:	They propose a dynamic prompt optimization framework for complex reasoning that unifies prompt templates and decodes hyperparameters as inheritable agent configurations.
Outcome:	Experiments on multiple mathematical and hybrid reasoning benchmarks show that Agent-GWO improves accuracy and stability over existing prompt optimization methods.

Copied to clipboard

Bo Li, Mingda Wang, Shikun Zhang, Wei Ye

Challenge:	Existing methods for instruction tuning use data-centric methods, but they do not explicitly reflect what a particular base model is missing.
Approach:	They propose a method for instruction tuning that uses geometric structure of multi-sample outputs to select instruction data.
Outcome:	The proposed approach outperforms strong selectors on six benchmarks spanning reasoning, knowledge, and coding.

Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding (2023.acl-long)

Copied to clipboard

Haoli Bai, Zhiguang Liu, Xiaojun Meng, Li Wentao, Shuang Liu, Yifeng Luo, Nian Xie, Rongfu Zheng, Liangwei Wang, Lu Hou, Jiansheng Wei, Xin Jiang, Qun Liu

Don’t Forget Your Reward Values: Language Model Alignment via Value-based Calibration (2024.emnlp-main)

Challenge:	Existing solutions for visual document understanding lack granularity of document textlines.
Approach:	They propose a supervised pre-training program to leverage structural knowledge nested in document textlines to achieve fine-grained alignment between visual regions and texts.
Outcome:	The proposed system performs better on various VDU tasks in English and Chinese.

Copied to clipboard

Xin Mao, Feng-Lin Li, Huimin Xu, Wei Zhang, Wang Chen, Anh Tuan Luu

Zer0-Jack: A memory-efficient gradient-based jailbreaking method for black box Multi-modal Large Language Models (2026.eacl-long)

Challenge:	Existing methods for generating large language models have been criticized for their complexity and instability.
Approach:	They propose a value-based calibration method to better align Large Language Models with human preferences.
Outcome:	The proposed method surpasses existing methods on AI assistant and summarization datasets, providing impressive generalizability, robustness, and diversity in different settings.

Copied to clipboard

Tiejin Chen, Kaishen Wang, Hua Wei

Proving membership in LLM pretraining data via data watermarks (2024.findings-acl)

Challenge:	Multi-modal large language models are highly vulnerable to jailbreak attacks due to their additional modality.
Approach:	They propose a black-box jailbreak framework based on zeroth-order optimization . they propose generating malicious images and patch-wise block coordinate descent .
Outcome:	The proposed framework achieves 98.2% success on MiniGPT-4 and 95% on the Harmful Behaviors Multi-modal dataset while jailbreaking commercial models such as GPT-4o.

Copied to clipboard

Johnny Wei, Ryan Wang, Robin Jia

Multi-Agent Simulator Drives Language Models for Legal Intensive Interaction (2025.findings-naacl)

Challenge:	Detecting whether copyright holders’ works were used in large language model (LLM) training is poised to be an important problem.
Approach:	They propose to use data watermarks to enable principled detection with only black-box model access, provided the rightholder contributed multiple training documents and watermarked them before public release.
Outcome:	The proposed method can be used to test hypothesis testing on a black-box model . it shows that the watermarks are strong under model and dataset scaling .

Copied to clipboard

ShengbinYue ShengbinYue, Ting Huang, Zheng Jia, Siyuan Wang, Shujun Liu, Yun Song, Xuanjing Huang, Zhongyu Wei

CHAE: Fine-Grained Controllable Story Generation with Characters, Actions and Emotions (2022.coling-1)

Challenge:	Large Language Models (LLMs) have advanced legal intelligence, but the scarcity of scenario data impedes the progress toward interactive legal scenarios.
Approach:	They propose a Multi-agent Legal Simulation Driver to generate synthetic data by simulating interactive legal scenarios.
Outcome:	The proposed framework ensures consistency of legal attributes between participants and introduces a supervisory mechanism to align participants’ characters and behaviors as well as addressing distractions.

Copied to clipboard

Xinpeng Wang, Han Jiang, Zhihua Wei, Shanlin Zhou

Improving Embedding-based Large-scale Retrieval via Label Enhancement (2021.findings-emnlp)

Challenge:	Existing studies on story generation focus on coarse-grained control of the story, neglecting the details of the narrative.
Approach:	They propose a model for fine-grained control on the story that allows the generation of customized stories with characters, corresponding actions and emotions arbitrarily assigned.
Outcome:	The proposed method has strong controllability to generate customized stories according to the fine-grained personalized guidance.

Copied to clipboard

Peiyang Liu, Xi Wang, Sen Wang, Wei Ye, Xiangyu Xi, Shikun Zhang

Both Matter: Enhancing the Emotional Intelligence of Large Language Models without Compromising the General Intelligence (2024.findings-acl)

Challenge:	Existing methods for large-scale retrieval are trained with 0-1 hard labels that indicate whether a query is relevant to a document, ignoring rich information of the relevance degree.
Approach:	They propose to introduce label enhancement for the first time to characterize query-document relevance degree by embedding label distribution into contextual embeddables.
Outcome:	The proposed method significantly outperforms existing retrieval models and its counterparts equipped with two alternative methods on English and Chinese large-scale retrieval tasks.

Copied to clipboard

Weixiang Zhao, Zhuojun Li, Shilong Wang, Yang Wang, Yulin Hu, Yanyan Zhao, Chen Wei, Bing Qin

Can LLMs Hear the Dogwhistle? (2026.findings-acl)

Challenge:	Emotional Intelligence (EI) is a key concept in the field of human intelligence.
Approach:	They propose a method to enhance EI of large language models by naive fine-tuning on EI-related tasks.
Outcome:	The proposed method improves EI of two LLM-based assistants without compromising GI.

Copied to clipboard

Yifan Liu, Yi Lin, Xinwei Guo, Ziwei Wang, Jiaxin Zhang, Guanhua Chen, Haiyan Wu, Xiangyu Zhao, Xin Yao, Xuetao Wei

SpeechMedAssist: Efficiently and Effectively Adapting Speech Language Models for Medical Consultation (2026.acl-long)

Challenge:	Existing safety benchmarks focus on explicitly harmful content, but ignore context-dependent expressions such as dogwhistles.
Approach:	They propose a benchmark for evaluating LLM safety under dogwhistle-driven prompts . their findings expose a blind spot in current safety evaluation practices .
Outcome:	The proposed benchmark compared safety performance with toxic terms using dogwhistle-driven prompts.

Copied to clipboard

Sirry Chen, Jieyi Wang, Wei Chen, Zhongyu Wei

Sentence Ordering with a Coherence Verifier (2023.findings-acl)

Challenge:	Recent advances in speech language models have enabled more natural speech-based interactions, but the scarcity of medical speech data and the inefficiency of fine-tuning on speech data hinder adoption of SpeechLMs in medical consultation.
Approach:	They propose a SpeechLM natively capable of conducting speech-based multi-turn interactions with patients.
Outcome:	The proposed model outperforms baselines in both effectiveness and robustness in most evaluation settings.

Copied to clipboard

Sainan Jia, Wei Song, Jiefu Gong, Shijin Wang, Ting Liu

DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data (2025.findings-emnlp)

Challenge:	Recent sentence ordering studies can be classified into 2 categories: pair-wise ranking-based and sequence generation-based methods.
Approach:	They propose a sentence ordering method by plugging a coherence verifier into ranking-based and sequence generation-based methods.
Outcome:	The proposed method improves on topological sorting-based and pointer network-based methods with topological and point-based models.

Copied to clipboard

Yuhang Zhou, Jing Zhu, Shengyi Qian, Zhuokai Zhao, Xiyao Wang, Xiaoyu Liu, Ming Li, Paiheng Xu, Wei Ai, Furong Huang

CQG: A Simple and Effective Controlled Generation Framework for Multi-hop Question Generation (2022.acl-long)

Challenge:	Large Language Models (LLMs) are increasingly aligned with human preferences through Reinforcement Learning from Human Feedback (RLHF).
Approach:	a new study proposes a domain-informed self-consistency policy optimization extension to GRPO that addresses inter-group imbalance.
Outcome:	a new extension of GRPO addresses inter-group imbalance with two key innovations . the proposed method outperforms existing GR PO variants by 5% on Qwen3 models .

Copied to clipboard

Zichu Fei, Qi Zhang, Tao Gui, Di Liang, Sirui Wang, Wei Wu, Xuanjing Huang

Mask Attention Networks: Rethinking and Strengthen Transformer (2021.naacl-main)

Challenge:	Current models can not ensure the complexity of generated questions, so they may generate shallow questions that can be answered without multi-hop reasoning.
Approach:	They propose a controlled framework to generate multi-hop questions that contain key entities in multi- hop reasoning chains and a novel Transformer-based decoder to guarantee that key entities appear in the questions.
Outcome:	The proposed model outperforms the state-of-the-art model 25% on HotpotQA.

Copied to clipboard

Zhihao Fan, Yeyun Gong, Dayiheng Liu, Zhongyu Wei, Siyuan Wang, Jian Jiao, Nan Duan, Ruofei Zhang, Xuanjing Huang

DisLoRA: Task-specific Low-Rank Adaptation via Orthogonal Basis from Singular Value Decomposition (2025.emnlp-main)

Challenge:	Existing research explores to enhance the two sublayers separately to improve the capability of Transformer for text representation.
Approach:	They propose to combine SAN and Feed-Forward Networks to create a dynamic mask attention network with a learnable mask matrix which can model localness adaptively.
Outcome:	The proposed model outperforms the original Transformer on translation and text summarization tasks.

Copied to clipboard

She Yifei, Xinhao Wei, Yulong Wang

Breaking the Evaluation Paradox: Evaluating High-Entropy Search with Computationally Irreducible Constraints (2026.findings-acl)

Challenge:	Extensive experiments on GLUE and Commonsense Reasoning benchmarks demonstrate that DisLoRA surpasses established PEFT methods, including LoRA, PiSSA, DoRA, LoRA-Dash, and SORSA.
Approach:	They propose a framework that leverages singular value decomposition to decompose pretrained weight matrices into orthogonal backbone and task-specific subspaces.
Outcome:	Extensive experiments on GLUE and Commonsense Reasoning benchmarks show that DisLoRA surpasses established PEFT methods, including LoRA, PiSSA, DoRA, LoRA-Dash, and SORSA.

Copied to clipboard

Juntao Wu, Wei Wen, Xianting Huang, Shuai Pang, Ruizhi Qiao, Xing Sun, Ke Wang

Improving Empathetic Response Generation by Recognizing Emotion Cause in Conversations (2021.findings-emnlp)

Challenge:	a new framework for evaluation of exhaustive search capabilities is needed . high-entropy enumeration tasks make such ground truth impossible for humans to create . VERITAS is a framework built on the principle of computationally irreducible constraints .
Approach:	They propose a framework that uses non-optimizable constraints to create verifiable searches . VERITAS can generate infinite number of test cases with perfect ground truth and precise difficulty control .
Outcome:	a new evaluation framework for large language models is based on non-optimizable constraints . the framework can generate infinite number of test cases with perfect ground truth and precise difficulty control .

Copied to clipboard

Jun Gao, Yuhan Liu, Haolin Deng, Wei Wang, Yu Cao, Jiachen Du, Ruifeng Xu

Using Customer Service Dialogues for Satisfaction Analysis with Context-Assisted Multiple Instance Learning (D19-1)

Challenge:	Existing approaches to empathetic response generation ignore the emotion cause . existing dialogue systems lack emotion understanding and empathy .
Approach:	They propose a framework that integrates emotion cause information into empathetic response generation by predicting context emotion labels and sequence of emotion cause-oriented labels.
Outcome:	The proposed framework improves empathetic response generation by incorporating emotion cause information into the model.

Copied to clipboard

Kaisong Song, Lidong Bing, Wei Gao, Jun Lin, Lujun Zhao, Jiancheng Wang, Changlong Sun, Xiaozhong Liu, Qiong Zhang

Unsupervised Natural Language Inference via Decoupled Multimodal Contrastive Learning (2020.emnlp-main)

Challenge:	Existing studies fail to provide comprehensive service satisfaction analysis . Existing models fail to include satisfaction polarity classification and sentimental utterance identification .
Approach:	They propose a model that predicts customer sentiments and aggregates them into service satisfaction polarity.
Outcome:	The proposed model predicts customer sentiments and aggregates them into service satisfaction polarity and reasoning clues.

Copied to clipboard

Wanyun Cui, Guangyu Zheng, Wei Wang

Spotting AI’s Touch: Identifying LLM-Paraphrased Spans in Text (2024.findings-acl)

Challenge:	a recent study shows that humans are not supervised by the natural language inference .
Approach:	They propose to solve the natural language inference problem via task-agnostic multimodal pretraining.
Outcome:	The proposed network outperforms fully-supervised BiLSTM and BiLS+ELMO on plain text inference datasets.

Copied to clipboard

Yafu Li, Zhilin Wang, Leyang Cui, Wei Bi, Shuming Shi, Yue Zhang

Lost in Pronunciation: Detecting Chinese Offensive Language Disguised by Phonetic Cloaking Replacement (2025.emnlp-industry)

Challenge:	Existing work focuses on detecting (partially) AI-generated texts, but paraphrasing is commonly employed in various application scenarios for text refinement and diversity.
Approach:	They propose a framework for paraphrased text span detection that takes in the full text and assigns each sentence with a score indicating the paraphrasing degree.
Outcome:	The proposed framework can detect paraphrased text spans within a text . it takes in the full text and assigns each sentence with a score indicating the paraphrasing degree.

Copied to clipboard

Haotan Guo, Jianfei He, Jiayuan Ma, Hongbin Na, Zimu Wang, Haiyang Zhang, Qi Chen, Wei Wang, Zijing Shi, Tao Shen, Ling Chen

TabPrompt: Graph-based Pre-training and Prompting for Few-shot Table Understanding (2023.findings-emnlp)

Challenge:	Phonetic Cloaking Replacement (PCR) is a problem in content moderation in China.
Approach:	They organize PCR into a four-way surface-form taxonomy and compile PCR-ToxiCN, a dataset of 500 phonetically cloaked offensive posts gathered from the RedNote platform.
Outcome:	The proposed model achieves only an F1-score and zero-shot chain-of-thought prompting pushes performance even lower.

Copied to clipboard

Rihui Jin, Jianan Wang, Wei Tan, Yongrui Chen, Guilin Qi, Wang Hao

ReasVQA: Advancing VideoQA with Imperfect Reasoning Process (2025.naacl-long)

Challenge:	Existing methods of Table Understanding (TU) focus on the textual content within the tabular data, disregarding the topological information of the table.
Approach:	They propose a framework that uses tabs to understand tabular data without ignoring the topological information of the table.
Outcome:	The proposed framework outperforms baselines in few-shot table understanding tasks.

Copied to clipboard

Jianxin Liang, Xiaojun Meng, Huishuai Zhang, Yueqian Wang, Jiansheng Wei, Dongyan Zhao

NegotiationToM: A Benchmark for Stress-testing Machine Theory of Mind on Negotiation Surrounding (2024.findings-emnlp)

Challenge:	Existing approaches to VideoQA often fail when complex reasoning or temporal relationships are involved.
Approach:	They propose a method that leverages reasoning processes generated by Multimodal Large Language Models to improve VideoQA models.
Outcome:	The proposed method improves VideoQA models on three benchmarks.

Copied to clipboard

Chunkit Chan, Cheng Jiayang, Yauwai Yim, Zheye Deng, Wei Fan, Haoran Li, Xin Liu, Hongming Zhang, Weiqi Wang, Yangqiu Song

Improving Document Representations by Generating Pseudo Query Embeddings for Dense Retrieval (2021.acl-long)

Challenge:	Theory of mind evaluations currently focus on testing models using machine-generated data or game settings prone to shortcuts and spurious correlations.
Approach:	They propose a benchmark to stress-test machine ToM in real-world negotiation surrounding covered multi-dimensional mental states.
Outcome:	The proposed benchmark builds upon the Belief-Desire-Intention theory and conducts the necessary empirical experiments to evaluate large language models.

Copied to clipboard

Hongyin Tang, Xingwu Sun, Beihong Jin, Jingang Wang, Fuzheng Zhang, Wei Wu

Slot Transferability for Cross-domain Slot Filling (2021.findings-acl)

Challenge:	Existing retrieval models based on dense representations show better performance than sparse representations.
Approach:	They propose a method to mimic the queries to each of the documents by an iterative clustering process and represent the documents using multiple pseudo queries.
Outcome:	The proposed model achieves state-of-the-art results on a large dataset while remaining high efficiency.

Copied to clipboard

Hengtong Lu, Zhuoxin Han, Caixia Yuan, Xiaojie Wang, Shuyu Lei, Huixing Jiang, Wei Wu

Semantic Parsing

Challenge:	Existing work on slot filling uses labeled data from source domains to train a model for target domains.
Approach:	They propose a model-agnostic Slot Transferability Measure (STM) to evaluate the transferability from a source slot to a target slot.
Outcome:	The proposed method outperforms state-of-the-art models on multiple datasets and models.

PEER: Pre-training ELECTRA Extended by Ranking (2023.findings-acl)

Copied to clipboard

Ru He, Wei Wang, Songfang Huang, Fei Huang

BizCompass: Benchmarking the Reasoning Capabilities of LLMs in Business Knowledge and Applications (2026.findings-acl)

Challenge:	Existing models for pre-training require expensive pre-trainer computation cost . ELECTRA model can perform replaced token detection (RTD) task with reduced pre- training cost compared to current models .
Approach:	They propose to extend a discriminator-based replaced token detection task into a ranker-based task . they propose to use a binary classifier to perform a more precise task with negligible additional computation cost.
Outcome:	The proposed model outperforms state-of-the-art models with ELECTRA in GLUE tasks given the same cost.

Copied to clipboard

Jianing Hao, Yuhe Wu, Yuanjian Xu, Shichang Meng, Shuai Yuan, Wei Zeng, Zixuan Wang, Guang Zhang

PATS: Sensitivity-aware Noisy Learning for Pretrained Language Models (2022.emnlp-main)

Challenge:	Existing benchmarks focus on narrow tasks and leave a fundamental question unanswered . Existing models only focus on specific tasks, requiring rigorous reasoning and knowledge .
Approach:	They propose a benchmark to connect theoretical foundations with practical business knowledge and applications.
Outcome:	The benchmark systematically evaluates both open-source and commercial LLMs . it reveals how theoretical knowledge translates into practical performance in business .

Copied to clipboard

Yupeng Zhang, Hongzhi Zhang, Sirui Wang, Wei Wu, Zhoujun Li

Global and Local Hierarchy-aware Contrastive Framework for Implicit Discourse Relation Recognition (2023.findings-acl)

Challenge:	A wide range of NLP tasks benefit from fine-tuning of pretrained language models (PLMs), however, a number of redundant parameters which contribute less to the downstream task are observed in a directly fine- tuned model.
Approach:	They propose a noisy training mechanism which considers each parameter’s importance in the downstream task to help fine-tune pretrained language models.
Outcome:	The proposed method can be used to fine-tune pretrained language models on a wide range of tasks and consistently achieve higher performance.

Copied to clipboard

Yuxin Jiang, Linhan Zhang, Wei Wang

Encoding and Fusing Semantic Connection and Linguistic Evidence for Implicit Discourse Relation Recognition (2022.findings-acl)

Challenge:	Existing methods to integrate whole hierarchical information of senses into discourse relation representations for multi-level sense recognition ignore static hierarchic structure containing all senses and ignore hierarchically sense label sequence corresponding to each instance.
Approach:	They propose to use a GlObal and Local Hierarchy-aware Contrastive Framework to model two kinds of hierarchies with the aid of multi-task learning and contrastive learning to learn better representations of discourse relation relationships.
Outcome:	The proposed method outperforms current state-of-the-art models at all hierarchical levels on PDTB 2.0 and PDTP 3.0 datasets.

Copied to clipboard

Wei Xiang, Bang Wang, Lu Dai, Yijun Mo

Challenge:	Existing studies use one attention mechanism to improve contextual semantic representation learning for implicit discourse relation recognition (IDRR).
Approach:	They propose a Multi-Attentive Neural Fusion model to fuse linguistic evidence and semantic connection for IDRR by using a Dual Attention Network and an Offset Matrix Network.
Outcome:	The proposed model achieves state-of-the-art on the PDTB 3.0 corpus.

ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer (2021.acl-long)

Copied to clipboard

Yuanmeng Yan, Rumei Li, Sirui Wang, Fuzheng Zhang, Wei Wu, Weiran Xu

Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding (2021.acl-long)

Challenge:	Existing BERT-based pre-trained language models achieve high performance on many downstream tasks, but native derived sentence representations are collapsed and thus poor performance on semantic textual similarity (STS) tasks.
Approach:	They propose a framework for self-supervised Sentence Representation Transfer that adopts contrastive learning to fine-tune BERT in an unsupervised way.
Outcome:	The proposed framework improves on the BERT-derived representations by 8% on STS datasets and shows robustness in data scarcity scenarios.

Copied to clipboard

Xin Sun, Tao Ge, Furu Wei, Houfeng Wang

Boundary Detection with BERT for Span-level Emotion Cause Analysis (2021.findings-acl)

Challenge:	Existing approaches to improve online inference efficiency of the Transformer for instantaneous Grammatical Error Correction (GEC) are sequenceto-sequence (seq2sequ) and sequenceto sequence (saq2eq)
Approach:	They propose a novel approach to improve the online inference efficiency of the Transformer model for instantaneous Grammatical Error Correction (GEC) it aggressively decodes as many tokens as possible in parallel instead of always decoding only one token in each step to improve computational parallelism.
Outcome:	The proposed approach can achieve state-of-the-art results in English and Chinese benchmarks with 10x speedup over the Transformer-big model.

Copied to clipboard

Xiangju Li, Wei Gao, Shi Feng, Yifei Zhang, Daling Wang

Lion: Adversarial Distillation of Proprietary Large Language Models (2023.emnlp-main)

Challenge:	Emotion cause analysis (ECA) is an emerging topic in natural language processing, which aims to identify the reasons behind a given emotion.
Approach:	They propose to detect the precise boundaries of text spans conveying accurate emotion causes from the given context by a sequence labeling and position identification problem.
Outcome:	The proposed methods outperform existing models on two benchmark datasets on the emotion cause analysis task.

Copied to clipboard

Yuxin Jiang, Chunkit Chan, Mingyang Chen, Wei Wang

NeuroSym-Cal: Bridging the Reasoning-Execution Gap in Code Generation via Hierarchical Calibration (2026.findings-acl)

Challenge:	Existing methods for transferring knowledge from a proprietary large language model to an open-source LLM have been criticized for not incorporating any feedback to boost student model's proficiency iteratively.
Approach:	They propose a novel adversarial distillation framework that integrates feedback to identify challenging instructions where the student model’s performance falls short.
Outcome:	The proposed framework surpasses existing state-of-the-art LLMs by 55.4% in challenging zero-shot reasoning benchmarks and 16.7% on AGIEval.

Copied to clipboard

Peiyang Liu, Yining Wang, Youru Li, Long Li, Zhi Cai, Wei Ye

Ready Jurist One: Benchmarking Language Agents for Legal Intelligence in Dynamic Environments (2026.acl-long)

Challenge:	Existing calibration methods rely on the assumption that consensus implies correctness . Existing methods fail under systematic errors, leading to miscalibrated high-confidence predictions.
Approach:	They propose a hierarchical calibration framework that measures confidence at two levels . they propose sensitivity analysis to measure local curvature of deductive process .
Outcome:	The proposed framework de-saturates overconfident errors and improves selective generation performance on OOD benchmarks.

Copied to clipboard

Zheng Jia, Shengbin Yue, Wei Chen, Siyuan Wang, Yidong Liu, Zejun Li, Yun Song, Zhongyu Wei

Challenge:	Existing benchmarks for legal intelligence are limited to static evaluation paradigms or simplified scenarios.
Approach:	They introduce J1-ENVS, the first interactive and dynamic legal environment tailored for LLM-based agents.
Outcome:	The proposed framework assesses task performance and procedural compliance across legal proficiency levels.

Improving Knowledge Graph Completion with Structure-Aware Supervised Contrastive Learning (2024.emnlp-main)

Copied to clipboard

Jiashi Lin, Lifang Wang, Xinyu Lu, Zhongtian Hu, Wei Zhang, Wenxuan Lu

Large-Scale Relation Learning for Question Answering over Knowledge Bases with Pre-trained Language Models (2021.emnlp-main)

Challenge:	Existing contrastive methods focus on individual triples, overlooking the broader structural connectivities and topologies of KGs.
Approach:	They propose a new contrastive learning framework that incorporates four tasks specifically tailored to KG data: Vertex-level CL, Neighbor-level Cl, Path-levelCL, and Relation composition level CL.
Outcome:	The proposed framework achieves SOTA performance under standard supervised and low-resource settings.

Copied to clipboard

Yuanmeng Yan, Rumei Li, Sirui Wang, Hongzhi Zhang, Zan Daoguang, Fuzheng Zhang, Wei Wu, Weiran Xu

Advancing Fine-Grained Visual Understanding with Multi-Scale Alignment in Multi-Modal Models (2025.emnlp-main)

Challenge:	Existing KBQA methods focus on the natural language but ignore textual information carried by the nodes and edges.
Approach:	They propose to perform relation extraction, relation matching, and relation reasoning tasks to align the natural language expressions to the relations in the KB and reason over the missing connections.
Outcome:	Experiments on WebQSP show that the proposed model outperforms baselines even when the KB is incomplete.

Copied to clipboard

Wei Wang, Zhaowei Li, Qi Xu, Linfeng Li, YiQing Cai, Botian Jiang, Hang Song, Xingcan Hu, Pengyu Wang, Li Xiao

PUER: Boosting Few-shot Positive-Unlabeled Entity Resolution with Reinforcement Learning (2025.findings-emnlp)

Challenge:	Recent advances in multi-modal large language models have demonstrated remarkable capabilities in multimodal understanding, reasoning, and interaction.
Approach:	They propose a method that effectively aligns and integrates multi-scale knowledge of objects . they use a pipeline that provides over 300K essential training data to enhance alignment .
Outcome:	The proposed method effectively aligns and integrates multi-scale knowledge of objects, including texts, coordinates, and images.

Copied to clipboard

Yaoshu Wang, Mengyi Yan, Wei Wang

Diagnosing Hidden Instabilities in Model Editing via Uncertainty Quantification (2026.acl-long)

Challenge:	Existing approaches to entity resolution focus on supervised learning, but manual annotation is labor-intensive.
Approach:	They propose an end-to-end ER solution that leverages Large Language Models in PU learning setting to address low-resource entity resolution.
Outcome:	The proposed solution improves the performance of PUER on a positive-unlabeled learning environment.

Copied to clipboard

Zihan Gu, TianYi Zhang, Xinyan Zhang, Zhiyuan Wang, Han Zhang, Yuhao Wei, Jiacheng Lu, Tianyi Ma, Xingsheng Zhang, Hua Zhang, Yue Hu

Challenge:	Existing methods to update large language models (LLMs) without expensive retraining are fragile under single-edit evaluation protocols.
Approach:	They propose a framework that characterizes activation-based editing as a constrained intervention on intermediate representations.
Outcome:	The proposed method reveals local knowledge conflicts invisible to existing benchmarks.

BADGE: Speeding Up BERT Inference after Deployment via Block-wise Bypasses and Divergence-based Early Exiting (2023.acl-industry)

Copied to clipboard

Wei Zhu, Peng Wang, Yuan Ni, Guotong Xie, Xiaoling Wang

FGraDA: A Dataset and Benchmark for Fine-Grained Domain Adaptation in Machine Translation (2022.lrec-1)

Challenge:	Recent years have witnessed the rise of many pre-trained language models (PLMs) such as GPT (Radford et al., 2019) and XLNet (Yang e.t al, 2019).
Approach:	They propose a framework which consists of two off-the-shelf methods for improving PLMs’ early exiting.
Outcome:	The proposed method can reduce the average latency of pre-trained language models and work with other inference speed-up methods like model pruning.

Copied to clipboard

Wenhao Zhu, Shujian Huang, Tong Pu, Pingxuan Huang, Xu Zhang, Jian Yu, Wei Chen, Yanfeng Wang, Jiajun Chen

INarIG: Iterative Non-autoregressive Instruct Generation Model For Word-Level Auto Completion (2023.findings-emnlp)

Challenge:	Recent research on domain adaptation neglects diversity in translation within a domain . current research on NMT models considers very broad target domains .
Approach:	They propose a fine-grained domain adaptation task for autonomous vehicles, AI education, real-time networks, and smart phone.
Outcome:	The proposed task is compared with a dataset of Chinese-English translation tasks for four sub-domains of information technology: autonomous vehicles, AI education, real-time networks, and smart phone.

Copied to clipboard

Hengchao Shang, Zongyao Li, Daimeng Wei, Jiaxin Guo, Minghan Wang, Xiaoyu Chen, Lizhi Lei, Hao Yang

Addressing Semantic Drift in Generative Question Answering with Auxiliary Extraction (2021.acl-short)

Challenge:	Existing models for word-level autocompletion (WLAC) only use human typed sequences as prefixes in decoding module.
Approach:	They propose a novel iterative nonautoregressive instruct generation model for WLAC task . it uses human typed sequences and iterating decoding with subwords to fully utilize input information.
Outcome:	The proposed model is more competent in dealing with low-frequency words, and achieves state-of-the-art results on the WMT22 and benchmark datasets.

Copied to clipboard

Chenliang Li, Bin Bi, Ming Yan, Wei Wang, Songfang Huang

DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to Determinacy (2024.acl-long)

Challenge:	Recent work focuses on question answering based on machine reading comprehension . current approaches treat QA as extracting a consecutive piece of text to a given question.
Approach:	They propose a generative QA model that incorporates an extractive mechanism into a model.
Outcome:	The proposed model improves quality and semantic accuracy over baseline models.

Copied to clipboard

Hongda Sun, Weikai Xu, Wei Liu, Jian Luan, Bin Wang, Shuo Shang, Ji-Rong Wen, Rui Yan

Leveraging Graph to Improve Abstractive Multi-Document Summarization (2020.acl-main)

Challenge:	Recent advances in large language models (LLMs) have revolutionized the landscape of reasoning tasks.
Approach:	They propose a new approach that rethinks the reasoning process as an evolution from indeterminacy to determinacy.
Outcome:	The proposed model surpasses all baselines on various logical reasoning benchmarks.

Copied to clipboard

Wei Li, Xinyan Xiao, Jiachen Liu, Hua Wu, Haifeng Wang, Junping Du

E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning (2025.emnlp-main)

Challenge:	Empirical results show that our model brings substantial improvements over several strong baselines.
Approach:	They propose a neural abstractive multi-document summarization model which captures cross-document relations and can guide the summary generation process.
Outcome:	The proposed model improves on the WikiSum and MultiNews datasets and can be easily combined with pre-trained language models.

Copied to clipboard

Zihan Liao, Jun Wang, Hang Yu, Lingxiao Wei, Jianguo Li, Jun Wang, Wei Zhang

Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration (2024.naacl-long)

Challenge:	Considerable efforts have been and are still being put into increasing the context length of Large Language Models (LLMs)
Approach:	They propose an approach that divides long contexts into chunks, compresses each into soft prompts using a pretrained text encoder, and aligns these representations with a decoder-only LLM via an adapter.
Outcome:	The proposed approach outperforms 8 state-of-the-art methods in effectiveness and efficiency for document summarization and question answering, and achieves the best performance on LongBench v2 among models of comparable size.

Copied to clipboard

Zhenhailong Wang, Shaoguang Mao, Wenshan Wu, Tao Ge, Furu Wei, Heng Ji

Cross-Document Cross-Lingual NLI via RST-Enhanced Graph Fusion and Interpretability Prediction (2025.emnlp-main)

Challenge:	Existing work on LLMs that only enhance reasoning abilities, but which lack factual hallucination and slow-thinking capabilities, argues that SPP is a cognitive synergist.
Approach:	They propose a Solo Performance Prompting (SPP) that transforms a single LLM into a cognitive synergist by engaging in multi-turn self-collaboration with multiple personas.
Outcome:	The proposed model reduces factual hallucination and maintains strong reasoning abilities on three challenging tasks .

Copied to clipboard

Mengying Yuan, WenHao Wang, Zixuan Wang, Yujie Huang, Kangli Wei, Fei Li, Chong Teng, Donghong Ji

Investigating BERT’s Knowledge of Language: Five Analysis Methods with NPIs (D19-1)

Challenge:	Despite the development of many subdirections, Cross-Document Cross-Lingual NLI remains largely unexplored.
Approach:	They propose a novel paradigm that extends traditional NLI capabilities to multi-document, multilingual scenarios by integrating RST-enhanced graph fusion with interpretability-aware prediction.
Outcome:	The proposed method improves on existing models and document-level NLI to multi-document, multilingual scenarios.

Copied to clipboard

Alex Warstadt, Yu Cao, Ioana Grosu, Wei Peng, Hagen Blix, Yining Nie, Anna Alsop, Shikha Bordia, Haokun Liu, Alicia Parrish, Sheng-Fu Wang, Jason Phang, Anhad Mohananey, Phu Mon Htut, Paloma Jeretic, Samuel R. Bowman

Powering Comparative Classification with Sentiment Analysis via Domain Adaptive Knowledge Transfer (2021.emnlp-main)

Challenge:	Recent work evaluating sentence representation models' knowledge of grammar has been slower to emerge.
Approach:	They propose five experimental methods inspired by prior work evaluating pretrained sentence representation models to examine their grammatical knowledge.
Outcome:	The proposed methods show that the model has significant knowledge of the licensing environment but its success varies widely across different methods.

Copied to clipboard

Zeyu Li, Yilong Qin, Zihan Liu, Wei Wang

C3KG: A Chinese Commonsense Conversation Knowledge Graph (2022.findings-acl)

Challenge:	Comparative Preference Classification (CPC) is a natural language processing task that predicts whether a preference comparison exists between two entities in a given sentence .
Approach:	They propose a sentiment analyzer that learns sentiments to individual entities via domain adaptive knowledge transfer.
Outcome:	Experiments on the CompSent-19 dataset present a significant improvement on the F1 scores over the best existing CPC approaches.

Copied to clipboard

Dawei Li, Yanran Li, Jiayi Zhang, Ke Li, Chen Wei, Jianwei Cui, Bin Wang

SUN: Exploring Intrinsic Uncertainties in Text-to-SQL Parsers (2022.coling-1)

Challenge:	Existing commonsense knowledge bases organize tuples in an isolated manner, causing problems for chatbots .
Approach:	They create a Chinese commonsense conversation knowledge graph which integrates social commonsensm and dialog flow information.
Outcome:	The proposed graph incorporates social commonsense knowledge and dialog flow information.

Copied to clipboard

Bowen Qin, Lihan Wang, Binyuan Hui, Bowen Li, Xiangpeng Wei, Binhua Li, Fei Huang, Luo Si, Min Yang, Yongbin Li

A Structure-Aware Argument Encoder for Literature Discourse Analysis (2022.coling-1)

Challenge:	Existing methods that learn from multiple semantically-equivalent questions are limited to one-to-one mapping .
Approach:	They propose a constraint to explore the underlying complementary semantic information among multiple semantically-equivalent questions and learn robust feature representations with reduced spurious associations.
Outcome:	The proposed method outperforms strong competitors and achieves state-of-the-art results on five benchmark datasets.

Copied to clipboard

Yinzi Li, Wei Chen, Zhongyu Wei, Yujun Huang, Chujun Wang, Siyuan Wang, Qi Zhang, Xuanjing Huang, Libo Wu

Correct When Paired, Wrong When Split: Decoupling and Editing Modality-Specific Neurons in MLLMs (2026.acl-long)

Challenge:	Existing research for argument representation learning treats tokens in sentences equally and ignores the implied structure information of argumentative context.
Approach:	They propose to separate tokens into two groups to capture structural information of arguments and to incorporate paragraph-level position information into the model.
Outcome:	The proposed model captures structural information of arguments and is able to identify arguments automatically.

Copied to clipboard

Tingchao Fu, Wenkai Wang, Fanxiao Li, Huadong Zhang, Jinhong Zhang, Dayang Li, Yunyun Dong, Renyang Liu, Wei Zhou

Global-to-Local Neural Networks for Document-Level Relation Extraction (2020.emnlp-main)

Challenge:	Existing knowledge editing paradigms suffer from editing decoupling failures . entity knowledge is sequestered into disentangled modality-specific pathways .
Approach:	They propose a method that explicitly disentangles and localizes modality-specific neuron groups for targeted knowledge.
Outcome:	The proposed method outperforms baselines in reliability and consistency while preserving model locality.

Copied to clipboard

Difeng Wang, Wei Hu, Ermei Cao, Weijian Sun

EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence (2026.acl-long)

Challenge:	Relation extraction (RE) aims to identify the semantic relations between named entities in text.
Approach:	They propose a novel relation extraction model that encodes document information in terms of entity global and local representations and context relation representations.
Outcome:	The proposed model achieves superior performance on two public datasets for document-level RE.

Copied to clipboard

Chaoyin She, Ruifang Lu, Lida Chen, Wei Wang, Qinghua Huang

DialogConv: A Lightweight Fully Convolutional Network for Multi-view Response Selection (2022.emnlp-main)

Challenge:	Ultrasound is the preferred early cancer screening modality due to non-ionizing radiation, cost-effectiveness, and real-time imaging.
Approach:	They propose to use ultrasound-tailored vision-language models with a mixture-of-experts architecture to train ultrasound-specific knowledge across seven anatomical systems.
Outcome:	The proposed model outperforms Qwen2-VL by 7.58 BLEU-1 and 3.45 ROUGE-1 points in report generation.

Copied to clipboard

Yongkang Liu, Shi Feng, Wei Gao, Daling Wang, Yifei Zhang

RACE: Retrieval-augmented Commit Message Generation (2022.emnlp-main)

Challenge:	Existing retrieval-based dialogue systems suffer from slow inference or huge number of parameters.
Approach:	They propose a lightweight fully convolutional architecture for response selection using convolution.
Outcome:	The proposed architecture extracts matching features of context and response from 3D views.

Copied to clipboard

Ensheng Shi, Yanlin Wang, Wei Tao, Lun Du, Hongyu Zhang, Shi Han, Dongmei Zhang, Hongbin Sun

LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement (2024.findings-emnlp)

Challenge:	Existing approaches to automatically generate commit messages are repetitive or redundant.
Approach:	They propose a retrieval-augmented neural commit message generation method which treats the retrieved similar commit as an exemplar and leverages it to generate an accurate commit message.
Outcome:	The proposed method outperforms baselines on a large dataset with five programming languages and can boost existing Seq2Seq models in commit message generation.

Copied to clipboard

Jiahao Ying, Mingbao Lin, Yixin Cao, Wei Tang, Bo Wang, Qianru Sun, Xuanjing Huang, Shuicheng Yan

Challenge:	Using advanced Large Language Models, instructors can improve training of smaller models by analyzing their own model's errors.
Approach:	They propose a framework that leverages advanced Large Language Models to enhance training of smaller target models.
Outcome:	The proposed framework outperforms ChatGPT on multiple benchmarks and shows that it improves on both in-domain and out-of-domain benchmarks.

MdEval: Massively Multilingual Code Debugging (2026.findings-acl)

Copied to clipboard

Shukai Liu, Linzheng Chai, Jian Yang, Jiajun Shi, He Zhu, Liran Wang, Jin Ke, Wei Zhang, Hualei Zhu, Shuyue Guo, Tao Sun, Jiaheng Liu, Yunlong Duan, Yu Hao, Liqun Yang, Guanglin Niu, Ge Zhang, Zhoujun Li

Named Entity and Relation Extraction with Multi-Modal Retrieval (2022.findings-emnlp)

Challenge:	Existing benchmarks primarily focus on Python and are limited in terms of language diversity.
Approach:	They propose a multilingual debugging benchmark that includes 3.9K test samples of 20 programming languages and introduces the debug instruction corpora MdEval-Instruct by injecting bugs into the correct multilingual queries and solutions.
Outcome:	The proposed benchmark includes 3.9K test samples of 20 programming languages and covers the automated program repair task, bug localization task, and bug identification task.

Copied to clipboard

Xinyu Wang, Jiong Cai, Yong Jiang, Pengjun Xie, Kewei Tu, Wei Lu

Neural Label Search for Zero-Shot Multi-Lingual Extractive Summarization (2022.acl-long)

Challenge:	Existing approaches to name entity recognition and relation extraction are knowledge-based and may not be highly relevant.
Approach:	They propose a multi-modal named entity recognition framework that leverages image information to improve the performance of NER and relation extraction.
Outcome:	The proposed framework can achieve state-of-the-art on four multi-modal named entity recognition datasets and one multi-module relation extraction dataset.

Copied to clipboard

Ruipeng Jia, Xingxing Zhang, Yanan Cao, Zheng Lin, Shi Wang, Furu Wei

Diagnosing and Remedying Representation Deficiencies for Deterministic Reasoning in KGQA (2026.acl-long)

Challenge:	Existing methods to translate sentences to other languages using heuristics are challenging.
Approach:	They propose a model that learns hierarchical weights for different sets of labels and applies them to other languages to translate them.
Outcome:	The proposed model can translate English datasets to other languages and obtain different sets of labels again using heuristics.

Copied to clipboard

Gewen Liang, Mufan Xu, Kehai Chen, Wei Wang, Yuwei Wang, Muyun Yang, Tiejun Zhao, Min Zhang

Toward Safe and Human-Aligned Game Conversational Recommendation via Multi-Agent Decomposition (2026.findings-eacl)

Challenge:	Existing approaches to solve non-deterministic reasoning problems in large language models are limited by their complexity and lack of a clear understanding of the problem.
Approach:	They propose a method to diagnose and correct non-deterministic reasoning behaviors in large language models.
Outcome:	The proposed method outperforms baselines and WebQSP benchmarks on the widely used WebQ SP and CWQ benchmarks.

Copied to clipboard

Zheng Hui, Xiaokai Wei, Yexi Jiang, Kevin Gao, Chen Wang, Se-eun Yoon, Rachit Pareek, Michelle Gong

Latent Distribution Decouple for Uncertain-Aware Multimodal Multi-label Emotion Recognition (2025.findings-acl)

Challenge:	Existing systems for conversational recommender systems (CRS) have strong results in movies, but games present distinct challenges . MATCHA framework provides specialized agents for intent parsing, tool-augmented retrieval, multi-LLM ranking, and stronger safety.
Approach:	They propose a framework for conversational recommender systems that assigns specialized agents for intent parsing, tool-augmented retrieval, multi-LLM ranking and risk control.
Outcome:	MATCHA outperforms baselines on real user request dataset, improves Hit@5 by 20%, reduces popularity bias by 24%, and achieves 97.9% adversarial defense.

Copied to clipboard

Jingwang Huang, Jiang Zhong, Qin Lei, Gaojinpeng Gaojinpeng, Ymyang Ymyang, Sirui Wang, PeiguangLi PeiguangLi, Kaiwen Wei

Improve Speech Translation Through Text Rewrite (2025.coling-industry)

Challenge:	Existing studies focus on improving fusion strategies and modeling modality-to-label dependencies, but they overlook the impact of aleatoric uncertainty, which is inherent noise in multimodal data.
Approach:	They propose a latent emotional distribution decomposition with uncertainty perception framework to model aleatoric uncertainty in multimodal data.
Outcome:	The proposed framework achieves state-of-the-art performance on the CMU-MOSEI and M3ED datasets, highlighting the importance of uncertainty modeling in MMER.

Copied to clipboard

Jing Wu, Shushu Wang, Kai Fan, Wei Luo, Minpeng Liao, Zhongqiang Huang

CIKT: A Collaborative and Iterative Knowledge Tracing Framework with Large Language Models (2025.emnlp-main)

Challenge:	Recent advances in speech translation (ST) research have focused on the unique characteristics of spontaneous speech, including accents and presentation quality.
Approach:	They propose to transform transcribed speech into a cleaner style more in line with the expectations of translation models built from written text.
Outcome:	Experiments on public and in-house translation models show that the proposed model can be effectively distilled into a standalone translation model.

Copied to clipboard

Runze Li, Siyu Wu, Jun Wang, Wei Zhang

From Long Videos to Engaging Clips: A Human-Inspired Video Editing Framework with Multimodal Narrative Understanding (2025.emnlp-industry)

Challenge:	Knowledge Tracing (KT) aims to model a student’s learning state over time and predict their future performance.
Approach:	They propose a framework that harnesses Large Language Models to enhance both prediction accuracy and explainability by a synergistic optimization loop.
Outcome:	The proposed framework improves both prediction accuracy and explainability by using a synergistic optimization loop.

Copied to clipboard

Xiangfeng Wang, Xiao Li, Yadong Wei, null Songxueyu, Yang Song, null Xiaxiaoqiang, Fangrui Zeng, Zaiyi Chen, null Liuliu, Gu Xu, Tong Xu

UIOrchestra: Generating High-Fidelity Code from UI Designs with a Multi-agent System (2025.findings-emnlp)

Challenge:	Existing methods for video editing rely on textual cues from ASR transcripts and segment selection, often neglecting rich visual context.
Approach:	They propose a human-inspired automatic video editing framework that leverages multimodal narrative understanding to address these limitations.
Outcome:	The proposed framework outperforms existing baselines across general and advertisement-oriented editing tasks.

Copied to clipboard

Chuhuai Yue, Jiajun Chai, Yufei Zhang, Zixiang Ding, Xihao Liang, Peixin Wang, Shihai Chen, Wang Yixuan, null Wangyanping, Guojun Yin, Wei Lin

Text-Tuple-Table: Towards Information Integration in Text-to-Table Generation via Global Tuple Extraction (2024.emnlp-main)

Challenge:	Recent advances in large language models have significantly improved automated code generation . however, the translation of complex mobile UI designs into high-fidelity front-end code remains a challenge .
Approach:	They propose a collaborative multi-agent system to reconstruct static single-page apps from mockups.
Outcome:	The proposed system outperforms existing methods in reconstructing complex app pages . the code and data will be released upon paper acceptance .

Copied to clipboard

Zheye Deng, Chunkit Chan, Weiqi Wang, Yuxi Sun, Wei Fan, Tianshi Zheng, Yauwai Yim, Yangqiu Song

Towards Universal Debiasing for Language Models-based Tabular Data Generation (2025.findings-emnlp)

Challenge:	Existing approaches to condensing textual information into concise and structured tables are limited in their applicability in broader contexts.
Approach:	They propose a benchmark dataset for generating summary tables of competitions based on real-time commentary texts that incorporates large-scale textual information into concise and structured tables.
Outcome:	The proposed method exhibits strong generalization abilities, surpassing previous approaches on several other text-to-table datasets.

Copied to clipboard

Tianchun Li, Tianci Liu, Xingchen Wang, Rongzhe Wei, Pan Li, Lu Su, Jing Gao

ToViLaG: Your Visual-Language Generative Model is Also An Evildoer (2023.emnlp-main)

Challenge:	Existing large language models have exacerbated fairness issues in tabular data generation . inherent historical biases in tabulated data cause LLMs to exacerbate fairness problems .
Approach:	They propose a universal debiasing framework that minimizes group-level dependencies . it leverages the autoregressive structure and analytic sampling distributions of LLM-based tabular data generators .
Outcome:	The proposed framework minimizes group-level dependencies while reducing mutual information between advantaged and protected attributes.

Copied to clipboard

Xinpeng Wang, Xiaoyuan Yi, Han Jiang, Shanlin Zhou, Zhihua Wei, Xing Xie

LayoutLMv2: Multi-modal Pre-training for Visually-rich Document Understanding (2021.acl-long)

Challenge:	Recent large-scale Visual-Language Generative Models (VLGMs) generate toxic content, e.g., offensive text and pornography images, raising significant ethical risks.
Approach:	They propose a bottleneck-based detoxification method to reduce toxicity while maintaining comparable generation quality.
Outcome:	The proposed method could reduce toxicity while maintaining comparable generation quality.

Copied to clipboard

Yang Xu, Yiheng Xu, Tengchao Lv, Lei Cui, Furu Wei, Guoxin Wang, Yijuan Lu, Dinei Florencio, Cha Zhang, Wanxiang Che, Min Zhang, Lidong Zhou

PMSS: Pretrained Matrices Skeleton Selection for LLM Fine-tuning (2025.coling-main)

Challenge:	Existing pre-training tasks for text and layout are effective in visually-rich document understanding tasks.
Approach:	They propose to combine pre-training tasks with a multi-modal model to model interaction between text, layout and image in a single multi-module framework.
Outcome:	The proposed model outperforms LayoutLM by a large margin on visual-rich document understanding tasks.

Copied to clipboard

Qibin Wang, Xiaolin Hu, Weikai Xu, Wei Liu, Jian Luan, Bin Wang

Natural-Language Policies to Executable Decisions: An Interpretable Large Language Model Framework (2026.acl-industry)

Challenge:	Low-rank adaptation and its variants have been popular due to their ability to avoid excessive inference costs.
Approach:	They propose a low-rank adaptation method that enables high-rank updates with low costs while leveraging semantic and linguistic information inherent in pre-trained weight.
Outcome:	The proposed method outperforms LoRA and other fine-tuning methods across tasks with less trainable parameters.

Copied to clipboard

Ziqiang Zhang, Jing Ma, Zilong Wang, Jiayuan Chen, Yi Qiao, Yu He, Wei Zhang, Dai Cheng, Xiaoyu Shen

Introducing Semantics into Speech Encoders (2023.acl-long)

Challenge:	a production-grade pricing system for tourism is challenging due to unstructured nature of travel orders and ever-evolving pricing policies.
Approach:	They propose a production-grade pricing system with a strict decision boundary . they propose to combine structured extraction and bounded policy/path selection with interpretable condition trees .
Outcome:	The proposed system processed 3,960 orders in six months and reduced the order management team from 15-20 to 3 . the system reduced the per-order handling time from 10 minutes to 2 minutes.

Copied to clipboard

Derek Xu, Shuyan Dong, Changhan Wang, Suyoun Kim, Zhaojiang Lin, Bing Liu, Akshat Shrivastava, Shang-Wen Li, Liang-Hsuan Tseng, Guan-Ting Lin, Alexei Baevski, Hung-yi Lee, Yizhou Sun, Wei Wang

Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards (2024.acl-long)

Challenge:	Existing self-supervised speech encoders contain primarily acoustic rather than semantic information.
Approach:	They propose a task-agnostic unsupervised way to incorporate semantic information from large language model (LLM) systems into self-supervised speech encoders without labeled audio transcriptions.
Outcome:	The proposed approach improves spoken language understanding (SLU) performance by over 5% on intent classification (IC), with modest gains in named entity resolution (NER) and slot filling (SF), and spoken question answering (SQA) score by over 22%.

Copied to clipboard

Haoxiang Wang, Yong Lin, Wei Xiong, Rui Yang, Shizhe Diao, Shuang Qiu, Han Zhao, Tong Zhang

Challenge:	Reinforcement Learning from Human Feedback (RLHF) relies on scalar rewards to capture user preferences.
Approach:	They propose a framework that integrates multi-objective reward modeling to represent diverse preference profiles.
Outcome:	The proposed method improves performance across reward objectives and targets.

Improving Neural Abstractive Document Summarization with Explicit Information Selection Modeling (D18-1)

Copied to clipboard

Wei Li, Xinyan Xiao, Yajuan Lyu, Yuanzhuo Wang

Answer-focused and Position-aware Neural Question Generation (D18-1)

Challenge:	Existing neural abstractive methods for document summarization are not effective for document summary.
Approach:	They propose to extend basic neural encoding-decoding framework with an information selection layer to explicitly model and optimize the information selection process in abstractive document summarization.
Outcome:	The proposed model outperforms state-of-the-art methods on document summarization tasks significantly.

Copied to clipboard

Xingwu Sun, Jing Liu, Yajuan Lyu, Wei He, Yanjun Ma, Shi Wang

Calibrating Inference Time Alignment with Sequence-level Risk Accumulation (2026.acl-long)

Challenge:	Recent neural network-based approaches generate interrogative words that do not match the answer type.
Approach:	They propose an answer-focused and position-aware neural question generation model to address these issues.
Outcome:	The proposed model outperforms the baseline and outperformed the state-of-the-art system.

Copied to clipboard

Shanwen Tan, Ziyang Dong, Wei Ju, Yiwei Fu, Hao Wu, Kun Wang, Yifan Wang, Ziyue Qiao

CNNSum: Exploring Long-Context Summarization with Large Language Models in Chinese Novels (2025.findings-acl)

Challenge:	Existing approaches to decode large language models (LLMs) often over-reject benign information, limiting their generalizability in real-world scenarios where harmful and benign information coexist.
Approach:	They propose a framework to regulate decoding alignments for Large Language Models (LLMs) they employ a reward-guided branch decoding paradigm to incorporate safety awareness during generation.
Outcome:	The proposed framework achieves superior performance on four attack benchmarks and two neutral datasets.

Copied to clipboard

Lingxiao Wei, He Yan, Lu Xiangju, Junmin Zhu, Jun Wang, Wei Zhang

Dynamic Generation of Multi LLM Agents Communication Topologies with Graph Diffusion Models (2026.acl-long)

Challenge:	Currently, long-context summarization mainly relies on memory ability.
Approach:	They propose a multi-scale long-context summarization benchmark based on Chinese novels . they use human-driven annotations to analyze long-constituency models .
Outcome:	The proposed benchmark features human-driven annotations across four subsets with lengths ranging from 16k to 128k.

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

Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy (2026.acl-long)

Challenge:	Existing frameworks rely on static or rule-based topologies that fail to adapt to task requirements.
Approach:	They propose a generative framework that generates highly task-adaptive topologies . they validated the framework on multiple benchmarks and validated it on multiple platforms .
Outcome:	The proposed framework outperforms existing frameworks in task-adaptive communication topologies.

Copied to clipboard

Eric Hanchen Jiang, Weixuan Ou, Run Liu, Shengyuan Pang, Guancheng Wan, Ranjie Duan, Wei Dong, Kai-Wei Chang, XiaoFeng Wang, Ying Nian Wu, Xinfeng Li

Generating Deep Questions with Commonsense Reasoning Ability from the Text by Disentangled Adversarial Inference (2023.findings-acl)

Challenge:	Existing safety alignment techniques prioritize mitigating harmful responses at the expense of overcautious behavior, leading models to incorrectly refuse benign requests.
Approach:	They propose a fine-tuning free framework to improve safety and reduce false refusals by dynamic, inference-time intervention.
Outcome:	The proposed framework raises compliance on the ORB-H benchmark from 57.3% to 82.6% while maintaining the baseline safety performance.

Copied to clipboard

Jianxing Yu, Shiqi Wang, Libin Zheng, Qinliang Su, Wei Liu, Baoquan Zhao, Jian Yin

A Reinforcement Learning Framework for Natural Question Generation using Bi-discriminators (C18-1)

Challenge:	Existing methods for commonsense question generation produce shallow questions that can be answered by simple word matching.
Approach:	They propose a task of commonsense question generation that aims to yield deep-level questions from the text.
Outcome:	The proposed model can yield deep-level and to-the-point questions from the text.

Copied to clipboard

Zhihao Fan, Zhongyu Wei, Siyuan Wang, Yang Liu, Xuanjing Huang

Confidence-Calibrated Small-Large Language Model Collaboration for Cost-Efficient Reasoning (2026.eacl-long)

Challenge:	Existing research on visual question generation is focused on training models to fit the annotated data set that makes them indifferent from other language generation tasks.
Approach:	They propose to use two discriminators to enhance the training of a visual question generator to ask natural questions about an image.
Outcome:	The proposed model outperforms state-of-the-art models in terms of automatic and human evaluation metrics.

Copied to clipboard

Chuang Zhang, Zizhen Zhu, Yihao Wei, Bing Tian, Junyi Liu, Henan Wang, Wang Xavier, Yaxiao Liu

Simple-VGC: Enhancing Visual Grounding in Multimodal Reasoning via Adaptive Tool Composition (2026.acl-long)

Challenge:	Large language models (LLMs) have superior reasoning capabilities compared to small language models, but incur substantially higher inference costs.
Approach:	They propose a system that cascades an LLM with an SLM to achieve a balance between accuracy and cost in complex reasoning tasks.
Outcome:	The proposed system improves the SLM’s reasoning ability and confidence calibration across diverse datasets and model backbones.

Copied to clipboard

Ye Wang, Qianglong Chen, Siyuan Wang, Zejun Li, Shijie Guo, Zhirui Zhang, Zhongyu Wei

ReachAgent: Enhancing Mobile Agent via Page Reaching and Operation (2025.naacl-long)

Challenge:	Existing multimodal large language models suffer from systematic failures in basic visual understanding.
Approach:	They propose a tool-augmented reasoning framework with three targeted compensation strategies to address these problems.
Outcome:	The proposed framework improves visual grounding by re-injecting the original image to mitigate visual forgetting, the authors show . the proposed framework also improves the accuracy of the visual inputs, the researchers show - and the results are promising .

Copied to clipboard

Qinzhuo Wu, Wei Liu, Jian Luan, Bin Wang

Challenge:	Existing mobile AI agents focus on most task-relevant elements at each step, leading to local optimal solutions and ignoring the overall GUI flow.
Approach:	They propose a mobile AI agent that breaks tasks into page reaching and operation subtasks and a framework that focuses on improving its task-completion abilities.
Outcome:	The proposed framework improves IoU accuracy and text accuracy by 7.12% and 7.69% on step-level and 4.72% and 4.63% on task-level compared to the SOTA agent.

Towards Verifiable Text Generation with Evolving Memory and Self-Reflection (2024.emnlp-main)

Copied to clipboard

Hao Sun, Hengyi Cai, Bo Wang, Yingyan Hou, Xiaochi Wei, Shuaiqiang Wang, Yan Zhang, Dawei Yin

Improving Semantic Matching through Dependency-Enhanced Pre-trained Model with Adaptive Fusion (2022.findings-emnlp)

Challenge:	Large language models (LLMs) often produce factually incorrect information, also known as hallucination.
Approach:	They propose a framework for verifiable text generation with evolving memory and self-reflection that incorporates long-term memory to retain documents and recent documents.
Outcome:	The proposed framework outperforms baselines on five datasets across three knowledge-intensive tasks.

Copied to clipboard

Jian Song, Di Liang, Rumei Li, Yuntao Li, Sirui Wang, Minlong Peng, Wei Wu, Yongxin Yu

LayoutReader: Pre-training of Text and Layout for Reading Order Detection (2021.emnlp-main)

Challenge:	Existing work on dependency prior structure integration into pre-trained models is still unclear.
Approach:	They propose a dependency-based fusion attention paradigm which explicitly introduces dependency prior structure into pre-trained models and adaptively fuses it with semantic information.
Outcome:	The proposed model achieves state-of-the-art or competitive performance on 10 public datasets, demonstrating the benefits of adaptively fusing dependency structure in semantic matching task.

Copied to clipboard

Zilong Wang, Yiheng Xu, Lei Cui, Jingbo Shang, Furu Wei

ChatMusician: Understanding and Generating Music Intrinsically with LLM (2024.findings-acl)

Challenge:	Existing methods for reading order detection are too laborious to annotate large datasets.
Approach:	They propose to use a large-scale dataset to annotate reading order information for document images . they use XML metadata to capture the reading order of WORD documents .
Outcome:	The proposed model performs almost perfectly in reading order detection and improves both open-source and commercial OCR engines in ordering text lines in their results.

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

Neural Segmental Hypergraphs for Overlapping Mention Recognition (D18-1)

Challenge:	Despite LLMs' impressive capabilities in musical knowledge, music reasoning remains an unsolved task.
Approach:	They propose an open-source large language model (LLM) that integrates intrinsic musical abilities into LLaMA2 and GPT-3.5.
Outcome:	The proposed model can understand and generate music with a pure text tokenizer without external multi-modal neural structures or tokenizers.

Copied to clipboard

Bailin Wang, Wei Lu

Challenge:	Existing models that assume that mentions are non-overlapping spans in text may not perform well in practice.
Approach:	They propose a segmental hypergraph representation to model overlapping entity mentions that are prevalent in many practical datasets.
Outcome:	The proposed representation achieves state-of-the-art performance in three benchmark datasets annotated with overlapping mentions.

SGM: Sequence Generation Model for Multi-label Classification (C18-1)

Copied to clipboard

Pengcheng Yang, Xu Sun, Wei Li, Shuming Ma, Wei Wu, Houfeng Wang

Meta-CQG: A Meta-Learning Framework for Complex Question Generation over Knowledge Bases (2022.coling-1)

Challenge:	Existing methods ignore the correlations between labels and different parts of the text can contribute differently for predicting different labels.
Approach:	They propose to view the multi-label classification task as a sequence generation problem and apply a decoder-based sequence generation model to solve it.
Outcome:	The proposed methods outperform previous work by a substantial margin.

Copied to clipboard

Kun Zhang, Yunqi Qiu, Yuanzhuo Wang, Long Bai, Wei Li, Xuhui Jiang, Huawei Shen, Xueqi Cheng

From Complex to Simple: Unraveling the Cognitive Tree for Reasoning with Small Language Models (2023.findings-emnlp)

Challenge:	Existing methods train one encoder-decoder-based model to fit all questions . however, such a one-size-fits-all strategy may not perform well for complex questions involving multiple KB relations or functional constraints.
Approach:	They propose a meta-learning framework for complex question generation over knowledge bases . they propose he meta-trained generator can acquire universal meta-knowledge .
Outcome:	The proposed framework can acquire universal and transferable meta-knowledge and quickly adapt to long-tailed samples under different dimensions.

Copied to clipboard

Yan Junbing, Chengyu Wang, Taolin Zhang, Xiaofeng He, Jun Huang, Wei Zhang

VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format (2025.findings-emnlp)

Challenge:	Existing methods to solve complex logical reasoning problems are cumbersome for language models.
Approach:	They propose to use iterative methodology to construct a cognitive tree using language models . they propose to generate multiple responses by utilizing in-context examples .
Outcome:	The proposed model achieves a performance level comparable to that of GPT-3.5 . the proposed model contains fewer parameters than 5% of the model with 175B parameters .

Copied to clipboard

Yueqian Wang, Xiaojun Meng, Yuxuan Wang, Jianxin Liang, Jiansheng Wei, Huishuai Zhang, Dongyan Zhao

RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation (2025.emnlp-main)

Challenge:	Recent studies on video large language models focus on model architectures and training datasets . interaction format between user and model is unsatisfactory for time-sensitive tasks .
Approach:	They propose a video-text duet interaction format that allows for continuous playback of the video . when a text message ends, the video continues to play, similar to the alternative of two performers in a duet.
Outcome:	The proposed format improves performance on time-sensitive tasks with minimal training efforts.

Copied to clipboard

Qingyao Li, Wei Xia, Xinyi Dai, Kounianhua Du, Weiwen Liu, Yasheng Wang, Ruiming Tang, Yong Yu, Weinan Zhang

Reward Modeling Requires Automatic Adjustment Based on Data Quality (2024.findings-emnlp)

Challenge:	Existing tree search methods neglect the underlying reasoning process, resulting in poor search quality.
Approach:	They propose a framework that systematically explores and refines the reasoning process for code generation by using a tree search engine and a reflection mechanism.
Outcome:	The proposed framework outperforms existing methods in the code generation domain.

Copied to clipboard

Binghai Wang, Rui Zheng, Lu Chen, Zhiheng Xi, Wei Shen, Yuhao Zhou, Dong Yan, Tao Gui, Qi Zhang, Xuanjing Huang

Challenge:	Reinforcement Learning from Human Feedback (RLHF) is a method for aligning language models with human values.
Approach:	They propose a method that automatically adjusts reward modeling based on data quality . they use preference data to train a reward model that is more aligned with human values .
Outcome:	The proposed method stabilizes reward model training and significantly improves alignment performance on human preference datasets.

Double-Checker: Large Language Model as a Checker for Few-shot Named Entity Recognition (2024.findings-emnlp)

Copied to clipboard

Wei Chen, Lili Zhao, Zhi Zheng, Tong Xu, Yang Wang, Enhong Chen

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs (2026.acl-long)

Challenge:	Recent studies have demonstrated remarkable performance on few-shot Named Entity Recognition tasks due to the high cost of obtaining high-quality labeled data.
Approach:	They propose to decompose the task into entity span detection and entity type classification using a type-independent entity span detector and then classify the detected spans based on their types.
Outcome:	The proposed method consistently yields improvements over two baseline approaches.

Copied to clipboard

Xuanwen Ding, Chengjun Pan, Zejun Li, Jiwen Zhang, Siyuan Wang, Zhongyu Wei

Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data (N19-1)

Challenge:	Evaluating multimodal large language models (MLLMs) is becoming increasingly expensive as benchmarks grow in scale and cross-modality complexity.
Approach:	They propose an adaptive evaluation framework for efficient benchmarking that treats evaluation as an interview-like process by keeping a hypothesized ability structure of the evaluated model and actively selecting the informative questions.
Outcome:	Experiments on four representative multimodal benchmarks show that **A2-Judger significantly improves sample efficiency while maintaining reliable evaluation results.

Copied to clipboard

Wei Zhao, Liang Wang, Kewei Shen, Ruoyu Jia, Jingming Liu

Jailbreak LLMs through Internal Stance Manipulation (2025.emnlp-main)

Challenge:	Neural machine translation systems have become state-of-the-art approaches for Grammatical Error Correction (GEC) task.
Approach:	They propose a copy-augmented architecture for the Grammatical Error Correction task by copying unchanged words from the source sentence to the target sentence.
Outcome:	The proposed architecture outperforms all recently published state-of-the-art results by a large margin.

Copied to clipboard

Shuangjie Fu, Du Su, Beining Huang, Fei Sun, Jingang Wang, Wei Chen, Huawei Shen, Xueqi Cheng

Memo-SQL: Structured Decomposition and Experience-Driven Self-Correction for Training-Free NL2SQL (2026.findings-acl)

Challenge:	Existing approaches to exploit LLMs' inherent safety mechanism, including GCG and AutoDAN, are ineffective for certain malicious requests.
Approach:	They propose a method that generates jailbreak prompts to suppress a refusal stance and induce affirmative responses by modifying adversarial prompts.
Outcome:	The proposed method outperforms the best baseline approach in Llama-2-7b-chat and achieves a 92.2% success rate across all models.

Copied to clipboard

Yang Zerui, Weichuan Wang, Yanwei Xu, Linqi Song, Yudai Matsuda, Wei Han, Bo Bai

You Never Know a Person, You Only Know Their Defenses: Detecting Levels of Psychological Defense Mechanisms in Supportive Conversations (2026.findings-acl)

Challenge:	Existing NL2SQL systems rely on in-context learning with only correct examples . current test-time scaling methods often decompose questions arbitrarily, resulting in poor performance .
Approach:	They propose a structured decomposition and experience-aware self-correction framework for NL2SQL . they build a dynamic memory of successful queries and historical error–fix pairs .
Outcome:	The proposed framework achieves 68.5% execution accuracy on BIRD, setting new state of the art among open, zero-fine-tuning methods.

Copied to clipboard

Hongbin Na, Zimu Wang, Zhaoming Chen, Peilin Zhou, Yining Hua, Grace Ziqi Zhou, Haiyang Zhang, Tao Shen, Wei Wang, John Torous, Shaoxiong Ji, Ling Chen

MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding (2024.findings-emnlp)

Challenge:	Psychological defenses are strategies people use to manage distress.
Approach:	They propose a dialogue corpus with help seeker utterances labeled for defense level and a DMRS Co-Pilot pipeline that provides evidence-based pre-annotations.
Outcome:	The proposed framework reduces annotation time by 24.0% in a counterbalanced study.

Copied to clipboard

Qinzhuo Wu, Weikai Xu, Wei Liu, Tao Tan, Liujian Liujianfeng, Ang Li, Jian Luan, Bin Wang, Shuo Shang

Dynamically Composing Domain-Data Selection with Clean-Data Selection by “Co-Curricular Learning” for Neural Machine Translation (P19-1)

Challenge:	Recent mobile AI agents based on VLMs lack basic mobile capabilities due to their pre-trained nature.
Approach:	They propose a mobile AI agent based on VLMs that includes additional pre-training stages to enhance both intra- and inter-UI understanding.
Outcome:	The proposed model outperforms existing VLMs on the Chinese mobile dataset Mobile3M .

Copied to clipboard

Wei Wang, Isaac Caswell, Ciprian Chelba

SVD-GCL: A Noise-Augmented Hybrid Graph Contrastive Learning Framework for Recommendation (2025.coling-main)

Challenge:	Existing studies focus separately on domain-data selection, clean-data selecting, or their static combination, leaving the dynamic interaction across them not explicitly examined.
Approach:	They propose a method to combine dynamic domain-data selection with dynamic clean-data selecting for transfer learning across both capabilities.
Outcome:	The proposed method performs well on two domains and shows the properties of the data scheduled by the co-curriculum.

Copied to clipboard

Liping Wang, Shichao Li, Hui Wang, Yuyan Gao, Mingyao Wei

DatawiseAgent: A Notebook-Centric LLM Agent Framework for Adaptive and Robust Data Science Automation (2025.emnlp-main)

Challenge:	Recent advances in graph neural networks have made it difficult to capture user preferences.
Approach:	They propose a graph contrastive learning recommendation model based on noise augmentation that integrates truncated singular value decomposition in the feature engineering stage.
Outcome:	The proposed model reduces dimensionality and denoises the original data.

Copied to clipboard

Ziming You, Yumiao Zhang, Dexuan Xu, Yiwei Lou, Yandong Yan, Wei Wang, Huamin Zhang, Yu Huang

FusionFlow: Enabling Deep Structural Exploration for Automated Agentic Workflow Generation (2026.acl-long)

Challenge:	Existing large language model (LLM) agents for data science automation are limited by narrow task scopes, limited generalization across tasks and models, and over-reliance on state-of-the-art (SOTA) LLMs.
Approach:	They propose a notebook-centric LLM agent framework for adaptive and robust data science automation.
Outcome:	The proposed framework surpasses baselines such as AutoGen and TaskWeaver in performance tests across diverse data science scenarios and models.

Copied to clipboard

Xiang Wang, Zongtao Yang, Zhuojian Hong, Shuhao Zhang, Wei Wei

Keywords and Instances: A Hierarchical Contrastive Learning Framework Unifying Hybrid Granularities for Text Generation (2022.acl-long)

Challenge:	Existing workflow generation methods rely on incremental refinement or tree-based search over a single evolving workflow.
Approach:	They propose a framework centered on workflow fusion that synthesizes multiple independently evolved workflows and allows exploration of deeper regions of the workflow space within a finite budget.
Outcome:	Experiments show that FusionFlow outperforms existing workflow generation methods on six reasoning benchmarks.

Copied to clipboard

Mingzhe Li, XieXiong Lin, Xiuying Chen, Jinxiong Chang, Qishen Zhang, Feng Wang, Taifeng Wang, Zhongyi Liu, Wei Chu, Dongyan Zhao, Rui Yan

Bridging by Word: Image Grounded Vocabulary Construction for Visual Captioning (P19-1)

Challenge:	Existing studies focus on contrastive learning on the instance level without discriminating the contribution of each word.
Approach:	They propose a hierarchical contrastive learning mechanism which can unify semantic meaning in the input text.
Outcome:	The proposed model outperforms baselines on storytelling, paraphrasing, dialogue generation, and storytelling tasks.

Copied to clipboard

Zhihao Fan, Zhongyu Wei, Siyuan Wang, Xuanjing Huang

K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters (2021.findings-acl)

Challenge:	Existing research on image captioning generates frequent n-grams with irrelevant words.
Approach:	They propose to construct an image-grounded vocabulary incorporating visual information and relations among words into the decoding process directly.
Outcome:	The proposed framework is compared with state-of-the-art models on MS COCO and Flickr30k and shows that it is more efficient than existing models.

Copied to clipboard

Ruize Wang, Duyu Tang, Nan Duan, Zhongyu Wei, Xuanjing Huang, Jianshu Ji, Guihong Cao, Daxin Jiang, Ming Zhou

VIRT: Improving Representation-based Text Matching via Virtual Interaction (2022.emnlp-main)

Challenge:	Existing methods for injecting knowledge into pre-trained models are inconsistent and can flush out knowledge when multiple kinds of knowledge are injected.
Approach:	They propose a framework that retains the original parameters of pre-trained models fixed and supports the development of versatile knowledge-infused models.
Outcome:	The proposed framework retains the original parameters of the pre-trained model fixed and supports the development of versatile knowledge-infused models.

Copied to clipboard

Dan Li, Yang Yang, Hongyin Tang, Jiahao Liu, Qifan Wang, Jingang Wang, Tong Xu, Wei Wu, Enhong Chen

Generating Informative Conversational Response using Recurrent Knowledge-Interaction and Knowledge-Copy (2020.acl-main)

Challenge:	Experimental results show that representation-based text matching methods suffer from performance degradation due to the lack of interactions between the pair of texts.
Approach:	They propose a virtual interaction mechanism that enables deep interaction between texts . they propose 'inteRacTion mechanism' that can be integrated into existing methods as plugins .
Outcome:	The proposed method outperforms state-of-the-art models on six text matching benchmarks.

Copied to clipboard

Xiexiong Lin, Weiyu Jian, Jianshan He, Taifeng Wang, Wei Chu

Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts (2024.findings-emnlp)

Challenge:	Knowledge-driven conversation approaches have attracted considerable research attention in recent years.
Approach:	They propose a method that integrates recurrent knowledge interaction among response decoding steps to incorporate appropriate knowledge.
Outcome:	The proposed method improves on two datasets Wizard-of-Wikipedia and DuConv with different knowledge formats and different languages.

Copied to clipboard

Haoxiang Wang, Wei Xiong, Tengyang Xie, Han Zhao, Tong Zhang

FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation (2025.acl-long)

Challenge:	Reinforcement learning from human feedback (RLHF) is the primary method for aligning large language models with human preferences.
Approach:	They propose to train an Absolute-Rating Multi-Objective Reward Model with multi-dimensional absolute-rating data.
Outcome:	The proposed model outperforms the LLM-as-a-judge method on RewardBench . it achieves state-of-the-art performance on the benchmark .

Copied to clipboard

Wei Li, Xin Zhang, Zhongxin Guo, Shaoguang Mao, Wen Luo, Guangyue Peng, Yangyu Huang, Houfeng Wang, Scarlett Li

PromptBERT: Improving BERT Sentence Embeddings with Prompts (2022.emnlp-main)

Challenge:	Existing benchmarks focus on standalone programming problems, such as HumanEval, MBPP, and LiveCodeBench.
Approach:	They propose to use large language models to evaluate their ability to perform incremental development within code repositories by collecting pull requests from 83 GitHub repositorias and using rule-based and intent-based filtering to construct task instances focused on new feature development.
Outcome:	The proposed benchmarks show that large language models perform significantly worse in the FEA-Bench, highlighting considerable challenges in repository-level incremental code development.

Copied to clipboard

Ting Jiang, Jian Jiao, Shaohan Huang, Zihan Zhang, Deqing Wang, Fuzhen Zhuang, Furu Wei, Haizhen Huang, Denvy Deng, Qi Zhang

AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning (2026.findings-acl)

Challenge:	Existing research shows that BERT and RoBERTa are poor in sentence embeddings due to static token embeddable bias and ineffective BERT layers.
Approach:	They propose a novel contrastive learning method for better sentence embeddings by using a template denoising technique.
Outcome:	The proposed method achieves 2.29 and 2.58 points of improvement compared to SimCSE and RoBERTa in the unsupervised setting.

Copied to clipboard

Jingbo Sun, Wenyue Chong, Songjun Tu, Qichao Zhang, Yaocheng Zhang, Jiajun Chai, Xiaohan Wang, Wei Lin, Guojun Yin, Dongbin Zhao

EasyNLP: A Comprehensive and Easy-to-use Toolkit for Natural Language Processing (2022.emnlp-demos)

Challenge:	Prior work limits search depth to reduce cost, but this often leads to underexploration of complex questions.
Approach:	They propose a reinforcement learning framework that evaluates each search step via self-generated intermediate answers.
Outcome:	Extensive experiments on multiple benchmarks show that AutoSearch achieves a superior accuracy-efficiency trade-off, alleviating over-searching while preserving search quality.

Copied to clipboard

Chengyu Wang, Minghui Qiu, Taolin Zhang, Tingting Liu, Lei Li, Jianing Wang, Ming Wang, Jun Huang, Wei Lin

Large Language and Protein Assistant for Protein-Protein Interactions Prediction (2025.acl-long)

Challenge:	Pre-Trained Models (PTMs) have reshaped the development of natural language processing (NLP) but it is not easy to obtain high-performing PTMs without a large amount of labeled training data and deploy them online with fast inference speed.
Approach:	They propose to make it easy to build NLP applications with knowledge-enhanced pre-training and knowledge distillation.
Outcome:	EasyNLP supports a comprehensive suite of NLP algorithms and features knowledge-enhanced pre-training, knowledge distillation and few-shot learning functionalities.

Copied to clipboard

Peng Zhou, Pengsen Ma, Jianmin Wang, Xibao Cai, Haitao Huang, Wei Liu, Longyue Wang, Lai Hou Tim, Xiangxiang Zeng

Challenge:	Existing methods for predicting protein-protein interactions oversimplify the problem of PPI prediction in a semi-supervised manner.
Approach:	They propose a multimodal large language model that integrates proteins and PPI networks.
Outcome:	Experiments show that LLaPA can predict protein-protein interactions (mPPI) types and affinities based on sequence data.

Global Attention Decoder for Chinese Spelling Error Correction (2021.findings-acl)

Copied to clipboard

Zhao Guo, Yuan Ni, Keqiang Wang, Wei Zhu, Guotong Xie

InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews (2024.acl-long)

Challenge:	Existing methods for Chinese spelling error correction focus on local contextual information, thus misleading the user and reducing performance.
Approach:	They propose a global attention decoder that learns the global relationship of correct input characters and candidates of potential error characters.
Outcome:	The proposed method outperforms all competitor models by a large margin of up to 6.2% on three human-annotated datasets.

Copied to clipboard

Xintao Wang, Yunze Xiao, Jen-tse Huang, Siyu Yuan, Rui Xu, Haoran Guo, Quan Tu, Yaying Fei, Ziang Leng, Wei Wang, Jiangjie Chen, Cheng Li, Yanghua Xiao

Challenge:	Existing methods focus on knowledge and linguistic patterns of characters.
Approach:	They propose to evaluate character fidelity of role-playing agents with psychological scales . they propose to use psychological scale to measure personality traits of RPAs based on personality traits.
Outcome:	The proposed model reproduces character fidelity with psychological scales and shows that it is effective in measuring personality traits.

Symbolic Working Memory Enhances Language Models for Complex Rule Application (2024.emnlp-main)

Copied to clipboard

Siyuan Wang, Zhongyu Wei, Yejin Choi, Xiang Ren

Learning to Edit: Aligning LLMs with Knowledge Editing (2024.acl-long)

Challenge:	Large Language Models (LLMs) excel in single-step rule application but struggle with multi-step deductive reasoning when rules are presented non-sequentially.
Approach:	They propose to augment LLMs with external working memory and introduce a neurosymbolic framework for rule application that stores facts and rules in both natural language and symbolic forms, enabling precise tracking.
Outcome:	The proposed framework iteratively performs symbolic rule grounding and LLM-based rule implementation.

Copied to clipboard

Yuxin Jiang, Yufei Wang, Chuhan Wu, Wanjun Zhong, Xingshan Zeng, Jiahui Gao, Liangyou Li, Xin Jiang, Lifeng Shang, Ruiming Tang, Qun Liu, Wei Wang

Challenge:	Existing knowledge editing techniques rely on memorizing updated knowledge, impeding LLMs from effectively combining the new knowledge with their inherent knowledge when answering questions.
Approach:	They propose a Learning to Edit framework that equips LLMs with the ability to apply updated knowledge to input questions through a two-phase process .
Outcome:	The proposed framework outperforms existing methods in knowledge editing tasks and compares it with four benchmarks and two LLM architectures.

XPrompt: Exploring the Extreme of Prompt Tuning (2022.emnlp-main)

Copied to clipboard

Fang Ma, Chen Zhang, Lei Ren, Jingang Wang, Qifan Wang, Wei Wu, Xiaojun Quan, Dawei Song

PACE: Predictive Adaptive Context Extraction for Long-Horizon LLM Agents (2026.acl-long)

Challenge:	Prompt tuning learns soft prompts to condition pre-trained Language Models for performing downstream tasks in a parameter-efficient manner.
Approach:	They propose a Prompt tuning model with an eXtremely small scale that learns soft prompts to condition the frozen Pre-trained Language Models for performing downstream tasks in a parameter-efficient manner.
Outcome:	The proposed model outperforms the vanilla Prompt-Tuning and can significantly improve across tasks and model scales.

Copied to clipboard

Lei Wei, Xiao Peng, null Tt, Guannan Zhang, Chenhao Jiang, Hongyu Li, Lanbo Lin, Yuanwu Xu, Jiayao Liu, Kesu Wang, Bin Wang

Learn to Memorize: Scalable Continual Learning in Semiparametric Models with Mixture-of-Neighbors Induction Memory (2025.acl-long)

Challenge:	Large Language Model (LLM) agents struggle with ultra-long-horizon tasks requiring hundreds or thousands of interaction steps.
Approach:	They propose a framework that reconceptualizes context management as a Next Step Prediction problem.
Outcome:	The proposed framework improves task success rates and robust cross-lingual performance.

Copied to clipboard

Guangyue Peng, Tao Ge, Wen Luo, Wei Li, Houfeng Wang

Dual Dynamic Memory Network for End-to-End Multi-turn Task-oriented Dialog Systems (2020.coling-main)

Challenge:	Semiparametric language models (LMs) use static storage, which lacks learning capability and is disconnected from the internal information flow of the parametric models.
Approach:	They reconceptualize the non-parametric memory represented by kNN-LM as a learnable Mixture-of-Neighbors Induction Memory (MoNIM) this synergizes the induction capabilities of attention heads with the memorization strength of feed-forward networks .
Outcome:	The proposed model is a learnable Mixture-of-neighbors induction memory (MoNIM) it synergizes the induction capabilities of attention heads with the memorization strength of feed-forward networks (FFNs).

Copied to clipboard

Jian Wang, Junhao Liu, Wei Bi, Xiaojiang Liu, Kejing He, Ruifeng Xu, Min Yang

SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters (2025.naacl-long)

Challenge:	Existing task-oriented dialog systems struggle to dynamically model long dialog context for interactions and effectively incorporate knowledge base (KB) information into dialog generation.
Approach:	They propose a dual dynamic memory network for multi-turn dialog generation . the model dynamically expands the dialog memory turn by turn and keeps track of dialog history .
Outcome:	The proposed model outperforms baseline models on three benchmark datasets on human evaluation and automatic evaluation.

Copied to clipboard

Yan Yang, Zeguan Xiao, Xin Lu, Hongru Wang, Xuetao Wei, Hailiang Huang, Guanhua Chen, Yun Chen

Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation (2022.emnlp-main)

Challenge:	Existing studies have focused on the potential misuse of large language models (LLMs) however, the ability to align LLMs with human values is still vulnerable to malicious attacks.
Approach:	They propose a red-teaming strategy to enhance LLM safety by using a framework to design jailbreak prompts automatically.
Outcome:	The proposed framework achieves attack success rates of 88% and 60% in cold-start scenarios.

Copied to clipboard

Chen Wang, Yuchen Liu, Boxing Chen, Jiajun Zhang, Wei Luo, Zhongqiang Huang, Chengqing Zong

Interleaved Latent Visual Reasoning with Selective Perceptual Modeling (2026.acl-long)

Challenge:	Existing zero-shot methods fail to align speech and text into a shared semantic space . Existing methods require expensive and expensive parallel ST data .
Approach:	They propose a method that uses a shared discrete vocabulary space to align speech and text into a common space.
Outcome:	The proposed method significantly improves the SOTA and even performs on par with the strong supervised ST baselines.

Copied to clipboard

Shuai Dong, Siyuan Wang, Xingyu Liu, Chenglin Li, Haowen Hou, Zhongyu Wei

Beyond Transcription: Unified Audio Schema for Perception-Aware AudioLLMs (2026.findings-acl)

Challenge:	Existing approaches to interleaved reasoning are limited by the cost of re-encoding pixel-dense images.
Approach:	They propose a framework that unifies dynamic state evolution with precise perceptual modeling.
Outcome:	The proposed framework outperforms existing approaches on multimodal reasoning benchmarks.

Copied to clipboard

Linhao Zhang, Yuhan Song, Aiwei Liu, Chuhan Wu, Sijun Zhang, Wei Jia, Yuan Liu, Houfeng Wang, Zhou Xiao

Multi-Granularity Hierarchical Attention Fusion Networks for Reading Comprehension and Question Answering (P18-1)

Challenge:	Recent Audio Large Language Models (AudioLLMs) excel at reasoning tasks, but struggle at elementary auditory perception.
Approach:	They propose a framework that organizes audio information into three explicit components in a unified JSON format.
Outcome:	The proposed framework boosts fine-grained perception by 10.9% on MMSU over state-of-the-art models while preserving robust reasoning capabilities.

Copied to clipboard

Wei Wang, Ming Yan, Chen Wu

IGenBench: Benchmarking the Reliability of Text-to-Infographic Generation (2026.acl-long)

Challenge:	Existing approaches to read comprehension style question answering are limited by the volume of annotated datasets.
Approach:	They propose a hierarchical attention network for reading comprehension style question answering . they first encode the question and paragraph with fine-grained language embeddings . then propose fusion approach to fuse information from both global and attended representations based on the hierarchic attention network .
Outcome:	The proposed method achieves state-of-the-art on the SQuAD and TriviaQA Wiki leaderboards and two adversarial SQu AD datasets.

Copied to clipboard

Yinghao Tang, Xueding Liu, Boyuan Zhang, Tingfeng Lan, Yupeng Xie, Jiale Lao, Yiyao Wang, Haoxuan Li, Tingting Gao, Bo Pan, Luoxuan Weng, Xiuqi Huang, Minfeng Zhu, Yingchaojie Feng, Yuyu Luo, Wei Chen

PURE: Aligning LLM via Pluggable Query Reformulation for Enhanced Helpfulness (2024.findings-emnlp)

Challenge:	Generated infographics may appear correct at first glance but contain easily overlooked issues, such as distorted data encoding or incorrect textual content.
Approach:	They propose to evaluate reliability of text-to-infographic generation using IGenBench . they employ multimodal large language models to verify each question .
Outcome:	The proposed framework decomposes reliability verification into atomic yes/no questions based on a taxonomy of 10 question types.

Copied to clipboard

Wenjin Yao, Yidong Wang, Zhuohao Yu, Rui Xie, Shikun Zhang, Wei Ye

Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia (2025.acl-long)

Challenge:	Large language models (LLMs) depend on vast amounts of text data sourced from the Internet for their training.
Approach:	They propose a new alignment paradigm that reformulates risky queries into highly relevant yet harmless ones before feeding them into LLMs.
Outcome:	The proposed approach eliminates the high costs of training base LLMs and achieves a promising balance of harmlessness and helpfulness.

Copied to clipboard

Samuel Cahyawijaya, Holy Lovenia, Joel Ruben Antony Moniz, Tack Hwa Wong, Mohammad Rifqi Farhansyah, Thant Thiri Maung, Frederikus Hudi, David Anugraha, Muhammad Ravi Shulthan Habibi, Muhammad Reza Qorib, Amit Agarwal, Joseph Marvin Imperial, Hitesh Laxmichand Patel, Vicky Feliren, Bahrul Ilmi Nasution, Manuel Antonio Rufino, Genta Indra Winata, Rian Adam Rajagede, Carlos Rafael Catalan, Mohamed Fazli Mohamed Imam, Priyaranjan Pattnayak, Salsabila Zahirah Pranida, Kevin Pratama, Yeshil Bangera, Adisai Na-Thalang, Patricia Nicole Monderin, Yueqi Song, Christian Simon, Lynnette Hui Xian Ng, Richardy Lobo Sapan, Taki Hasan Rafi, Bin Wang, null Supryadi, Kanyakorn Veerakanjana, Piyalitt Ittichaiwong, Matthew Theodore Roque, Karissa Vincentio, Takdanai Kreangphet, Phakphum Artkaew, Kadek Hendrawan Palgunadi, Yanzhi Yu, Rochana Prih Hastuti, William Nixon, Mithil Bangera, Adrian Xuan Wei Lim, Aye Hninn Khine, Hanif Muhammad Zhafran, Teddy Ferdinan, Audra Aurora Izzani, Ayushman Singh, Evan Evan, Jauza Akbar Krito, Michael Anugraha, Fenal Ashokbhai Ilasariya, Haochen Li, John Amadeo Daniswara, Filbert Aurelian Tjiaranata, Eryawan Presma Yulianrifat, Can Udomcharoenchaikit, Fadil Risdian Ansori, Mahardika Krisna Ihsani, Giang Nguyen, Anab Maulana Barik, Dan John Velasco, Rifo Ahmad Genadi, Saptarshi Saha, Chengwei Wei, Isaiah Edri W. Flores, Kenneth Chen Ko Han, Anjela Gail D. Santos, Wan Shen Lim, Kaung Si Phyo, Tim Santos, Meisyarah Dwiastuti, Jiayun Luo, Jan Christian Blaise Cruz, Ming Shan Hee, Ikhlasul Akmal Hanif, M.Alif Al Hakim, Muhammad Rizky Sya’ban, Kun Kerdthaisong, Lester James Validad Miranda, Fajri Koto, Tirana Noor Fatyanosa, Alham Fikri Aji, Jostin Jerico Rosal, Jun Kevin, Robert Wijaya, Onno P. Kampman, Ruochen Zhang, Börje F. Karlsson, Peerat Limkonchotiwat

Label-Free Distant Supervision for Relation Extraction via Knowledge Graph Embedding (D18-1)

Challenge:	Southeast Asia is underrepresented in vision-language research . SEA-VL is an open-source initiative dedicated to developing culturally relevant datasets for SEA languages.
Approach:	They propose to use crowdsourced, automated image crawling and synthetic image generation to develop culturally relevant datasets for SEA languages.
Outcome:	The proposed datasets capture SEA cultural nuances and contexts better than existing datasets.

Copied to clipboard

Guanying Wang, Wen Zhang, Ruoxu Wang, Yalin Zhou, Xi Chen, Wei Zhang, Hai Zhu, Huajun Chen

Robust Lottery Tickets for Pre-trained Language Models (2022.acl-long)

Challenge:	Existing methods to generate large scale labeled data for relation extraction produce noisy relation labels when there are multiple relationships between entities.
Approach:	They propose a method which assumes that a pair of entities appears in a Knowledge Graph and trains a relation classifier.
Outcome:	The proposed method performs well in the current distant supervision dataset.

Copied to clipboard

Rui Zheng, Bao Rong, Yuhao Zhou, Di Liang, Sirui Wang, Wei Wu, Tao Gui, Qi Zhang, Xuanjing Huang

Don’t Click That: Teaching Web Agents to Resist Deceptive Interfaces (2026.acl-long)

Challenge:	Recent studies have shown that pre-trained language models contain smaller matching subnetworks that are not robust to adversarial examples.
Approach:	They propose a method to find robust tickets hidden in pre-trained language models by learning binary weight masks and an adversarial loss objective to guide the search.
Outcome:	The proposed method improves on previous work on adversarial robustness evaluation.

Copied to clipboard

Yilin Zhang, Yingkai Hua, Chunyu Wei, Xin Wang, Yueguo Chen

Challenge:	Existing approaches to deception detection and defenses are inadequate . Existing methods do not integrate with agent decision-making .
Approach:	They propose a framework that integrates hybrid-reward learning with asymmetric penalties and experience summarization to distill failure patterns into transferable guidance.
Outcome:	The proposed framework reduces deception susceptibility by 53.8% while maintaining task performance, establishing an effective foundation for robust web agent deployment.

O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning (2026.findings-acl)

Copied to clipboard

Haotian Luo, Haiying He, Yibo Wang, Shiwei Liu, Wei Li, Xiaochun Cao, Dacheng Tao, Naiqiang Tan, Li Shen

Let Me Check the Examples: Enhancing Demonstration Learning via Explicit Imitation (2023.acl-short)

Challenge:	Recent long-thought reasoning models adopt extended reasoning processes similar to how humans ponder over complex problems.
Approach:	They propose a model that uses RL-style fine-tuning to reduce inference overhead while maintaining accuracy.
Outcome:	The proposed model reduces inference overhead while maintaining accuracy.

Copied to clipboard

Sirui Wang, Kaiwen Wei, Hongzhi Zhang, Yuntao Li, Wei Wu

MAUD: An Expert-Annotated Legal NLP Dataset for Merger Agreement Understanding (2023.emnlp-main)

Challenge:	Existing work only concatenates answered examples as demonstrations to prompt template without any additional operation, neglecting the prompt-demonstration dependencies.
Approach:	They propose to concatenate answered examples as demonstrations to prompt template without any additional operation, neglecting the prompt-demonstration dependencies.
Outcome:	Experiments show that the proposed method achieves state-of-the-art performance on 5 out of 14 classification corpus.

Copied to clipboard

Steven Wang, Antoine Scardigli, Leonard Tang, Wei Chen, Dmitry Levkin, Anya Chen, Spencer Ball, Thomas Woodside, Oliver Zhang, Dan Hendrycks

TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection (2025.emnlp-main)

Challenge:	Merger Agreement Understanding Dataset (MAUD) is an expert-annotated reading comprehension dataset based on the American Bar Association's 2021 Public Target Deal Points Study.
Approach:	They propose a Merger Agreement Understanding Dataset with over 39,000 examples and over 47,000 annotations.
Outcome:	The Merger Agreement Understanding Dataset (MAUD) is an expert-annotated reading comprehension dataset based on the American Bar Association's 2021 Public Target Deal Points Study.

Copied to clipboard

Wei Wu, Zhuoshi Pan, Kun Fu, Chao Wang, Liyi Chen, Yunchu Bai, Tianfu Wang, Zheng Wang, Hui Xiong

MPPO: Multi Pair-wise Preference Optimization for LLMs with Arbitrary Negative Samples (2025.coling-main)

Challenge:	Rapid advances in Large Language Models have spurred demand for processing extended context sequences . however, performance degradation due to sequence lengths out-of-distribution and excessively long inference times are limiting LLMs in long-context scenarios.
Approach:	They propose a training-free method for efficient and accurate long-context inference . they selectively involves a few critical KV cache tokens in attention calculation .
Outcome:	The proposed method speeds up attention computation and accelerates inference time while reducing selection overhead.

Copied to clipboard

Shuo Xie, Fangzhi Zhu, Jiahui Wang, Lulu Wen, Wei Dai, Xiaowei Chen, Junxiong Zhu, Kai Zhou, Bo Zheng

Challenge:	Existing preference optimization methods such as DPO and KTO are inherently derived from PPO, requiring a reference model that adds GPU memory resources and relies heavily on abundant preference data.
Approach:	They propose an algorithm that leverages the average likelihood of model responses to fit the reward function and maximizes the utilization of preference data.
Outcome:	The proposed algorithm outperforms DPO, ORPO, and SimPO on MT-Bench and Arena-Hard.

From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models (2026.findings-acl)

Copied to clipboard

Junlong Tong, Zilong Wang, YuJie Ren, Peiran Yin, Hao Wu, Wei Zhang, Xiaoyu Shen

Uncovering Argumentative Flow: A Question-Focus Discourse Structuring Framework (2025.emnlp-main)

Challenge:	Existing definitions of streaming LLMs are fragmented and lack a systematic taxonomy . large language models are pre-trained on static and full-context corpora .
Approach:	They propose a systematic taxonomy of current streaming Large Language Models and propose underlying methodologies for streaming LLMs.
Outcome:	The proposed model is based on data flow and dynamic interaction to clarify existing ambiguities.

Copied to clipboard

Yini Wang, Xian Zhou, Shengan Zheng, Linpeng Huang, Zhunchen Luo, Wei Luo, Xiaoying Bai

GOME: Grounding-based Metaphor Binding With Conceptual Elaboration For Figurative Language Illustration (2024.emnlp-main)

Challenge:	Existing structure modeling approaches fail to capture the author’s rhetorical intent and reasoning process.
Approach:	They propose a Question-Focus discourse structuring framework that explicitly models the underlying argumentative flow by anchoring each argumentative unit to a guiding question and a set of attentional foci.
Outcome:	The proposed framework outperforms baseline models and curated models on an argument reconstruction task in Chinese think-tank articles and claims coverage.

Copied to clipboard

Linhao Zhang, Jintao Liu, Li Jin, Hao Wang, Kaiwen Wei, Guangluan Xu

Adversarial Preference Learning for Robust LLM Alignment (2025.findings-acl)

Challenge:	Existing Large Language Models (LLMs) and multimodal models are unable to illustrate figurative language based on literal objects, ignoring the underlying groundings and associations across disparate metaphorical domains.
Approach:	They propose a grounding-based method for metaphor illustration that integrates metaphorical knowledge into systematic instructions for existing large language models.
Outcome:	The proposed method is superior to existing LLMs, diffusion models, or their direct collaboration.

Copied to clipboard

Yuanfu Wang, Pengyu Wang, Chenyang Xi, Bo Tang, Junyi Zhu, Wenqiang Wei, Chen Chen, Chao Yang, Jingfeng Zhang, Chaochao Lu, Yijun Niu, Keming Mao, Zhiyu Li, Feiyu Xiong, Jie Hu, Mingchuan Yang

LoPT: Lossless Parallel Tokenization Acceleration for Long Context Inference of Large Language Model (2026.acl-long)

Challenge:	Modern language models rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors, but they remain vulnerable to adversarial attacks due to three key limitations: (1) the inefficiency and high cost of human annotation; (2) the vast diversity of potential adversarials; and (3) the risk of feedback bias and reward hacking.
Approach:	They propose an iterative adversarial training method that incorporates three key innovations to address these challenges.
Outcome:	Experiments on Mistral-7B-Instruct-v0.3 show that the proposed method significantly enhances robustness and reduces harmful outputs from 5.88% to 0.43%.

Copied to clipboard

Wei Shao, Zheng Lingchao, Pengyu Wang, Peizhen Zheng, Li Jun, Yuwei Fan

Learning from LLM Agents: In-Context Generative Models for Text Casing in E-Commerce Ads (2025.emnlp-industry)

Challenge:	Existing parallel tokenization methods suffer from inconsistent results due to boundary artifacts that occur after merging.
Approach:	They propose a Lossless Parallel Tokenization framework that ensures output identical to standard sequential tokenization.
Outcome:	The proposed method achieves significant speedup while guaranteeing lossless tokenization.

Copied to clipboard

Yingxue Zhou, Tan Zhu, Tao Zeng, Zigeng Wang, Wei Shen

Long Document Ranking with Query-Directed Sparse Transformer (2020.findings-emnlp)

Challenge:	Existing NER-based transformer models are expensive and lack contextual dependencies, making them less reliable when handling unseen or ad-specific terms, e.g., brand names.
Approach:	They propose a two-stage approach to casing correction in e-commerce ad content that leverages Chain-of-Actions to enforce content policies while accurately handling ads-specific terms.
Outcome:	The proposed model outperforms existing NER-based models and achieves near-LLM performance at a fraction of the cost.

Copied to clipboard

Jyun-Yu Jiang, Chenyan Xiong, Chia-Jung Lee, Wei Wang

GRAPHIA: Harnessing Social Graph Data to Enhance LLM-Based Social Simulation (2026.acl-long)

Challenge:	Existing approaches to document ranking require long documents to be broken to fit in pretrained models.
Approach:	They propose a Query-Directed Sparse attention model that induces IR-axiomatic structures in transformer self-attention.
Outcome:	The proposed model enforces the principle properties desired in ranking while also enjoying efficiency from sparsity.

Copied to clipboard

Jiarui Ji, Zehua Zhang, Zhewei Wei, Bin Tong, Guan Wang, Bo Zheng

Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation (2024.findings-acl)

Challenge:	Social graphs provide high-quality supervision signals that encode local interactions and global network structure, yet they remain underutilized for LLM training.
Approach:	They propose a general LLM-based social graph simulation framework that leverages graph data as supervision for LLM training.
Outcome:	The proposed framework improves micro-level alignment by 6.1% on three real-world networks compared to the strongest baseline.

Copied to clipboard

Ruomeng Ding, Chaoyun Zhang, Lu Wang, Yong Xu, Minghua Ma, Wei Zhang, Si Qin, Saravan Rajmohan, Qingwei Lin, Dongmei Zhang

Challenge:	Recent advances in Large Language Models (LLMs) have greatly advanced problem solving in diverse domains such as mathematical reasoning and knowledge reasoning.
Approach:	They propose a thought prompting approach called 'Everything of Thoughts' it leverages pretrained reinforcement learning and Monte Carlo Tree Search to incorporate external domain knowledge and planning capability into thoughts.
Outcome:	The proposed approach outperforms existing approaches on game of 24, 8-Puzzle, and Pocket Cube.

Mem2Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation (2026.acl-long)

Copied to clipboard

Zihao Cheng, Zeming Liu, Yingyu Shan, Xinyi Wang, Xiangrong Zhu, Yunpu Ma, Hongru Wang, Yuhang Guo, Wei Lin, Yunhong Wang

ClimAgent: LLM as Agents for Autonomous Open-ended Climate Science Analysis (2026.findings-acl)

Challenge:	Existing frameworks that focus on static tools and static assets are ineffective for self-evolving agents.
Approach:	They propose a paradigm of co-evolutionary Capability Expansion and Experience Distillation that leverages accumulated experience to guide dynamic creation of assets.
Outcome:	The proposed framework improves performance in single-task and cross-task settings by 18.53% over standard LLMs, 11.80% over agents evolving solely through experience, and 6.46% over those evolving solelly through asset creation.

Copied to clipboard

Hao Wang, Jindong Han, Wei Fan, Hao Liu

Challenge:	Existing approaches to climate research are limited to simple Q A tasks . a lack of data and computational expertise has created bottlenecks .
Approach:	They propose a general-purpose autonomous framework to perform end-to-end climate research tasks across diverse climate sub-fields.
Outcome:	The proposed framework outperforms state-of-the-art benchmarks in rigorousness and practicality.

Cross-lingual Multimodal Sentiment Analysis for Low-Resource Languages via Language Family Disentanglement and Rethinking Transfer (2025.findings-acl)

Copied to clipboard

Long Chen, Shuoyu Guan, Xiaohua Huang, Wen-Jing Wang, Cai Xu, Ziyu Guan, Wei Zhao

How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition (2024.acl-long)

Challenge:	Existing multimodal sentiment analysis methods are limited to textual data and cannot handle multimodal scenarios.
Approach:	They propose a transfer learning framework that allows cross-lingual and cross-modal alignments and a language family disentanglement module that enhances the sharing of language universals within families.
Outcome:	The proposed method is superior to existing methods and can handle low-resource languages.

Copied to clipboard

Guanting Dong, Hongyi Yuan, Keming Lu, Chengpeng Li, Mingfeng Xue, Dayiheng Liu, Wei Wang, Zheng Yuan, Chang Zhou, Jingren Zhou

Towards Effective and Efficient Continual Pre-training of Large Language Models (2025.acl-long)

Challenge:	supervised fine-tuning (SFT) is a technique used to enhance multiple abilities in large language models.
Approach:	They propose to study the interplay of data composition between mathematical reasoning, code generation, and general human-aligning abilities during supervised fine-tuning.
Outcome:	The proposed model improves math reasoning and code generation with increasing data amount . the proposed model size and SFT strategies can be used to learn multiple skills with different scaling patterns.

Copied to clipboard

Jie Chen, Zhipeng Chen, Jiapeng Wang, Kun Zhou, Yutao Zhu, Jinhao Jiang, Yingqian Min, Xin Zhao, Zhicheng Dou, Jiaxin Mao, Yankai Lin, Ruihua Song, Jun Xu, Xu Chen, Rui Yan, Zhewei Wei, Di Hu, Wenbing Huang, Ji-Rong Wen

Watch Every Step! LLM Agent Learning via Iterative Step-level Process Refinement (2024.emnlp-main)

Challenge:	Continual pre-training (CPT) has been an important approach for adapting language models to specific domains or tasks.
Approach:	They propose a Continual pre-training method that can greatly improve Chinese language ability and scientific reasoning ability of LLMs.
Outcome:	The proposed method can greatly improve Chinese language ability and scientific reasoning ability of LLMs.

Copied to clipboard

Weimin Xiong, Yifan Song, Xiutian Zhao, Wenhao Wu, Xun Wang, Ke Wang, Cheng Li, Wei Peng, Sujian Li

ChatHF: Collecting Rich Human Feedback from Real-time Conversations (2024.emnlp-demo)

Challenge:	Recent approaches to enhance agent performance focus on outcome rewards, which may lead to errors or suboptimal actions due to the absence of process supervision signals.
Approach:	They propose a step-level framework that provides detailed step-by-step guidance to enhance agent training by using Monte Carlo methods.
Outcome:	The proposed framework outperforms strong baselines on three tasks and shows that it is effective in augmenting efficiency and its applicability to diverse models.

Copied to clipboard

Andrew Li, Zhenduo Wang, Ethan Mendes, Duong Le, Wei Xu, Alan Ritter

InfuserKI: Enhancing Large Language Models with Knowledge Graphs via Infuser-Guided Knowledge Integration (2024.findings-emnlp)

Challenge:	We present an interactive framework for chatbot evaluation that integrates configurable annotation within a chat interface.
Approach:	They propose an interactive framework for chatbot evaluation that integrates configurable annotation within a chat interface.
Outcome:	The proposed framework supports fine-grained error detection and human evaluation at the same time.

Copied to clipboard

Fali Wang, Runxue Bao, Suhang Wang, Wenchao Yu, Yanchi Liu, Wei Cheng, Haifeng Chen

Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memory (2026.acl-long)

Challenge:	Large Language Models have exceptional capabilities in open generation, yet they encounter difficulties with tasks that require intensive knowledge.
Approach:	They propose a framework that integrates unknown knowledge into LLMs without overlap . they propose integrating domain-specific knowledge graphs into Llms to reduce knowledge forgetting .
Outcome:	The proposed framework outperforms state-of-the-art baselines in integrating new knowledge into LLMs.

Copied to clipboard

Sen Hu, Yuxiang Wei, Jiaxin Ran, Xueran Han, Zhiyuan Yao, Huacan Wang, Ronghao Chen, Lei Zou

STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning (2026.acl-long)

Challenge:	Existing literature on dialog memory systems is inconsistent on their effectiveness . empirical findings on graph structures are difficult to attribute to specific design choices .
Approach:	They propose a framework that decomposes dialog memory systems into core components . they conduct stage-wise experiments on LongMemEval and HaluMeM, and compare implementation details .
Outcome:	The proposed framework compares graph-based and non-graph memory architectures on long-term dialog memory systems.

Copied to clipboard

Juntong Ni, Shiyu Wang, Qi He, Ming Jin, Wei Jin

SgSum:Transforming Multi-document Summarization into Sub-graph Selection (2021.emnlp-main)

Challenge:	Existing models focus on predictive accuracy over reasoning, a gap exists . time series data are ubiquitous in real-world systems and exhibit complex spatio-temporal structures.
Approach:	They propose a time series reasoning model that integrates time series, graph structure, and text for explicit reasoning.
Outcome:	The proposed model achieves average accuracy gains between 17% and 135% at 0.004x the cost of proprietary models and generalizes robustly to real-world data.

Copied to clipboard

Moye Chen, Wei Li, Jiachen Liu, Xinyan Xiao, Hua Wu, Haifeng Wang

Minimal Distillation Schedule for Extreme Language Model Compression (2024.findings-eacl)

Challenge:	Existing extractive multi-document summarization methods score each sentence individually and extract salient sentences one by one.
Approach:	They propose a novel framework for extractive multi-document summarization that selects a sub-graph as the summary instead of selecting salient sentences.
Outcome:	The proposed framework improves on existing methods on multi-document datasets and human evaluations show it produces more coherent and informative summaries.

Copied to clipboard

Chen Zhang, Yang Yang, Qifan Wang, Jiahao Liu, Jingang Wang, Wei Wu, Dawei Song

Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills (2025.emnlp-main)

Challenge:	Existing methods for teacher assistant-based distillation require multiple trials to find the optimal teacher assistant.
Approach:	They propose a method that allows scheduling of an optimal teacher assistant in just one trial . they show that student performance is positively correlated with the scale-performance tradeoff .
Outcome:	The proposed method can select the optimal teacher assistant in just one trial . it can be used to compare performance of student and teacher assistants on GLUE benchmarks.

Copied to clipboard

Changsheng Wang, Chongyu Fan, Yihua Zhang, Jinghan Jia, Dennis Wei, Parikshit Ram, Nathalie Baracaldo, Sijia Liu

DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination (2024.emnlp-main)

Challenge:	Existing methods for LRM unlearning overlook critical information leakage in reasoning traces, even when final answers are successfully removed.
Approach:	They propose a method that suppresses reasoning traces while preserving the model's general reasoning ability.
Outcome:	The proposed method significantly reduces reasoning trace leakage and achieves strong performance across reasoning and safety benchmarks, including WMDP, StrongReject, JBB-Behaviors and WildJailbreak.

Copied to clipboard

Xuan Gong, Tianshi Ming, Xinpeng Wang, Zhihua Wei

DataSciBench: An LLM Agent Benchmark for Data Science (2026.findings-acl)

Challenge:	Despite the success of Large Vision-Language Models, they suffer from hallucination.
Approach:	They propose a training-free strategy that "Dive into" the attention of LVLMs to "Reduce" object hallucination by using classification tokens of ViT.
Outcome:	The proposed method reduces the impact of outlier tokens on LVLMs . the proposed method is based on LLaVA-1.5, LLvaVA-NeXT and InstructBLIP .

Copied to clipboard

Dan Zhang, Sining Zhoubian, Min Cai, Fengzu Li, Lekang Yang, Wei Wang, Tianjiao Dong, Ziniu Hu, Jie Tang, Yisong Yue

Challenge:	Existing benchmarks focus on single task, simple evaluation metrics, and readily available ground truth (GT) DataSciBench is built on curated, natural, and challenging prompts with complex evaluation criteria and uncertain GT.
Approach:	They propose a benchmark for evaluating Large Language Models in data science that integrates LLM-based self-consistency and human verification to ensure accuracy.
Outcome:	The proposed framework outperforms open-source models in all metrics and offers rigorous insights into LLM strengths and weaknesses.

Question Directed Graph Attention Network for Numerical Reasoning over Text (2020.emnlp-main)

Copied to clipboard

Kunlong Chen, Weidi Xu, Xingyi Cheng, Zou Xiaochuan, Yuyu Zhang, Le Song, Taifeng Wang, Yuan Qi, Wei Chu

Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory (N19-1)

Challenge:	Numerical reasoning requires both natural language understanding and arithmetic computation.
Approach:	They propose a graph representation for the context of the passage and question needed for numerical reasoning.
Outcome:	The proposed model achieves remarkable results in benchmark datasets such as DROP.

Copied to clipboard

Deng Cai, Yan Wang, Wei Bi, Zhaopeng Tu, Xiaojiang Liu, Wai Lam, Shuming Shi

ORCHID: A Chinese Debate Corpus for Target-Independent Stance Detection and Argumentative Dialogue Summarization (2023.emnlp-main)

Challenge:	Existing generative dialogue models generate responses from input queries . however, the results are limited and the models are unsatisfactory .
Approach:	They propose a framework which exploits retrieval results via a skeleton-to-response paradigm . they extract a query skelet and use it to generate a new skele and response .
Outcome:	The proposed approach significantly improves the informativeness of the generated responses.

Copied to clipboard

Xiutian Zhao, Ke Wang, Wei Peng

Question Condensing Networks for Answer Selection in Community Question Answering (P18-1)

Challenge:	Recent development of large language models (LLMs) have boosted interest on dialogue agents . however, research on these tasks is limited by the insufficiency of public datasets . stance detection and debate summarization are key for engaging argumentative dialogues - but are not available for non-English languages.
Approach:	They propose to use ORCHID to benchmark stance detection and debate summarization in Chinese debates.
Outcome:	The proposed task is based on 1,218 real-world debates conducted in Chinese on 476 unique topics.

Copied to clipboard

Wei Wu, Xu Sun, Houfeng Wang

SATBench: Benchmarking LLMs’ Logical Reasoning via Automated Puzzle Generation from SAT Formulas (2025.emnlp-main)

Challenge:	Community question answering (CQA) is a subtask of community question answering . previous researches ignored the difference between the two parts and concatenated them as the question representation .
Approach:	They propose a question condensing network that makes use of the subject-body relationship of community questions.
Outcome:	The proposed model outperforms existing models on two CQA datasets.

Copied to clipboard

Anjiang Wei, Yuheng Wu, Yingjia Wan, Tarun Suresh, Huanmi Tan, Zhanke Zhou, Sanmi Koyejo, Ke Wang, Alex Aiken

ViDove: A Translation Agent System with Multimodal Context and Memory-Augmented Reasoning (2025.emnlp-demos)

Challenge:	SATBench is a benchmark for evaluating the logical reasoning capabilities of large language models (LLMs) through logical puzzles derived from Boolean satisfiability (SAT) problems.
Approach:	They propose a benchmark to evaluate logical reasoning capabilities of large language models (LLMs) using logical puzzles derived from Boolean satisfiability problems.
Outcome:	The proposed model achieves 65.0% accuracy on hard UNSAT problems, close to the baseline of 50%.

Copied to clipboard

Yichen Lu, Wei Dai, Jiaen Liu, Ching Wing Kwok, Zongheng Wu, Xudong Xiao, Ao Sun, Sheng Fu, Jianyuan Zhan, Yian Wang, Takatomo Saito, Sicheng Lai

DyBBT: Dynamic Balance via Bandit-inspired Targeting for Dialog Policy with Cognitive Dual Systems (2026.acl-long)

Challenge:	Recent advances in Large Language Models (LLMs) have demonstrated remarkable capabilities in Machine Translation (MT) tasks.
Approach:	They propose a translation agent system designed for multimodal input that leverages visual and contextual background information to enhance the translation process.
Outcome:	The proposed translation agent achieves significantly higher translation quality in subtitle generation and general translation tasks compared to previous state-of-the-art systems.

Copied to clipboard

Shuyu Zhang, Yifan Wei, Jialuo Yuan, Xinru Wang, Yanmin Zhu, Yujie Liu, Bin Li

JTAV: Jointly Learning Social Media Content Representation by Fusing Textual, Acoustic, and Visual Features (C18-1)

Challenge:	Task oriented dialog systems often rely on static exploration strategies that do not adapt to dynamic dialog contexts.
Approach:	They propose a dialog policy learning framework that formalizes the exploration challenge through a structured cognitive state space C.
Outcome:	The proposed framework achieves SOTA performance in success rate, efficiency, and generalization.

Copied to clipboard

Hongru Liang, Haozheng Wang, Jun Wang, Shaodi You, Zhe Sun, Jin-Mao Wei, Zhenglu Yang

SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Models (2025.emnlp-main)

Challenge:	Existing studies on learning social media content focus on single modal or bi-modal learning, but this approach is non-trivial and challenging because content is multi-modal and involves several types of data, including text, audio, and image.
Approach:	They propose to combine textual, acoustic, and visual information to learn social media content by fusing them jointly.
Outcome:	The proposed model outperforms the state-of-the-art approaches on real-world datasets by a large margin.

Copied to clipboard

Peng Ding, Wen Sun, Dailin Li, Wei Zou, Jiaming Wang, Jiajun Chen, Shujian Huang

Towards Making the Most of Cross-Lingual Transfer for Zero-Shot Neural Machine Translation (2022.acl-long)

Challenge:	Large Language Models (LLMs) excel at various tasks but are vulnerable to jailbreak attacks that induce harmful content generation.
Approach:	They propose a reinforcement learning framework that leverages the model’s own discrimination capabilities as a reward signal to enhance generation safety through iterative self-improvement.
Outcome:	The proposed framework improves model safety by iterative self-improvement without additional annotated data or external models during training phase.

Copied to clipboard

Guanhua Chen, Shuming Ma, Yun Chen, Dongdong Zhang, Jia Pan, Wenping Wang, Furu Wei

Skill-Aware Data Selection and Fine-Tuning for Data-Efficient Reasoning Distillation (2026.acl-short)

Challenge:	Existing unsupervised neural machine translation systems can degrade when labeled data is limited.
Approach:	They propose a multilingual pretraining and multilingual fine-tuning for facilitating cross-lingual transfer in zero-shot translation using a parallel dataset.
Outcome:	The proposed model outperforms state-of-the-art models on many-to-English translation by over 7.2 and 5.0 BLEU.

Copied to clipboard

Lechen Zhang, Yunxiang Zhang, Wei Hu, Lu Wang

Cross-lingual Feature Extraction from Monolingual Corpora for Low-resource Unsupervised Bilingual Lexicon Induction (2022.coling-1)

Challenge:	Large reasoning models such as DeepSeek-R1 and their distilled variants achieve impressive performance on complex reasoning tasks, yet their costs remain substantial.
Approach:	They propose a skill-centric distillation framework that efficiently transfers reasoning ability to weaker models with two components: (1) Skill-based data selection, which prioritizes examples targeting the student model’s weaker skills, and (2) Skillaware fine-tuning, which encourages explicit skill decomposition during problem solving.
Outcome:	The proposed framework surpasses baselines on Qwen3-4B and Qwend3-8B and focuses on skills emphasized during training.

Copied to clipboard

Zihao Feng, Hailong Cao, Tiejun Zhao, Weixuan Wang, Wei Peng

Enhancing Air Quality Prediction with Social Media and Natural Language Processing (P19-1)

Challenge:	Unsupervised bilingual lexicon induction models fail on low-resource language pairs due to insufficient initialization.
Approach:	They propose a method to learn cross-lingual features from monolingual corpora for low-resource UBLI by integrating cross-linguistic representations with pre-trained word embeddings in a fully unsupervised initialization.
Outcome:	The proposed method outperforms state-of-the-art methods on low-resource language pairs and improves representational ability and robustness of existing embedding models.

Copied to clipboard

Jyun-Yu Jiang, Xue Sun, Wei Wang, Sean Young

DaMoC: Efficiently Selecting the Optimal Large Language Model for Fine-tuning Domain Tasks Based on Data and Model Compression (2025.findings-emnlp)

Challenge:	predicting air quality is a major concern for human health, but the changes of air quality conditions are still difficult to monitor.
Approach:	They propose to exploit social media and natural language processing techniques to enhance air quality prediction.
Outcome:	The proposed approach improves air quality prediction over baseline that does not use social media by 6.9% to 17.7% in macro-F1 scores.

Copied to clipboard

Wei Huang, Huang Wei, Yinggui Wang

AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation (2024.acl-long)

Challenge:	Large language models excel in general tasks but struggle with domain-specific ones, requiring fine-tuning with specific data.
Approach:	They propose a Data and Model Compression Framework that categorizes data filtering methodologies into three distinct paradigms: (1) distribution-aware methods, (2) quality-a aware methods, and (3) hybrid approaches considering both dimensions.
Outcome:	The proposed framework can select the optimal LLM while saving approximately 20-fold in training time.

Copied to clipboard

Zhaowei Wang, Wei Fan, Qing Zong, Hongming Zhang, Sehyun Choi, Tianqing Fang, Xin Liu, Yangqiu Song, Ginny Wong, Simon See

Online Distilling from Checkpoints for Neural Machine Translation (N19-1)

Challenge:	Existing work shows that LLMs are deficient in abstract ability, and how to improve it remains unexplored.
Approach:	They propose a framework AbsInstruct to enhance LLMs’ abstract ability through instruction tuning.
Outcome:	The proposed framework can enhance LLMs’ abstraction ability with strong generalization performance while maintaining their general instruction-following abilities.

Copied to clipboard

Hao-Ran Wei, Shujian Huang, Ran Wang, Xin-yu Dai, Jiajun Chen

RankCSE: Unsupervised Sentence Representations Learning via Learning to Rank (2023.acl-long)

Challenge:	Existing neural machine translation models have a deep structure with large amounts of parameters, making them hard to train.
Approach:	They propose an online method to generate a teacher model from checkpoints . they show steady improvement over a strong self-attention-based baseline system .
Outcome:	The proposed method improves on-the-fly on several datasets and language pairs.

Copied to clipboard

Jiduan Liu, Jiahao Liu, Qifan Wang, Jingang Wang, Wei Wu, Yunsen Xian, Dongyan Zhao, Kai Chen, Rui Yan

Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering (2022.coling-1)

Challenge:	Unsupervised sentence representation learning is one of the fundamental problems in natural language processing . contrastive learning methods fail to capture fine-grained ranking information among the sentences .
Approach:	They propose a novel approach for unsupervised sentence representation learning that integrates ranking consistency and ranking distillation with contrastive learning into a unified framework.
Outcome:	The proposed approach performs better over state-of-the-art models on STS and TR tasks.

Copied to clipboard

Siyuan Wang, Zhongyu Wei, Zhihao Fan, Qi Zhang, Xuanjing Huang

CoTrust: Privacy-Preserving Collaboration Between Large and Small Language Models in Trusted Execution Environments (2026.findings-acl)

Challenge:	Existing methods for multi-hop reasoning ignore grounding on supporting facts of each step, which tends to generate inaccurate decompositions.
Approach:	They propose an interpretable stepwise reasoning framework that incorporates supporting sentences and questions at each intermediate step and utilizes the inference of the current hop for the next until reasoning out the final result.
Outcome:	The proposed model can boost performance and yield a better interpretable reasoning process without decomposition supervision.

Copied to clipboard

Zhenya Ma, Tingyi Wang, Yongheng Deng, Ziqing Qiao, Yinggui Wang, Tao Wei, Lei Wang, Ju Ren

FrontCoder: Scaling Visual Fidelity in Front-End Code Generation (2026.findings-acl)

Challenge:	Large language models (LLMs) provide powerful text generation capabilities, but accessing sensitive user inputs raises privacy concerns.
Approach:	They propose a privacy-preserving collaborative inference framework that combines large language models with small language models inside TEE to preserve privacy.
Outcome:	Experiments show that CoTrust outperforms unconstrained LLMs on multiple question answering and summarization benchmarks while maintaining strong privacy protection.

Copied to clipboard

Jun Feng, Jian Yang, Wei Zhang, Jing Wang, Keyi Chen, Xiaokun Yang, Weicheng Gu, Yihang Lou, Yan Bai, Xianglong Liu

LEAF: Large Language Diffusion Model for Time Series Forecasting (2025.findings-emnlp)

Challenge:	Existing work on front-end code generation fails to provide visual fidelity and rendering quality for front- end developers.
Approach:	They propose a three-stage pipeline to enhance front-end code generation capabilities in LLMs . they use synthetic data, quality-controlled supervised fine-tuning, and reinforcement learning .
Outcome:	The proposed model achieves competitive performance with frontier models while maintaining generation efficiency.

Copied to clipboard

Yuhang Pei, Tao Ren, Yifan Wang, Zhipeng Sun, Wei Ju, Chong Chen, Xian-Sheng Hua, Xiao Luo

CDA: A Contrastive Data Augmentation Method for Alzheimer’s Disease Detection (2023.findings-acl)

Challenge:	Recent work has applied large language models (LLMs) into time series forecasting, but they lack an understanding of holistic temporal patterns with potential error accumulation.
Approach:	They propose a framework that marries Larg e Langu age Diffusion Model with time series forecasting (LEAF) they propose converting time series into tokens and adopting language diffusion models to capture temporal dependencies.
Outcome:	The proposed framework generates future predictions with a diffusion model from a holistic view.

Copied to clipboard

Junwen Duan, Fangyuan Wei, Jin Liu, Hongdong Li, Tianming Liu, Jianxin Wang

Long-context Language Models Fail in Basic Retrieval Tasks Without Sufficient Reasoning Steps (2025.findings-emnlp)

Challenge:	Existing methods for detecting AD are challenging and time-consuming due to lack of data and generalizability of the models.
Approach:	They propose a contrastive data augmentation method which simulates the cognitive impairment of a patient by randomly deleting a proportion of text from the transcript to create negative samples.
Outcome:	The proposed method achieves the best performance among language-based models on the benchmark ADReSS Challenge dataset.

Copied to clipboard

Yijiong Yu, Zhixiao Qi, Yongfeng Huang, Wei Wang, null Weifeng.liu, Ran Chen, Ji Pei

AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator (2025.coling-main)

Challenge:	despite their extensive context window, long-context language models fail in some basic cases . a recent study shows that long-cot methods are not necessary for long-constituency tasks .
Approach:	a new study evaluates long-context language models with a large context window . the authors propose a method that can be well addressed with arbitrary reasoning steps .
Outcome:	The proposed methods are well addressed with a sufficient number of reasoning steps, guided by specific CoT prompts.

Copied to clipboard

Zhihao Fan, Lai Wei, Jialong Tang, Wei Chen, Wang Siyuan, Zhongyu Wei, Fei Huang

MAGNET: Towards Adaptive GUI Agents with Memory-Driven Knowledge Evolution (2026.acl-long)

Challenge:	Recent large language models (LLMs) have demonstrated superior performance in static medical question answering benchmarks, rivaling even human experts.
Approach:	They propose a multi-agent framework emulating dynamic medical interactions between Doctor as player and NPCs including Patient and Examiner to assess the performance of LLM-driven Doctor agents in simulated clinical scenarios.
Outcome:	The proposed framework emulates dynamic medical interactions between Doctor as player and NPCs including Patient and Examiner.

Copied to clipboard

Libo Sun, Jiwen Zhang, Siyuan Wang, Zhongyu Wei

Challenge:	Mobile GUI agents powered by large foundation models can perform tasks autonomously, but frequent updates that alter UI appearance and reorganize workflows cause agents trained on historical data to fail.
Approach:	They propose a memory-driven adaptive agent framework with stationary memory that links visual features to stable functional semantics and procedural memory that captures stable task intents across varying workflows.
Outcome:	The proposed framework improves performance over memory-augmented baselines and offline benchmarks on AndroidWorld.

MGR: Multi-generator Based Rationalization (2023.acl-long)

Copied to clipboard

Wei Liu, Haozhao Wang, Jun Wang, Ruixuan Li, Xinyang Li, YuanKai Zhang, Yang Qiu

Challenge:	Existing approaches to explain NLP models have two key challenges: spurious correlation and degeneration.
Approach:	They propose a rationalization framework using a generator and a predictor to construct a self-explaining NLP model with spurious correlation and degeneration as key challenges.
Outcome:	The proposed method improves the F1 score by 20.9% compared to state-of-the-art methods.

LegalAgentBench: Evaluating LLM Agents in Legal Domain (2025.acl-long)

Copied to clipboard

Haitao Li, Junjie Chen, Jingli Yang, Qingyao Ai, Wei Jia, Youfeng Liu, Kai Lin, Yueyue Wu, Guozhi Yuan, Yiran Hu, Wuyue Wang, Yiqun Liu, Minlie Huang

Challenge:	Existing general-domain benchmarks do not capture complexity of real-world judicial cognition and decision-making.
Approach:	They propose a benchmark specifically designed to evaluate LLM Agents in the legal domain.
Outcome:	The proposed benchmark includes 17 corpora from real-world legal scenarios and provides 37 tools for interacting with external knowledge.

LegalDrill: Diagnosis-Driven Synthesis for Legal Reasoning in Small Language Models (2026.acl-industry)

Copied to clipboard

Tianchun Li, Haochen Liu, Vishwa Pardeshi, Xingchen Wang, Tianci Liu, Huijun Zhao, Wei Fan, Jing Gao

Enabling Agents to Communicate Entirely in Latent Space (2026.acl-long)

Challenge:	Small language models (SLMs) are promising for real-world deployment but struggle with high-stakes legal reasoning tasks.
Approach:	They propose a diagnostic-driven synthesis framework that extracts and refines reasoning trajectories from a capable teacher via fine-grained prompting and a self-reflective verification is employed to adaptively select the most effective data for the SLM student.
Outcome:	The proposed framework extracts and refines reasoning trajectories from a capable teacher via fine-grained prompting, then a self-reflective verification is employed to adaptively select the most effective data for the student.

Copied to clipboard

Zhuoyun Du, Runze Wang, Huiyu Bai, Zouying Cao, Xiaoyong Zhu, Yu Cheng, Bo Zheng, Wei Chen, Haochao Ying

Challenge:	Natural language is the de facto communication medium for LLM-based agents, but it presents a fundamental constraint . natural language downsampling limits the depth and nuance of information that can be transmitted . et al.: inter-agent latent space communication is a promising paradigm for solving complex tasks .
Approach:	They propose a paradigm that leverages the last hidden states of an LLM as a representation of its thought for direct communication.
Outcome:	The proposed paradigm outperforms fine-tuned chain-of-thought prompting and single-agent baselines even across heterogeneous models.

Listen, Pause, and Reason: Toward Perception-Grounded Hybrid Reasoning for Audio Understanding (2026.findings-acl)

Copied to clipboard

Jieyi Wang, Yazhe Niu, Dexuan Xu, Zhongyu Wei

Decoupling Memories, Muting Neurons: Towards Practical Machine Unlearning for Large Language Models (2025.findings-acl)

Challenge:	Recent Large Audio Language Models (LALMs) have shown strong capabilities in audio understanding, yet their reasoning remains vulnerable to perceptual errors.
Approach:	They propose a large-scale dataset for Perception-Aware Question Answering that uses a hierarchical decoupling strategy to separate speech from environmental sounds and distinguishes among multiple speakers.
Outcome:	The proposed model improves on MMAU-mini, MMAR, and PAQA while maintaining comparable performance on multiple benchmarks.

Copied to clipboard

Lishuai Hou, Zixiong Wang, Gaoyang Liu, Chen Wang, Wei Liu, Kai Peng

Unlocking the Power of Large Language Models for Entity Alignment (2024.acl-long)

Challenge:	Existing methods for MU degrade model utility, especially when accessing the original training data.
Approach:	They propose a method that eliminates the influence of unlearned data by modulating the outputs of merely 1% of the neurons in the feed-forward network modules within the Transformer blocks.
Outcome:	The proposed method eliminates the influence of unlearned data from Large Language Models by modulating the outputs of 1% of the neurons in the feed-forward network modules within the Transformer blocks, minimizing disruption to the model’s performance.

Copied to clipboard

Xuhui Jiang, Yinghan Shen, Zhichao Shi, Chengjin Xu, Wei Li, Zixuan Li, Jian Guo, Huawei Shen, Yuanzhuo Wang

MoQAE: Mixed-Precision Quantization for Long-Context LLM Inference via Mixture of Quantization-Aware Experts (2025.acl-long)

Challenge:	Entity Alignment (EA) is a crucial step in unifying data from heterogeneous sources and plays a critical role in data-driven AI applications.
Approach:	They propose a framework that incorporates large language models to improve EA.
Outcome:	The proposed framework incorporates large language models (LLMs) to improve EA accuracy while preserving efficiency.

Copied to clipboard

Wei Tao, Haocheng Lu, Xiaoyang Qu, Bin Zhang, Kai Lu, Jiguang Wan, Jianzong Wang

SWE-Dev: Building Software Engineering Agents with Training and Inference Scaling (2025.findings-acl)

Challenge:	Existing approaches to optimize large language models for long-context inference are inefficient and consume memory.
Approach:	They propose a mixed-precision quantization method via mixture of experts that inputs tokens into router chunk by chunk to reduce inference overhead.
Outcome:	The proposed method outperforms state-of-the-art KV cache quantization methods on multiple benchmark datasets.

Copied to clipboard

Haoran Wang, Zhenyu Hou, Yao Wei, Jie Tang, Yuxiao Dong

Challenge:	Large language models (LLMs) have advanced rapidly from conversational problem solving to addressing real-world tasks involving tool use, such as software engineering (SWE).
Approach:	They propose to build an LLM-based software engineering agent that synthesizes test cases and scales up agent trajectories to build training data.
Outcome:	The proposed model outperforms state-of-the-art models on the SWE-bench-Verified benchmark.

Aligning Cross-lingual Sentence Representations with Dual Momentum Contrast (2021.emnlp-main)

Copied to clipboard

Liang Wang, Wei Zhao, Jingming Liu

Joint Pre-Encoding Representation and Structure Embedding for Efficient and Low-Resource Knowledge Graph Completion (2024.emnlp-main)

Challenge:	Existing work uses sentences within the same batch as negatives, which suffers from easy negatives.
Approach:	They propose to align sentence representations from different languages into a unified embedding space . they adapt MoCo to further improve the quality of alignment .
Outcome:	The proposed model achieves state-of-the-art on several tasks.

Copied to clipboard

Chenyu Qiu, Pengjiang Qian, Chuang Wang, Jian Yao, Li Liu, Fang Wei, Eddie Eddie

AwarenessBench: Assessing Cognitive Capabilities of Language Models (2026.acl-long)

Challenge:	Existing knowledge graph completion models require longer training and inference times as well as increased memory usage.
Approach:	They propose to encode textual descriptions into semantic representations before training and integrate structural embedding with pre-encoded semantic description to improve model's prediction performance on 1-N relations.
Outcome:	The proposed model increases inference speed by 30x and reduces training memory by approximately 60% on the WN18RR and UMLS datasets.

Copied to clipboard

Xiaojian Li, Rongwu Xu, Tianyun Zhang, Yue Wang, Shuo Chen, Qiner Lyu, Briana Zhang, Peiran Yang, Kyle Xue Chen, Haoyuan Shi, Yu Wang, Wei Xu

SPO: Self Preference Optimization with Self Regularization (2025.findings-emnlp)

Challenge:	Language models exhibit increasingly consciousness-like behaviors, requiring a baseline to evaluate their cognitive abilities.
Approach:	They propose a benchmark to assess the cognitive abilities of language models (LMs) they compare 18 state-of-the-art LMs to human models in metacognition, self-awareness, social awareness and situational awareness .
Outcome:	Evaluating 18 state-of-the-art LMs, they find they consistently surpass baselines . but most models fall short in metacognition and self-awareness, the study finds .

Copied to clipboard

Yuhao Sun, Yifan Zhang, Quandong Wang, Qinzhuo Wu, Wei Liu, Jian Luan

RiskLab: A Controlled Toolkit for Probing Emergent Risks in LLM-Based Multi-Agent Systems (2026.acl-demo)

Challenge:	Existing reference-free preference optimization methods exhibit higher training efficiency but are prone to overoptimization, leading to performance degradation.
Approach:	They propose a reference-free preference optimization method that replaces the logsigmoid loss function with a SiLU function to improve the model's performance.
Outcome:	The proposed method achieves 7% improvement over SimPO on AlpacaEval 2 and MT-Bench.

Copied to clipboard

Yu Jiang, Wenjie Wang, Yue Huang, Yanbo Wang, Zhenhong Zhou, Xiuying Chen, Yang Liu, Pin-Yu Chen, Wei Wang, Xiangliang Zhang

Text Style Transfer Back-Translation (2023.acl-long)

Challenge:	Recent advances in large language model (LLM) agents have accelerated deployment of multi-agent systems for complex tasks.
Approach:	They propose an open-source toolkit for instantiating, probing, and measuring emergent risks in LLM-based multi-agent systems under controlled conditions.
Outcome:	The proposed toolkit is based on a structured topology–environment–protocol–agent–task quintuple enabling reproducible studies of how communication structure, coordination mechanisms, and incentives shape system-level risks.

Copied to clipboard

Daimeng Wei, Zhanglin Wu, Hengchao Shang, Zongyao Li, Minghan Wang, Jiaxin Guo, Xiaoyu Chen, Zhengzhe Yu, Hao Yang

M3TQA: Massively Multilingual Multitask Table Question Answering (2026.findings-acl)

Challenge:	Current methods require large amount of bilingual training data, which is challenging and sometimes impossible task.
Approach:	They propose a method to modify the style of inputs by modifying the source side of BT data.
Outcome:	The proposed method significantly improves translation quality against popular BT benchmarks on high-resource and low-resourced language pairs.

Copied to clipboard

Daixin Shu, Jian Yang, Zhenhe Wu, Xianjie Wu, Xianfu Cheng, Guan Xiangyuan, Yanghai Wang, Pengfei Wu, Tingyang Yang, Hualei Zhu, Wei Zhang, Ge Zhang, Jiaheng Liu, Zhoujun Li

Learned Adapters Are Better Than Manually Designed Adapters (2023.findings-acl)

Challenge:	Existing multilingual table benchmarks suffer from geolinguistic imbalance - overrepresenting certain languages and lacking sufficient scale for rigorous cross-lingual analysis.
Approach:	They propose a framework for massively multilingual table question answering that includes tables expanded to 97 languages from Chinese and English sources.
Outcome:	Experiments on state-of-the-art LLMs show that synthetically generated training data significantly boosts performance, especially for low-resource languages.

Copied to clipboard

Yuming Zhang, Peng Wang, Ming Tan, Wei Zhu

UniKeyphrase: A Unified Extraction and Generation Framework for Keyphrase Prediction (2021.findings-acl)

Challenge:	Existing approaches to improve adapter-based tuning are sub-optimal . a learning framework is proposed to learn the optimal adapter architectures .
Approach:	They propose a framework to automatically learn optimal adapter architectures for better task adaptation of pre-trained models.
Outcome:	The proposed framework outperforms the previous parameter-efficient tuning baselines while tuning comparable or fewer parameters.

Copied to clipboard

Huanqin Wu, Wei Liu, Lei Li, Dan Nie, Tao Chen, Feng Zhang, Di Wang

Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering (2025.acl-long)

Challenge:	Mainstream methods that ignore the diversity among keyphrases or weakly capture the relation between tasks implicitly ignore keyphrase diversity.
Approach:	They propose a novel end-to-end learning framework that jointly learns to extract and generate keyphrases by exploiting latent semantic relation between extraction and generation.
Outcome:	The proposed approach outperforms mainstream methods on a benchmarked document on keyphrase prediction.

Copied to clipboard

Rongzhi Zhu, Xiangyu Liu, Zequn Sun, Yiwei Wang, Wei Hu

To Code or not to Code? Adaptive Tool Integration for Math Language Models via Expectation-Maximization (2025.findings-acl)

Challenge:	Empirical results show that ChainRAG consistently outperforms baselines in both effectiveness and efficiency.
Approach:	They propose a method which sequentially handles each sub-question by completing missing key entities and retrieving relevant sentences from a sentence graph for answer generation.
Outcome:	The proposed method outperforms baselines on three multi-hop QA datasets.

Copied to clipboard

Haozhe Wang, Long Li, Chao Qu, Weidi Xu, Fengming Zhu, Wei Chu, Fangzhen Lin

GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs (2026.findings-acl)

Challenge:	Existing tools that integrate chain-of-thought reasoning and code execution lack metacognitive awareness to integrate tools.
Approach:	They propose a framework that synergizes structured exploration with off-policy RL optimization to create a cycle between metacognitive tool-use decisions and evolving capabilities.
Outcome:	The proposed framework improves over 11% on MATH500 and 9.4% on AIME without o1-like CoT.

Copied to clipboard

Meixiu Long, Duolin Sun, Dan Yang, Yihan Jiao, Lei Liu, Jiahai Wang, Binbin Hu, Yue Shen, Jie Feng, Zhehao Tan, Junjie Wang, Lianzhen Zhong, Jian Wang, Peng Wei, Jinjie Gu

Crafting Personalized Agents through Retrieval-Augmented Generation on Editable Memory Graphs (2024.emnlp-main)

Challenge:	Existing rankers excel in lexical-matching scenarios, while they struggle with complex queries requiring deep reasoning.
Approach:	They propose a new paradigm that balances flexibility and context awareness to unlock the full potential of groupwise reranking.
Outcome:	The proposed approach achieves a state-of-the-art 65.2 NDCG@10 on BRIGHT and surpasses baselines by 2.1 points on R2MED while delivering a 6.4 inference speedup.

Copied to clipboard

Zheng Wang, Zhongyang Li, Zeren Jiang, Dandan Tu, Wei Shi

Mixture of LoRA Experts for Continual Information Extraction with LLMs (2025.findings-emnlp)

Challenge:	In the age of mobile internet, personal information is constantly being generated on smartphones.
Approach:	They propose a novel task of crafting personalized agents powered by large language models that leverage a user's smartphone memories to enhance downstream applications with LLM capabilities.
Outcome:	The proposed approach improves 10% over the best existing approach on a real-world dataset and improves usability.

Copied to clipboard

Zitao Wang, Xinyi Wang, Wei Hu

MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral Discussions (2023.acl-long)

Challenge:	Existing methods to continual information extraction are either task-specialized for a single task or suffer from catastrophic forgetting and insufficient knowledge transfer in continual IE.
Approach:	They propose a continual IE model that uses token-level mixture of LoRA experts with LLMs to extract emerging information across diverse IE tasks incessantly while avoiding forgetting.
Outcome:	The proposed model achieves state-of-the-art performance, effectively mitigating catastrophic forgetting and enhancing knowledge transfer in continual IE.

Copied to clipboard

Hao Sun, Zhexin Zhang, Fei Mi, Yasheng Wang, Wei Liu, Jianwei Cui, Bin Wang, Qun Liu, Minlie Huang

Combining Spans into Entities: A Neural Two-Stage Approach for Recognizing Discontiguous Entities (D19-1)

Challenge:	A moral dialogue system aligned with users’ values could enhance conversation engagement and user connections.
Approach:	They propose a framework to train and evaluate moral dialogue systems based on communication mechanisms of morality and a method to construct moral discussions between simulated users and the dialogue system.
Outcome:	The proposed framework can train and evaluate moral dialogue systems based on simulated users and their values .

Copied to clipboard

Bailin Wang, Wei Lu

Challenge:	Named entity recognition (NER) aims at identifying shallow semantic elements in text.
Approach:	They propose a neural two-stage approach to recognizing discontiguous and overlapping entities by decomposing the problem into two subtasks.
Outcome:	The proposed model achieves state-of-the-art in a standard dataset even without external features.

Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoning (2026.acl-long)

Copied to clipboard

Renliang Sun, Wei Cheng, Dawei Li, Haifeng Chen, Wei Wang

Experiential Co-Learning of Software-Developing Agents (2024.acl-long)

Challenge:	Chain-of-Thought reasoning has driven recent gains of large language models (LLMs) on reasoning-intensive tasks by externalizing intermediate steps.
Approach:	They propose a training-free framework that adaptively determines when to stop reasoning to mitigate overthinking.
Outcome:	The proposed framework reduces token usage by 20-55% while maintaining or improving accuracy compared to standard CoT prompting.

Copied to clipboard

Chen Qian, Yufan Dang, Jiahao Li, Wei Liu, Zihao Xie, YiFei Wang, Weize Chen, Cheng Yang, Xin Cong, Xiaoyin Che, Zhiyuan Liu, Maosong Sun

Learning Cooperative Interactions for Multi-Overlap Aspect Sentiment Triplet Extraction (2022.findings-emnlp)

Challenge:	Recent advances in large language models (LLMs) have brought significant changes to various domains, especially through autonomous agents.
Approach:	They propose a framework that lets agents learn shortcuts from their past tasks and use them for future task execution.
Outcome:	The proposed framework enables agents to tackle unseen software-developing tasks more effectively.

Copied to clipboard

Shiman Zhao, Wei Chen, Tengjiao Wang

Me-Agent: A Personalized Mobile Agent with Two-Level User Habit Learning for Enhanced Interaction (2026.findings-acl)

Challenge:	Existing methods for aspect sentiment triplet extraction focus on the single interactions between an aspect and an opinion.
Approach:	They propose a multi-overlap triplet extraction method which decodes the complex relations between multiple aspects and opinions by learning their cooperative interactions.
Outcome:	The proposed method outperforms baselines, especially multi-overlap triplets.

Copied to clipboard

Shuoxin Wang, Chang Liu, Gowen Loo, Lifan Zheng, Kaiwen Wei, Huanqian Yan, Xinyi Zeng, Jingyuan Zhang, Yu Tian

ALYMPICS: LLM Agents Meet Game Theory (2025.coling-main)

Challenge:	Existing Large Language Model (LLM)-based mobile agents follow explicit user instructions without personalized needs.
Approach:	They propose a user preference learning strategy enhanced with a Personal Reward Model to improve personalization performance.
Outcome:	The proposed agent achieves state-of-the-art performance while maintaining competitive instruction execution performance.

Copied to clipboard

Shaoguang Mao, Yuzhe Cai, Yan Xia, Wenshan Wu, Xun Wang, Fengyi Wang, Qiang Guan, Tao Ge, Furu Wei

Linguistics & Cognitive NLP

Challenge:	Alympics provides a framework for simulating human-like strategic interactions with Large Language Model (LLM) agents.
Approach:	They propose a framework utilizing Large Language Models (LLM) agents for empirical game theory research.
Outcome:	The proposed framework can be used to study human-like strategic interactions with large language model (LLM) agents in a game on the multi-round auction of scarce survival resources.

Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets (N18-1)

Copied to clipboard

Zhen Yang, Wei Chen, Feng Wang, Bo Xu

An Enhanced Knowledge Injection Model for Commonsense Generation (2020.coling-main)

Challenge:	Experimental results show that the proposed model consistently outperforms the traditional RNNSearch and the newly emerged state-of-the-art Transformer on English-German and Chinese-English translation tasks.
Approach:	They propose an approach for applying GANs to NMT by building a conditional sequence generative adversarial net with two adversarials.
Outcome:	The proposed model outperforms the existing RNNSearch and Transformer on English-German and Chinese-English translation tasks.

Copied to clipboard

Zhihao Fan, Yeyun Gong, Zhongyu Wei, Siyuan Wang, Yameng Huang, Jian Jiao, Xuanjing Huang, Nan Duan, Ruofei Zhang

SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Models (2022.acl-long)

Challenge:	a recent study shows that digging the relationship of concepts from scratch is non-trivial for commonsense generation tasks.
Approach:	They use a retrieve-and-edit framework to retrieve a prototype with these concepts . they use qt and qq to generate commonsense questions at scale .
Outcome:	The proposed method significantly improves the performance on commonsense generation tasks.

Copied to clipboard

Liang Wang, Wei Zhao, Zhuoyu Wei, Jingming Liu

Fin-STAR: Structure-as-Semantics to Resolve Implicitness in Financial Retrieval (2026.findings-acl)

Challenge:	Text-based methods lag behind graph embedding-based approaches for knowledge graph completion (KGC)
Approach:	They propose three types of negatives to improve contrastive learning to improve learning efficiency.
Outcome:	The proposed model outperforms embedding-based methods on several benchmark datasets.

Copied to clipboard

Yu Zou, Yan Chen, Lida He, Qi Zhou, Xiaorui Zhou, Aixi Zhong, Yi Wang, Wei Li, Qingyu Wang, Jiatao Li, Wei Gong, Jialei Zeng, Jingmei Zhao, Ke Jiang, Qing Li

KG-Adapter: Enabling Knowledge Graph Integration in Large Language Models through Parameter-Efficient Fine-Tuning (2024.findings-acl)

Challenge:	Existing Retrieval-Augmented Generation systems treat structure as a physical navigational skeleton rather than intrinsic semantic knowledge.
Approach:	They propose a framework that redefining hierarchy as intrinsic semantics and uses snippets to enrich hierarchical lineage.
Outcome:	The proposed framework outperforms state-of-the-art hierarchical and graph-based benchmarks on FinTierQA Gold.

Copied to clipboard

Shiyu Tian, Yangyang Luo, Tianze Xu, Caixia Yuan, Huixing Jiang, Chen Wei, Xiaojie Wang

Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification (P18-1)

Challenge:	Large language models (LLMs) are criticized for lack of expertise and knowledge conflict . KG-Adapter is a parameter-level KG integration method for decoder-only LLMs .
Approach:	They propose a parameter-level KG integration method based on parameter-efficient fine-tuning . they use KG-Adapter to integrate knowledge graphs with LLMs and perform joint reasoning .
Outcome:	The proposed method outperforms the current state-of-the-art method on four datasets for two different tasks.

Copied to clipboard

Yizhong Wang, Kai Liu, Jing Liu, Wei He, Yajuan Lyu, Hua Wu, Sujian Li, Haifeng Wang

RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation (2024.emnlp-demo)

Challenge:	Recent years have seen rapid growth in the MRC community . MRC is believed to be a crucial step in building a general intelligent agent .
Approach:	They propose an end-to-end neural model that enables multiple passages to verify each other based on their content representations.
Outcome:	The proposed model outperforms the baseline on the English MS-MARCO dataset and the Chinese DuReader dataset, and achieves state-of-the-art performance on both datasets.

Copied to clipboard

Xuanwang Zhang, Yun-Ze Song, Yidong Wang, Shuyun Tang, Xinfeng Li, Zhengran Zeng, Zhen Wu, Wei Ye, Wenyuan Xu, Yue Zhang, Xinyu Dai, Shikun Zhang, Qingsong Wen

KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment (2023.acl-long)

Challenge:	Existing research on Retrieval Augmented Generation (RAG) does not address the problem of hallucinations and real-time updating of knowledge.
Approach:	They propose a modular open-source library to equip LLMs with external knowledge.
Outcome:	The proposed approach reduces the need for expensive open-source tools and lacks fair comparisons between novel RAG algorithms.

Copied to clipboard

Lingzhi Wang, Tong Chen, Wei Yuan, Xingshan Zeng, Kam-Fai Wong, Hongzhi Yin

Challenge:	Recent legislation of the "right to be forgotten" has led to the interest in machine unlearning . MU can be used to forget specific training instances as if they have never existed .
Approach:	They propose a general unlearning framework called KGA to induce forgetfulness . they propose several unlearning evaluation metrics with pertinence .
Outcome:	The proposed framework improves on large-scale datasets and provides insight into unlearning for NLP tasks.

Can GRPO Boost Complex Multimodal Table Understanding? (2025.emnlp-main)

Copied to clipboard

Xiaoqiang Kang, Shengen Wu, Zimu Wang, Yilin Liu, Xiaobo Jin, Kaizhu Huang, Wei Wang, Yutao Yue, Xiaowei Huang, Qiufeng Wang

Enhancing In-Context Learning via Implicit Demonstration Augmentation (2024.acl-long)

Challenge:	Existing table understanding methods struggle with low initialization accuracy and coarse rewards in tabular contexts.
Approach:	They propose a three-stage RL framework that enhances multimodal table understanding through: (1) Warm-up that prompts initial perception and reasoning capabilities; (2) Perception Alignment GRPO (PA-GRPO); (3) Hint-Completion GR PO (HC-GRP);
Outcome:	The proposed framework outperforms existing models on held-in and held-out datasets, outperforming SFT and GRPO largely.

Copied to clipboard

Xiaoling Zhou, Wei Ye, Yidong Wang, Chaoya Jiang, Zhemg Lee, Rui Xie, Shikun Zhang

Effidit: An Assistant for Improving Writing Efficiency (2023.acl-demo)

Challenge:	In-context learning (ICL) is a new paradigm for pre-trained language models that can make predictions for unseen inputs without updating parameters.
Approach:	They propose a method that enables a model to augmented copies of a demonstration by leveraging their deep feature distribution and a logit calibration mechanism.
Outcome:	The proposed method significantly improves the average and worst-case accuracy across diverse PLMs and tasks.

Copied to clipboard

Shuming Shi, Enbo Zhao, Wei Bi, Deng Cai, Leyang Cui, Xinting Huang, Haiyun Jiang, Duyu Tang, Kaiqiang Song, Longyue Wang, Chenyan Huang, Guoping Huang, Yan Wang, Piji Li

AlphaContext: An Evolutionary Tree-based Psychometric Context Generator for Creativity Assessment (2026.acl-long)

Challenge:	Effidit is a digital writing assistant that provides three modules to help users write faster and more efficiently.
Approach:	They present Effidit, a digital writing assistant that provides three modules to help users write higher-quality text more efficiently.
Outcome:	Effidit expands the capabilities of a typical writing assistant by providing three modules . Effit can help users create their own text faster and more efficiently .

Copied to clipboard

Yixuan Wang, Yue Huang, Hong Qian, Yunzhao Wei, Yifei Ding, Wenkai Wang, Zhi Liu, Zhongjing Huang, Aimin Zhou, Jiajun Guo

Challenge:	Existing LLM-based tools struggle with insufficient assessment cues, weak narrative coherence, limited stylistic diversity, and poor support for creative thinking.
Approach:	They propose an evolutionary tree-based psychometric context generator that integrates rule-guided outline planning, sentence-level MCTS generation, MAP-Elites quality-diversity optimization and assessment-guide refiner simulation.
Outcome:	The proposed tool outperforms strong LLMs and structured frameworks on 7 evaluation dimensions and shows higher alignment with expert-designed contexts.

Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention (2025.acl-long)

Copied to clipboard

Jingyang Yuan, Huazuo Gao, Damai Dai, Junyu Luo, Liang Zhao, Zhengyan Zhang, Zhenda Xie, Yuxing Wei, Lean Wang, Zhiping Xiao, Yuqing Wang, Chong Ruan, Ming Zhang, Wenfeng Liang, Wangding Zeng

Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data (2024.findings-acl)

Challenge:	Long-context modeling is crucial for next-generation language models, but high computational cost of standard attention mechanisms poses significant computational challenges.
Approach:	They propose a natively trained Sparse Attention mechanism that integrates algorithms with hardware-aligned optimizations to achieve efficient long-context modeling.
Outcome:	The proposed model maintains or exceeds Full Attention models across general benchmarks, long-context tasks, and instruction-based reasoning.

Copied to clipboard

Yanda Li, Chi Zhang, Gang Yu, Wanqi Yang, Zhibin Wang, Bin Fu, Guosheng Lin, Chunhua Shen, Ling Chen, Yunchao Wei

League of LLMs: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models (2026.acl-long)

Challenge:	OpenAI's GPT-4 has demonstrated remarkable multimodal capabilities, but specific mechanics of GPT4 remain unknown.
Approach:	They propose a data collection methodology that synchronously synthesizes images and dialogues for visual instruction tuning.
Outcome:	The proposed method improves on ten commonly assessed models and provides greater flexibility compared to existing methods.

Copied to clipboard

Qianhong Guo, Wei Xie, Xiaofang Cai, Enze Wang, Shuoyoucheng Ma, Xiaobing Sun, Tian Xia, Kai Chen, Xiaofeng Wang, Baosheng Wang

Activating Distributed Visual Region within LLMs for Efficient and Effective Vision-Language Training and Inference (2025.acl-long)

Challenge:	Large language models (LLMs) have shown exceptional capabilities across a wide range of tasks, but reliable evaluation remains a challenge due to data contamination, opaque operation, and subjective preferences.
Approach:	They propose a benchmark-free evaluation paradigm that organizes multiple LLMs into a self-governed league for multi-round mutual evaluation.
Outcome:	Experiments on eight mainstream LLMs in mathematics and programming show that the proposed model can distinguish capabilities while maintaining high internal ranking stability.

Copied to clipboard

Siyuan Wang, Dianyi Wang, Chengxing Zhou, Zejun Li, Zhihao Fan, Xuanjing Huang, Zhongyu Wei

Retrieval as Generation: A Unified Framework with Self-Triggered Information Planning (2026.acl-long)

Challenge:	Existing Large Vision-Language Models (LVLMs) learn visual capacity through visual instruction tuning.
Approach:	They propose a method for LVLMs to be trained by selective layers tuning . they propose removing non-critical layers outside the visual region .
Outcome:	The proposed approach preserves nearly 99% of visual performance and improves textual task results while reducing training time.

Copied to clipboard

Bo Li, Mingda Wang, Gexiang Fang, Shikun Zhang, Wei Ye

Plug-and-Play Data Module for Code RL: Adaptive Ambiguity Replay (2026.findings-acl)

Challenge:	Existing models that ground retrieval on external evidence are limited in their ability to implement retrieval-augmented generation.
Approach:	They propose a retrieval-augmented generation model that embeds retrieval control directly into generation.
Outcome:	The proposed model surpasses strong RAG baselines and uses substantially fewer parameters.

Copied to clipboard

Jianqing Zhang, Wei Xia, Zhezheng Hao, Hong Wang, Hande Dong, Qiang Lin, Yang Liu, Jian Cao, Qiang Yang

LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models (2025.acl-long)

Challenge:	Existing approaches to reinforcement learning (RL) rely on static, in-epoch metrics that overlook training dynamics, often introducing low-utility or outdated data.
Approach:	They propose a plug-and-play module that prioritizes cross-epoch ambiguous samples to neutralize the noise from stale experiences.
Outcome:	Extensive experiments on nine LLMs show that Adaptive Ambiguity Replay outperforms state-of-the-art baselines on real-world code editing tasks.

Copied to clipboard

Zhiyuan Hu, Yuliang Liu, Jinman Zhao, Suyuchen Wang, WangYan WangYan, Wei Shen, Qing Gu, Anh Tuan Luu, See-Kiong Ng, Zhiwei Jiang, Bryan Hooi

Re-examining the Role of Schema Linking in Text-to-SQL (2020.emnlp-main)

Challenge:	Large language models face significant challenges in handling long-context tasks because of their limited effective context window size during pretraining, which restricts their ability to generalize over extended sequences.
Approach:	They propose a training strategy for extending the context window of LLMs including impactful token analysis, position index transformation, and training optimization strategies.
Outcome:	Experiments on three types of LLMs show that LongRecipe can utilize long sequences while requiring only 30% of the target context window size.

Copied to clipboard

Wenqiang Lei, Weixin Wang, Zhixin Ma, Tian Gan, Wei Lu, Min-Yen Kan, Tat-Seng Chua

When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection (2026.acl-long)

Challenge:	Existing text-to-SQL models treat schema linking as a minor component . Existing solutions treat schema as merely a string component based on string matching .
Approach:	They build a schema linking corpus based on a Spider text-to-SQL dataset . they find schema linking is the crux for the current text- to-Sql task .
Outcome:	The proposed model performs well on the Spider text-to-SQL dataset despite its simplicity.

Copied to clipboard

Lang Gao, Xuhui Li, Chenxi Wang, Mingzhe Li, Wei Liu, Zirui Song, Jinghui Zhang, Rui Yan, Preslav Nakov, Xiuying Chen

FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models (2024.acl-long)

Challenge:	Personalized MGT detection remains largely underexplored due to personalization challenges . large language models (LLMs) can imitate personal writing styles, but they can generate fake news and misinformation.
Approach:	They propose a benchmark to evaluate detector robustness under personalization . they attribute this limitation to a feature-inversion trap that flips the effect in personalized contexts .
Outcome:	The proposed framework predicts detector robustness under personalization with an 85% correlation to actual results.

Copied to clipboard

Yuxin Jiang, Yufei Wang, Xingshan Zeng, Wanjun Zhong, Liangyou Li, Fei Mi, Lifeng Shang, Xin Jiang, Qun Liu, Wei Wang

A Survey on Detection of LLMs-Generated Content (2024.findings-emnlp)

Challenge:	Existing benchmarks focus on evaluating pure response quality, rather than assessing whether the response follows constraints stated in the instruction.
Approach:	They propose a Multi-level Fine-grained Constraints Following Benchmark for Large Language Models that adds a single constraint to the initial instruction at each increased level.
Outcome:	The proposed model can follow instructions with more constraints, and is deemed to have better instruction-following ability.

Copied to clipboard

Xianjun Yang, Liangming Pan, Xuandong Zhao, Haifeng Chen, Linda Petzold, William Yang Wang, Wei Cheng

Challenge:	Recent advances in large language models have led to an increase in synthetic content generation . the ability to detect LLMs-generated content has become of paramount importance .
Approach:	They propose to provide a detailed overview of existing detection strategies and benchmarks, scrutinizing their differences and advocating for more adaptable and robust models to enhance detection accuracy.
Outcome:	The proposed model will be able to detect human-written content in real time.

Think and Recall: Layer-Level Prompting for Lifelong Model Editing (2025.emnlp-main)

Copied to clipboard

Jinke Wang, Zenan Ying, Qi Liu, Wei Chen, Tong Xu, Huijun Hou, Zhi Zheng

Little Giants: Synthesizing High-Quality Embedding Data at Scale (2025.naacl-long)

Challenge:	Existing methods for lifelong model editing suffer from limitations in usability, such as requiring additional training corpora or lacking support for reversible and detachable edits.
Approach:	They propose a plug-and-play method for knowledge retrieval and storage, i.e., Layer-Level Prompting, which enables seamless and efficient lifelong model editing.
Outcome:	The proposed method outperforms existing methods on question answering and hallucination benchmarks across different LLMs.

Copied to clipboard

Haonan Chen, Liang Wang, Nan Yang, Yutao Zhu, Ziliang Zhao, Furu Wei, Zhicheng Dou

Protein Large Language Models: A Comprehensive Survey (2025.findings-emnlp)

Challenge:	Synthetic data generation is an increasingly popular way of training models without the need for large, manually labeled datasets.
Approach:	They propose a framework that aligns open-source small models to efficiently generate large-scale embedding data.
Outcome:	The proposed framework outperforms state-of-the-art embedding models by using only 1/10 of the GPT API calls.

Copied to clipboard

Yijia Xiao, Wanjia Zhao, Junkai Zhang, Yiqiao Jin, Han Zhang, Zhicheng Ren, Renliang Sun, Haixin Wang, Guancheng Wan, Pan Lu, Xiao Luo, Yu Zhang, James Zou, Yizhou Sun, Wei Wang

Knowledge Conflicts for LLMs: A Survey (2024.emnlp-main)

Challenge:	Existing studies focus on specific aspects or applications, but this study provides a comprehensive overview of Protein-specific large language models.
Approach:	This paper proposes a structured taxonomy of state-of-the-art ProteinLLMs . they analyze how they leverage large-scale protein sequence data for improved accuracy .
Outcome:	The proposed model covers their architectures, training datasets, evaluation metrics, and diverse applications.

Copied to clipboard

Rongwu Xu, Zehan Qi, Zhijiang Guo, Cunxiang Wang, Hongru Wang, Yue Zhang, Wei Xu

Keep it Consistent: Topic-Aware Storytelling from an Image Stream via Iterative Multi-agent Communication (2020.coling-main)

Challenge:	This survey examines knowledge conflicts for large language models (LLMs) this survey aims to shed light on strategies for improving the robustness of LLMs .
Approach:	They focus on three categories of knowledge conflicts: context-memory, inter-context, and intra-membry conflict.
Outcome:	The findings highlight the challenges faced by large language models when blending contextual and parametric knowledge.

Copied to clipboard

Ruize Wang, Zhongyu Wei, Ying Cheng, Piji Li, Haijun Shan, Ji Zhang, Qi Zhang, Xuanjing Huang

LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement (2025.acl-long)

Challenge:	Existing methods for visual storytelling construct text description independently for each image and roughly concatenate them as a story, which leads to the problem of generating semantically incoherent content.
Approach:	They propose a topic description task to detect the global semantic context of an image stream and a story is then constructed with the guidance of the topic description.
Outcome:	The proposed framework can generate stories with higher quality compared to state-of-the-art methods on a VIST dataset.

Copied to clipboard

Boyi Kang, Xinfa Zhu, Zihan Zhang, Zhen Ye, Mingshuai Liu, Ziqian Wang, Yike Zhu, Guobin Ma, Jun Chen, Longshuai Xiao, Chao Weng, Wei Xue, Lei Xie

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding (2025.findings-acl)

Challenge:	Recent advances in language models have demonstrated strong capabilities in semantic understanding and contextual modeling.
Approach:	They propose a LLaMA-based language model that incentivizes generalization capabilities for speech enhancement.
Outcome:	The proposed language model outperforms prior task-specific discriminative and generative models in acoustic enhancement tasks.

Copied to clipboard

Feifan Song, Shaohang Wei, Wen Luo, Yuxuan Fan, Tianyu Liu, Guoyin Wang, Houfeng Wang

VisFinEval: A Scenario-Driven Chinese Multimodal Benchmark for Holistic Financial Understanding (2025.emnlp-main)

Challenge:	Low-resource methods for LLM alignment have been popular, but still face challenges in obtaining high-quality and aligned content.
Approach:	They propose a framework to enhance alignment ability of base models by the guidance of a small aligned model.
Outcome:	The proposed framework outperforms baseline methods while avoiding degradation on downstream tasks.

Copied to clipboard

Zhaowei Liu, Xin Guo, Haotian Xia, Lingfeng Zeng, Fangqi Lou, Jinyi Niu, Mengping Li, Qi Qi, Jiahuan Li, Wei Zhang, Yinglong Wang, Weige Cai, Weining Shen, Liwen Zhang

Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation (2024.acl-long)

Challenge:	Existing benchmarks focus on text comprehension, but MLLMs lack the ability to integrate visual data over financial visuals.
Approach:	They evaluate 21 state-of-the-art multimodal large language models in a zero-shot setting . they use an annotated question–answer pair from eight common financial image modalities .
Outcome:	The new benchmark outperforms existing models but trailed financial experts by 14 percentage points.

Copied to clipboard

Tianqi Zhong, Zhaoyi Li, Quan Wang, Linqi Song, Ying Wei, Defu Lian, Zhendong Mao

SaCa: A Highly Compatible Reinforcing Framework for Knowledge Graph Embedding via Structural Pattern Contrast (2025.findings-emnlp)

Challenge:	Existing MCTG methods face a noticeable performance drop in compositional testing.
Approach:	They propose a benchmark to evaluate compositional generalization of MCTG methods by combining multi-aspect labeled datasets and a crafted three-dimensional evaluation protocol.
Outcome:	The proposed framework improves compositional generalization performance by 3.64% and 94.4% in compositional testing.

Copied to clipboard

Jiashi Lin, Changhong Jiang, Yixiao Wang, Xinyi Zhu, Zhongtian Hu, Wei Zhang

Improving Text Embeddings with Large Language Models (2024.acl-long)

Challenge:	Existing knowledge Graph Embedding approaches lack structural semantics of knowledge graphs . structure-aware calibration (SaCa) is a framework designed to calibrate KGEs based on global structural patterns.
Approach:	a new framework is designed to calibrate knowledge graphs using global structural patterns.
Outcome:	a new framework can calibrate KGE models using global structural patterns . the framework consistently boosts performance across ten models on link prediction and entity classification tasks .

Copied to clipboard

Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei

CloneMem: Benchmarking Long-Term Memory for AI Clones (2026.acl-long)

Challenge:	Existing methods for obtaining text embeddings require complex training pipelines . authors leverage proprietary LLMs to generate diverse synthetic data for text embeds based on 93 languages .
Approach:	They propose a method for obtaining high-quality text embeddings using only synthetic data and less than 1k training steps.
Outcome:	The proposed method achieves strong performance on competitive text embedding benchmarks without using any labeled data.

Copied to clipboard

Sen Hu, Zhiyu Zhang, Yuxiang Wei, Xueran Han, Zhenheng Tang, Ronghao Chen, Huacan Wang

Targeted Exploration via Unified Entropy Control for Reinforcement Learning (2026.findings-acl)

Challenge:	Existing memory benchmarks rely on user–agent conversational histories, which are temporally fragmented and insufficient for capturing continuous life trajectories.
Approach:	They propose a benchmark for evaluating long-term memory in AI Clone scenarios grounded in non-conversational digital traces, including diaries, social media posts, and emails, spanning one to three years.
Outcome:	Experiments show that existing memory benchmarks struggle in this setting, highlighting open challenges for life-grounded personalized AI.

Copied to clipboard

Chen Wang, Lai Wei, Yanzhi Zhang, Chenyang Shao, Zedong Dan, Weiran Huang, Ge Lan, Yue Wang

DVAGen: Dynamic Vocabulary Augmented Generation (2025.emnlp-demos)

Challenge:	Existing methods for group relative policy optimization suffer from entropy collapse . Existing exploration methods introduce additional bias or variance during exploration, making it difficult to maintain stability.
Approach:	They propose a framework that provides targeted mechanisms for exploration and stabilization.
Outcome:	The proposed framework expands search space on difficult prompts while preventing entropy growth uncontrollably.

Copied to clipboard

Wei Du, Nuowei Liu, Jie Wang, Jiahao Kuang, Tao Ji, Xiaoling Wang, Yuanbin Wu

Modeling LLM Unlearning as an Asymmetric Two-Task Learning Problem (2026.acl-long)

Challenge:	Existing dynamic vocabulary approaches struggle to generalize to novel or out-of-vocabulary words, limiting their flexibility in handling diverse token combinations.
Approach:	They propose an open-source framework for training, evaluation, and visualization of dynamic vocabulary-augmented language models.
Outcome:	The proposed framework validates the effectiveness of dynamic vocabulary-augmented language models on modern LLMs and shows support for batch inference significantly improving inference throughput.

Copied to clipboard

Zeguan Xiao, Siqing Li, Yong Wang, Xuetao Wei, Jian Yang, Yun Chen, Guanhua Chen

Recommend for a Reason: Unlocking the Power of Unsupervised Aspect-Sentiment Co-Extraction (2021.findings-emnlp)

Challenge:	Large language models (LLMs) are inherently dual-use and can be leveraged for both beneficial and harmful purposes.
Approach:	They propose a retention-prioritized gradient synthesis framework that decouples task-specific gradient extraction from conflict-aware combination.
Outcome:	The proposed method achieves tighter alignment on WMDP Bio and RWKU benchmarks.

Copied to clipboard

Zeyu Li, Wei Cheng, Reema Kshetramade, John Houser, Haifeng Chen, Wei Wang

A Fully Probabilistic Perspective on Large Language Model Unlearning: Evaluation and Optimization (2025.emnlp-main)

Challenge:	Existing review-based recommenders favor large and complex language encoders that can only learn latent and uninterpretable text representations.
Approach:	They propose a tightly coupled two-stage approach to extract latent user sentiments and item properties from reviews and an Attention-Property-aware Rating Estimator (APRE).
Outcome:	Extensive experiments on seven real-world Amazon review datasets show that the proposed approach extracts the latent user sentiments, item properties, and the complicated interactions between the two components.

Copied to clipboard

Anda Cheng, Wei Huang, Yinggui Wang

ReasMark: A Robust Watermark for Attributing LLM Reasoning Under Knowledge Distillation Attacks (2026.acl-long)

Challenge:	Large Language Model Unlearning (LLMU) is a promising way to remove private or sensitive information from large language models.
Approach:	They propose a Fully Probabilistic Evaluation framework that incorporates input and output distributions in LLMU evaluation.
Outcome:	The proposed framework improves unlearning effectiveness by 50.1% and robustness by 37.2% on Llama-2-7B.

Copied to clipboard

Peizhuo Lv, Ruihua Zhou, Yunpeng Li, Ruigang Liang, Xingshuo Han, XiaoFeng Wang, Wei Dong, Yuling Liu

A + B: A General Generator-Reader Framework for Optimizing LLMs to Unleash Synergy Potential (2024.findings-acl)

Challenge:	Existing reasoning-enhanced large language models fail to provide reliable attribution of reasoning behavior once it is transferred through knowledge distillation.
Approach:	They propose to embed a reasoning-length gap in a model by querying a target domain and training a local student to imitate its outputs.
Outcome:	et al. show that ReasMark outperforms baselines while preserving task utility.

Copied to clipboard

Wei Tang, Yixin Cao, Jiahao Ying, Bo Wang, Yuyue Zhao, Yong Liao, Peng Zhou

Decoding Susceptibility: Modeling Misbelief to Misinformation Through a Computational Approach (2024.emnlp-main)

Challenge:	Retrieval-Augmented Generation (RAG) is an effective solution to supplement necessary knowledge to large language models.
Approach:	They propose a "generate-then-read" pipeline to replace retrieval stage with generation from the LLM itself.
Outcome:	The proposed framework outperforms single models in the base and chat versions and addresses safety and helpfulness post-adaptation challenges.

Copied to clipboard

Yanchen Liu, Mingyu Ma, Wenna Qin, Azure Zhou, Jiaao Chen, Weiyan Shi, Wei Wang, Diyi Yang

Can Large Language Models Identify Implicit Suicidal Ideation? An Empirical Evaluation (2025.findings-emnlp)

Challenge:	Existing studies on susceptibility to misinformation rely on self-reported beliefs, which can be subject to bias, expensive to collect, and challenging to scale for downstream applications.
Approach:	They propose a computational approach to efficiently model users’ latent susceptibility levels by using demographic factors and political ideology as inputs.
Outcome:	The proposed model shows that political leanings and other psychological factors exhibit varying degrees of association with susceptibility to COVID-19 misinformation.

Copied to clipboard

Tong Li, Shu Yang, Junchao Wu, Jiyao Wei, Lijie Hu, Mengdi Li, Derek F. Wong, Joshua R. Oltmanns, Di Wang

PersonaAgent: Bridging Memory and Action for Personalized LLM Agents (2026.findings-acl)

Challenge:	Existing data on suicidal ideation in private conversations are limited . a new dataset of 1,200 test cases is presented to address this gap .
Approach:	They propose a dataset of 1,200 test cases simulating implicit suicidal ideation in private contexts.
Outcome:	The proposed dataset includes 1,200 test cases simulating implicit suicidal ideation in dialogue scenarios.

Copied to clipboard

Weizhi Zhang, Xinyang Zhang, Chenwei Zhang, Liangwei Yang, Jingbo Shang, Zhepei Wei, Henry Peng Zou, Zijie Huang, Zhengyang Wang, Yifan Gao, Xiaoman Pan, Lian Xiong, Jingguo Liu, Philip S. Yu, Xian Li

Lightweight LLM Agent Memory with Small Language Models (2026.acl-long)

Challenge:	Existing Large Language Model (LLM) enabled agents lack flexibility to respond to users’ varying needs and preferences.
Approach:	They propose a test-time user-preference alignment strategy that optimizes the persona prompt, ensuring real-time preference alignment through textual loss feedback between simulated and ground-truth responses.
Outcome:	The proposed framework outperforms baseline methods in real-time and in real applications.

Copied to clipboard

Jiaquan Zhang, Chaoning Zhang, Shuxu Chen, Zhenzhen Huang, Pengcheng Zheng, Zhicheng Wang, Ping Guo, Fan Mo, Sung-Ho Bae, Jie Zou, Jiwei Wei, Yang Yang

MAGE: Machine-generated Text Detection in the Wild (2024.acl-long)

Challenge:	Existing external memory systems for LLMs have low online overhead but are unstable in accumulating latency over long interactions.
Approach:	They propose a lightweight memory system for better agent memory driven by Small Language Models . lightmem modularizes memory retrieval, writing, and long-term consolidation . they show consistent gains across model scales and high efficiency .
Outcome:	The proposed system improves agent memory but has low latency and low online overhead . it separates online processing from offline consolidation to enable efficient memory invocation . the proposed system achieves an average F1 improvement of 2.5 over A-MEM on LoCoMo .

Copied to clipboard

Yafu Li, Qintong Li, Leyang Cui, Wei Bi, Zhilin Wang, Longyue Wang, Linyi Yang, Shuming Shi, Yue Zhang

Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets (2026.findings-acl)

Challenge:	Existing research has focused on evaluating detection methods for specific domains or language models.
Approach:	They build a testbed to detect texts from diverse human writings and LLMs using different detection methods.
Outcome:	Empirical results show that the top performing detector can identify 84.12% out-of-domain texts generated by a new LLM, indicating the feasibility for application scenarios.

Copied to clipboard

Yuan Xiao, Jiaming Wang, Yuchen Chen, Wei Song, Jun Sun, Shiqing Ma, Yanzhou Mu, Juan Zhai, Chunrong Fang, Jin Song Dong, Zhenyu Chen

Extracting Trigger-sharing Events via an Event Matrix (2022.findings-emnlp)

Challenge:	Existing methods for dataset poisoning require full-dataset poison, which breaks code compilability.
Approach:	They propose a functionality-preserving poisoning approach that injects short, compilable weak-use fragments into executed code paths.
Outcome:	The proposed method contaminates 10% of the dataset while maintaining 100% compilability and functional correctness.

Copied to clipboard

Jun Xu, Weidi Xu, Mengshu Sun, Taifeng Wang, Wei Chu

IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response Theory (2025.acl-long)

Challenge:	Existing methods to extract multiple events with triggers and arguments are invalid as there may be multiple events.
Approach:	They propose a framework for event extraction which models the relations between arguments by an event matrix.
Outcome:	The proposed framework beats all the advanced competitors on 3 widely-used datasets.

Copied to clipboard

Wei Song, Zhenya Huang, Cheng Cheng, Weibo Gao, Bihan Xu, GuanHao Zhao, Fei Wang, Runze Wu

Linguistic Theories

Challenge:	Large language models have demonstrated exceptional performance across a wide range of tasks . however, selecting the optimal LLM to respond to a user query often necessitates a delicate balance between performance and cost.
Approach:	They propose a multi-LLM routing framework that efficiently routes user queries to the most suitable LLM.
Outcome:	The proposed framework outperforms baseline methods in terms of effectiveness and interpretability.

ToolPlanner: A Tool Augmented LLM for Multi Granularity Instructions with Path Planning and Feedback (2024.emnlp-main)

Copied to clipboard

Qinzhuo Wu, Wei Liu, Jian Luan, Bin Wang

Challenge:	Recent studies have shown that tool-augmented large language models can interact with external tools in multiple rounds and provide a final answer.
Approach:	They propose a tool-augmented large language model that can interact with external tools in multiple rounds and provide a final answer to an instruction.
Outcome:	The proposed framework significantly improves Match Rate, Pass Rate and Win Rate by 26.8%, 20.2%, and 5.6% compared to the SOTA model.

PairRE: Knowledge Graph Embeddings via Paired Relation Vectors (2021.acl-long)

Copied to clipboard

Linlin Chao, Jianshan He, Taifeng Wang, Wei Chu

Joint Optimization of Training Data and Policy in RLHF (2026.findings-acl)

Challenge:	Existing knowledge graph embedding methods fail to solve two major problems at the same time, leading to unsatisfactory results.
Approach:	They propose a model with paired vectors for each relation representation that can be adaptively adjusted to fit for different complex relations.
Outcome:	Experiments on two knowledge graph datasets show the proposed model can handle complex relations and encode relation patterns.

Copied to clipboard

Zhuohao Yu, Jiali Zeng, Weizheng Gu, Mengyuan Sun, Yidong Wang, Fandong Meng, Jie Zhou, Shikun Zhang, Wei Ye

Challenge:	JODP optimizes policies on fixed training inputs, limiting the diversity of learning signals.
Approach:	They propose a framework where policy generates improved variants of training problems to enhance its own learning.
Outcome:	The proposed framework improves on safety alignment tasks by allowing 4B models to reach 8B model performance with less than 1% additional computational overhead.

SOAR: Supervision from Observation for Agentic Reinforcement Learning (2026.acl-long)

Copied to clipboard

Meng Li, Lei Li, Xiting Wang, Yi Yuan, Zheng Wei, null Brucebian, Zang Li

Learning to Disentangle Interleaved Conversational Threads with a Siamese Hierarchical Network and Similarity Ranking (N18-1)

Challenge:	Prior work assigns supervision based on outcome rewards or external reward models, but ignores environment observations, a critical source of learning.
Approach:	They propose a supervision-based agentic reinforcement learning system that integrates environment observations as an explicit supervision signal.
Outcome:	The proposed model improves performance on reasoning and deep research tasks while reducing erroneous and inefficient tool usage.

Copied to clipboard

Jyun-Yu Jiang, Francine Chen, Yan-Ying Chen, Wei Wang

BiSyn-GAT+: Bi-Syntax Aware Graph Attention Network for Aspect-based Sentiment Analysis (2022.findings-acl)

Challenge:	Existing methods to disentangle interleaved conversations can lead to difficulties in following discussions and retrieving relevant information from simultaneous messages.
Approach:	They propose to leverage representation learning to separate intermingled messages into detached conversations by estimating conversation-level similarity between closely posted messages.
Outcome:	The proposed approach outperforms baselines in pairwise similarity estimation and conversation disentanglement.

Copied to clipboard

Shuo Liang, Wei Wei, Xian-Ling Mao, Fei Wang, Zhiyong He

UNIMO-2: End-to-End Unified Vision-Language Grounded Learning (2022.findings-acl)

Challenge:	Aspect-based sentiment analysis is challenging because a sentence may contain multiple aspects or complicated relationships.
Approach:	They propose a bi-syntax aware Graph Attention Network to model the context of every aspect and sentiment relations across aspects for learning.
Outcome:	The proposed model outperforms the state-of-the-art methods on four benchmark datasets.

Copied to clipboard

Wei Li, Can Gao, Guocheng Niu, Xinyan Xiao, Hao Liu, Jiachen Liu, Hua Wu, Haifeng Wang

From 128K to 4M: Efficient Training of Ultra-Long Context Large Language Models (2026.findings-acl)

Challenge:	Existing methods for vision-language pre-training can only learn from aligned image-caption data and rely heavily on expensive regional features.
Approach:	They propose an end-to-end unified-modal pre-training framework for joint learning . they propose to conduct grounded learning on both images and texts via a sharing grounded space .
Outcome:	The proposed model improves visual and visual semantic alignment on images and texts.

Copied to clipboard

Chejian Xu, Wei Ping, Peng Xu, Zihan Liu, Boxin Wang, Mohammad Shoeybi, Bo Li, Bryan Catanzaro

Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models (2024.acl-long)

Challenge:	Long-context capabilities are essential for document and video understanding, in-contact learning, and inference-time scaling.
Approach:	They propose an efficient training recipe for building ultra-long context LLMs from aligned instruct model, pushing the boundaries of context lengths from 128K to 1M, 2M, and 4M tokens.
Outcome:	The proposed model extends the context window while maintaining short context capabilities while maintaining the performance of the existing model.

Copied to clipboard

Tianyi Tang, Wenyang Luo, Haoyang Huang, Dongdong Zhang, Xiaolei Wang, Xin Zhao, Furu Wei, Ji-Rong Wen

DenseSSM: State Space Models with Dense Hidden Connection for Efficient Large Language Models (2025.naacl-long)

Challenge:	Despite the impressive multilingual capabilities demonstrated by LLMs, the understanding of how these abilities develop and function remains nascent.
Approach:	They propose a novel detection method to pinpoint language-specific neurons within LLMs by selectively activating or deactivating these neurons.
Outcome:	The proposed method can “steer” the output language of LLMs by selectively activating or deactivating language-specific neurons.

Copied to clipboard

Wei He, Kai Han, Yehui Tang, Chengcheng Wang, Yujie Yang, Tianyu Guo, Yunhe Wang

ROMA: Real-time Omni-Multimodal Assistant with Interactive Streaming Understanding (2026.findings-acl)

Challenge:	Large language models (LLMs) face excessive computational and memory requirements due to the commonly used Transformer architecture.
Approach:	They propose a method to enhance the flow of hidden information between layers in large language models by selectively integrating shallow-layer hidden states into deeper layers.
Outcome:	The proposed method maintains parallelizability and inference efficiency of SSMs while significantly boosting performance on public benchmarks.

Copied to clipboard

Tian Xueyun, Wei Li, Bingbing Xu, Heng Dong, Yuanzhuo Wang, Huawei Shen

MedFact: A Large-scale Chinese Dataset for Evidence-based Medical Fact-checking of LLM Responses (2025.emnlp-main)

Challenge:	Existing omni-multimodal large language models lack incomplete modality support or lack autonomous proactive monitoring.
Approach:	They propose a real-time omni-multimodal assistant for unified reactive and proactive interaction that decouples response initiation from generation to ensure precise triggering without task conflict.
Outcome:	The proposed model achieves state-of-the-art performance on proactive tasks while competing in reactive settings.

Copied to clipboard

Tong Chen, Zimu Wang, Yiyi Miao, Haoran Luo, Sun Yuanfei, Wei Wang, Zhengyong Jiang, Procheta Sen, Jionglong Su

Knowledge-Infused Prompting: Assessing and Advancing Clinical Text Data Generation with Large Language Models (2024.findings-acl)

Challenge:	Existing medical fact-checking datasets focus on human-generated content, leaving the verification of content generated by large language models (LLMs) relatively unexplored.
Approach:	They propose to use Chinese medical fact-checking datasets to verify LLM-generated medical content by combining in-context learning and fine-tuning.
Outcome:	The first evidence-based Chinese medical fact-checking dataset of LLM-generated medical content consists of 1,321 questions and 7,409 claims .

Copied to clipboard

Ran Xu, Hejie Cui, Yue Yu, Xuan Kan, Wenqi Shi, Yuchen Zhuang, May Dongmei Wang, Wei Jin, Joyce Ho, Carl Yang

Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning (2026.acl-long)

Challenge:	Clinical natural language processing (NLP) is a subfield that requires the extraction, analysis, and interpretation of unstructured clinical text.
Approach:	They propose a model which infuses knowledge into clinical text generation with LLMs for clinical NLP tasks.
Outcome:	The proposed model improves performance across 8 clinical NLP tasks and 18 datasets by 7.7%-8.7% on average.

Copied to clipboard

Yifan Wang, Shiyu Li, Peiming Li, Xiaochen Yang, Zheng Wei, Yang Tang

HoPE: A Novel Positional Encoding Without Long-Term Decay for Enhanced Context Awareness and Extrapolation (2025.acl-long)

Challenge:	Recent work on Chain-of-Thought prompting imposes substantial computational overhead . lack of supervision obscures the analyzability of the latent reasoning chain.
Approach:	They propose a framework to render latent reasoning chain into images, making latent rationale explicit and traceable.
Outcome:	The proposed framework achieves 3-4 token compression and substantial inference acceleration compared to explicit CoT prompting.

Copied to clipboard

Yuhan Chen, Ang Lv, Jian Luan, Bin Wang, Wei Liu

Evaluating the Expressive Appropriateness of Speech in Rich Contexts (2026.acl-long)

Challenge:	Existing positional encodings exhibit long-term decay, based on an entrenched and long-standing opinion that tokens farther away from the current position carry less relevant information.
Approach:	They propose a high-frequency rotary position encoding (HoPE) that replaces specific components in RoPE with position-independent ones, retaining only high- frequency signals.
Outcome:	The proposed method exhibits greater robustness to the out-of-distribution behavior in attention patterns during extrapolation.

Copied to clipboard

Tianrui Wang, Ziyang Ma, Yizhou Peng, Haoyu Wang, Zhikang Niu, Zikang Huang, Yihao Wu, Yi-Wen Chao, Yu Jiang, Yuheng Lu, Guanrou Yang, Xuanchen Li, Hexin Liu, Chunyu Qiang, Cheng Gong, Yifan Yang, Tianchi Liu, Junyu Wang, Nana Hou, Meng Ge, Fuming You, Yang Wei, Zhongqian Sun, Hu Haifeng, Xiaobao Wang, Eng Siong Chng, Xie Chen, Longbiao Wang, Jianwu Dang

Speech & Audio in NLP

Challenge:	Existing methods for evaluating expressive speech focus on word accuracy, naturalness, signal quality, or emotional intensity at the utterance level.
Approach:	They propose a framework for Evaluating Expressive Appropriateness in speech that assesses whether a speech sample aligns with the underlying communicative intent implied by its discourse-level narrative context.
Outcome:	The proposed framework outperforms existing speech evaluation and analysis systems on a human-annotated test set.

Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study (2023.emnlp-main)

Copied to clipboard

Boxin Wang, Wei Ping, Peng Xu, Lawrence McAfee, Zihan Liu, Mohammad Shoeybi, Yi Dong, Oleksii Kuchaiev, Bo Li, Chaowei Xiao, Anima Anandkumar, Bryan Catanzaro

Inferring from Logits: Exploring Best Practices for Decoding-Free Generative Candidate Selection (2025.acl-long)

Challenge:	a recent study shows that retrieval-augmented LMs can improve text generation quality and accuracy.
Approach:	They propose a model that reproduces RETRO parameters while retrieving a text corpus . they find RETRO outperforms GPT on text generation with less repetition .
Outcome:	The proposed model outperforms standard retrieval-augmented GPT and retrieval augmented GTP on text generation and accuracy tasks.

Copied to clipboard

Mingyu Derek Ma, Yanna Ding, Zijie Huang, Jianxi Gao, Yizhou Sun, Wei Wang

Challenge:	Existing work has been using decoding-free candidate selection methods to obtain candidate probability from initial output logits over vocabulary.
Approach:	They propose to evaluate a set of tasks using decoding-free candidate selection methods on a comprehensive set of questions.
Outcome:	The proposed methods are evaluated on a set of tasks including five multiple-choice QA tasks with a small candidate pool and four clinical decision tasks with 10k+ options.

From Discrimination to Generation: Low-Resource Intent Detection with Language Model Instruction Tuning (2024.findings-acl)

Copied to clipboard

Feng Zhang, Wei Chen, Fei Ding, Meng Gao, Tengjiao Wang, Jiahui Yao, Jiabin Zheng

AutoDSL: Automated domain-specific language design for structural representation of procedures with constraints (2024.acl-long)

Challenge:	Existing studies fine-tune discriminative models on specific defined intent classes, preventing them from being directly adopted to new intent domains.
Approach:	They propose to use a pre-trained generative intent model to detect new intents from different domains with no parameter updates.
Outcome:	The proposed model outperforms baselines that need further fine-tuning or domain-specific samples.

Copied to clipboard

Yu-Zhe Shi, Haofei Hou, Zhangqian Bi, Fanxu Meng, Xiang Wei, Lecheng Ruan, Qining Wang

IAPT: Instance-Aware Prompt Tuning for Large Language Models (2024.acl-long)

Challenge:	Domain-specific Language (DSL) is an effective tool to express constraints structurally, but requires case-by-case hand-crafting.
Approach:	They propose a framework to automate domain-specific language constraint design . they propose 'autoDSL' framework to optimize syntactic and semantic constraints .
Outcome:	The framework automates constraint design across domains and abstracts semantic constraints.

Copied to clipboard

Wei Zhu, Aaron Tian, Congrui Yin, Yuan Ni, Xiaoling Wang, Guotong Xie

Benchmarking for Domain-Specific LLMs: A Case Study on Academia and Beyond (2025.findings-emnlp)

Challenge:	Existing methods for prompt tuning require many soft tokens to guarantee performance . large language models still require a large amount of GPU memory and computations to fine-tune .
Approach:	They propose to use a parameter-efficient soft prompt generator to generate idiosyncratic soft prompts for each input instruction.
Outcome:	The proposed method outperforms the baselines with comparable tunable parameters and is more efficient than LoRA under the single-backbone multi-tenant setting.

Copied to clipboard

Rubing Chen, Jiaxin Wu, Jian Wang, Xulu Zhang, Wenqi Fan, Chenghua Lin, Xiaoyong Wei, Li Qing

Boosting Event Extraction with Denoised Structure-to-Text Augmentation (2023.findings-acl)

Challenge:	Comp-Comp is an iterative benchmarking framework grounded in the principles of comprehensiveness and compactness.
Approach:	They propose a benchmark framework that incorporates the principle of comprehensiveness and compactness.
Outcome:	The proposed framework is domain-agnostic and adaptable to a wide range of specialized fields.

Copied to clipboard

Bo Wang, Heyan Huang, Xiaochi Wei, Ge Shi, Xiao Liu, Chong Feng, Tong Zhou, Shuaiqiang Wang, Dawei Yin

Bi-Directional Iterative Prompt-Tuning for Event Argument Extraction (2022.emnlp-main)

Challenge:	Existing methods for event extraction neglect grammatical incorrectness, structure misalignment, and semantic drifting . et al., 2004; Ahn, 2006) show that the proposed method generates more diverse text representations for event extracting compared with the state-of-the-art.
Approach:	They propose a framework for event extraction that generates additional training data and iteratively selects the effective subset from the generated training data.
Outcome:	The proposed method generates more diverse representations of training data and achieves comparable results with the state-of-the-art.

Copied to clipboard

Lu Dai, Bang Wang, Wei Xiang, Yijun Mo

SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval (2023.acl-long)

Challenge:	Existing prompt-tuning methods for event argument extraction lack entity information . eAE is a key step of event extraction, but it requires a pre-trained language model to extract event arguments.
Approach:	They propose a prompt-tuning method that takes advantage of entity information and pre-trained language models.
Outcome:	The proposed method outperforms the state-of-the-art prompt-tuning methods on an english dataset.

Copied to clipboard

Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei

Large-Scale and Multi-Perspective Opinion Summarization with Diverse Review Subsets (2023.findings-emnlp)

Challenge:	SimLM uses a simple bottleneck architecture that learns to compress the passage information into a dense vector through self-supervised pre-training.
Approach:	They propose a simple yet effective pre-training method for dense passage retrieval that learns to compress the passage information into a dense vector through self-supervised pre-tuning.
Outcome:	The proposed method outperforms multi-vector approaches on large-scale passage retrieval datasets and shows significant improvements over baselines.

Copied to clipboard

Han Jiang, Rui Wang, Zhihua Wei, Yu Li, Xinpeng Wang

Semi-Supervised Disfluency Detection (C18-1)

Challenge:	Existing methods for opinion summarization are deficient in epitomizing extensive reviews and offering opinion summaries from various angles.
Approach:	They propose a supervised opinion summarization framework that takes sentiment orientation into account and trains the summarizer to learn from sub-optimal and optimal review subsets.
Outcome:	The proposed framework generates pros, cons, and verdict summaries from hundreds of input reviews.

Copied to clipboard

Feng Wang, Wei Chen, Zhen Yang, Qianqian Dong, Shuang Xu, Bo Xu

Encoding Hierarchical Schema via Concept Flow for Multifaceted Ideology Detection (2024.findings-acl)

Challenge:	Detecting disfluency can be difficult because of the flexible nature of reparandum structure and the lack of a nested structure.
Approach:	They propose a semi-supervised approach which extracts hidden features from self-attention without any Recurrent Neural Network (RNN) or Convolutional Neural Net (CNN).
Outcome:	The proposed approach improves over baselines by using unlabelled data . identifying and removing non-fluent factors would help to improve spontaneous speech quality .

Copied to clipboard

Songtao Liu, Bang Wang, Wei Xiang, Han Xu, Minghua Xu

Challenge:	Existing studies on ideology detection focus on one generic facet and ignore label semantics and explanatory descriptions of ideologies.
Approach:	They propose a concept semantics-enhanced framework for multifaceted ideology detection . it enables concepts to flow across levels of the schema tree and enriches concept representations with multi-granularity semantics.
Outcome:	The proposed framework achieves state-of-the-art in the cross-topic scenario and on the benchmark dataset.

A Dataset and Baselines for Multilingual Reply Suggestion (2021.acl-long)

Copied to clipboard

Mozhi Zhang, Wei Wang, Budhaditya Deb, Guoqing Zheng, Milad Shokouhi, Ahmed Hassan Awadallah

SCALE: Synergized Collaboration of Asymmetric Language Translation Engines (2024.findings-acl)

Challenge:	Reply suggestion models help users process emails and chats faster.
Approach:	They present a multilingual reply suggestion dataset with ten languages . they build a generation model and a retrieval model as baselines for MRS .
Outcome:	The proposed model complements existing benchmarks for cross-lingual generalization . the model has different strengths in the English monolingual setting and requires different strategies to generalize across languages.

Copied to clipboard

Xin Cheng, Xun Wang, Tao Ge, Si-Qing Chen, Furu Wei, Dongyan Zhao, Rui Yan

Phased Instruction Fine-Tuning for Large Language Models (2024.findings-acl)

Challenge:	In this paper, we introduce SCALE, a collaborative framework that connects a compact Specialized Translation Model (STM) and a general-purpose Large Language Model (LLM) as one unified translation engine.
Approach:	They propose a collaborative framework that connects a Specialized Translation Model (STM) and a general-purpose Large Language Model (LLM) as one unified translation engine.
Outcome:	The proposed framework outperforms both LLMs and supervised models in high-resource or challenging low-resourced settings.

Copied to clipboard

Wei Pang, Chuan Zhou, Xiao-Hua Zhou, Xiaojie Wang

The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis (2026.acl-long)

Challenge:	Existing methods to enhance pre-trained language models' ability to follow instructions are limited due to the simultaneous handling of varying instruction complexities.
Approach:	They propose a phased instruction fine-tuning method that posits that the transition of a pre-trained language model from simple next-word prediction to sophisticated instruction following is a gradual learning process.
Outcome:	The proposed method surpasses the one-off instruction fine-tuning method in win rate and validates the hypothesis of progressive alignment.

Copied to clipboard

Zihao Wei, Liang Pang, Jiahao Liu, Wenjie Shi, Jingcheng Deng, Shicheng Xu, Zenghao Duan, Jingang Wang, Fei Sun, Huawei Shen, Xueqi Cheng

K-Level Reasoning: Establishing Higher Order Beliefs in Large Language Models for Strategic Reasoning (2025.naacl-long)

Challenge:	Explicit reasoning trajectories increase performance but often trigger overthinking . despite its importance, this study examines how each step of reasoning affects the final outcome .
Approach:	They propose a Reasoning Completion Point Detector that detects the RCP by monitoring rank dynamics of termination tokens.
Outcome:	The proposed method reduces token usage by up to 44% while preserving accuracy.

Copied to clipboard

Yadong Zhang, Shaoguang Mao, Tao Ge, Xun Wang, Yan Xia, Man Lan, Furu Wei

Monte Carlo Tree Search Based Prompt Autogeneration for Jailbreak Attacks against LLMs (2025.coling-main)

Challenge:	Strategic reasoning requires Large Language Model (LLM) agents to adapt their strategies dynamically in multi-agent environments.
Approach:	They propose a framework that enables Large Language Models to achieve varying levels of strategic depth by recursive mechanisms that allow agents to form higher order beliefs about others' beliefs.
Outcome:	The proposed framework enables LLMs to achieve varying levels of strategic depth, allowing agents to form higher order beliefs—beliefs about others’ beliefs.

Copied to clipboard

Suhuang Wu, Huimin Wang, Yutian Zhao, Xian Wu, Yefeng Zheng, Wei Li, Hui Li, Rongrong Ji

SCA: Selective Compression Attention for Efficiently Extending the Context Window of Large Language Models (2024.findings-emnlp)

Challenge:	Jailbreak attacks craft specific prompts or append adversarial suffixes to prompts, thereby inducing language models to generate harmful or unethical content and bypassing the model’s safety guardrails.
Approach:	They propose a Monte Carlo Tree Search (MCTS) based Prompt Auto-generation (MPA) method to generate adversarial suffixes for valid jailbreak attacks.
Outcome:	The proposed method outperforms existing methods on open-source and closed-source models and shows that it can generate harmful responses.

Copied to clipboard

Huanran Zheng, Wei Zhu, Xiaoling Wang

Doc-V*: Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA (2026.acl-long)

Challenge:	Existing methods to compress the KV cache of large language models are expensive and limited in their context window and cost.
Approach:	They propose a method to expand the context window and reduce memory footprint by compressing the KV cache of large language models.
Outcome:	The proposed method can reduce memory footprint and expand context window of large language models without training.

Copied to clipboard

Yuanlei Zheng, Pei Fu, Hang Li, Ziyang Wang, Yuyi Zhang, Wenyu Ruan, Xiaojin Zhang, Zhongyu Wei, Zhenbo Luo, Jian Luan, Wei Chen, Xiang Bai

Enhancing Multimodal Named Entity Recognition through Adaptive Mixup Image Augmentation (2025.coling-main)

Challenge:	Existing OCR-free approaches to document visual question answering are brittle and passive.
Approach:	They propose an OCR-free agentic framework that casts multi-page DocVQA as sequential evidence aggregation.
Outcome:	The proposed framework outperforms open-source and proprietary models in five benchmarks and improves out-of-domain performance by 47.9% over baseline.

Copied to clipboard

Bo Xu, Haiqi Jiang, Jie Wei, Hongyu Jing, Ming Du, Hui Song, Hongya Wang, Yanghua Xiao

TokenSmith: Streamlining Data Editing, Search, and Inspection for Large-Scale Language Model Training and Interpretability (2025.emnlp-demos)

Challenge:	Current named entity recognition methods struggle with text-image mismatch problem due to a lack of visual context.
Approach:	They propose an adaptive mixup image augmentation method that generates augmented images based on matching score between text and image .
Outcome:	The proposed method can be integrated into existing models and demonstrate consistent performance improvements.

Copied to clipboard

Mohammad Aflah Khan, Ameya Godbole, Johnny Wei, Ryan Yixiang Wang, James Flemings, Krishna P. Gummadi, Willie Neiswanger, Robin Jia

ChartMind: A Comprehensive Benchmark for Complex Real-world Multimodal Chart Question Answering (2025.emnlp-main)

Challenge:	Existing workflows for pretraining large language models are cumbersome, fragmented and inaccessible.
Approach:	They propose an open-source library for editing, inspection, and analysis of large language model datasets.
Outcome:	TokenSmith is an open-source library for editing, inspection, and analysis of large language model datasets.

Copied to clipboard

Jingxuan Wei, Nan Xu, Junnan Zhu, null Haoyanni, Gaowei Wu, Qi Chen, Bihui Yu, Lei Wang

OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models (2025.acl-long)

Challenge:	Chart question answering (CQA) is a multimodal task for evaluating the reasoning capabilities of vision-language models.
Approach:	They propose a chart question answering benchmark that incorporates multilingual contexts and supports open-domain textual outputs.
Outcome:	The proposed framework outperforms the previous three common CQA paradigms: instruction-following, OCR-enhanced, and chain-of-thought.

Copied to clipboard

Siming Huang, Tianhao Cheng, Jason Klein Liu, Weidi Xu, Jiaran Hao, Liuyihan Song, Yang Xu, Jian Yang, Jiaheng Liu, Chenchen Zhang, Linzheng Chai, Ruifeng Yuan, Xianzhen Luo, Qiufeng Wang, YuanTao Fan, Qingfu Zhu, Zhaoxiang Zhang, Yang Gao, Jie Fu, Qian Liu, Houyi Li, Ge Zhang, Yuan Qi, Xu Yinghui, Wei Chu, Zili Wang

MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning (2026.acl-long)

Challenge:	Code LLMs lack reproducible data pipelines and training protocols for reproducible advancements in code intelligence.
Approach:	They propose a top-tier code LLM that releases model weights and inference code . reproducible data pipelines, rigorous experimental ablation results and training protocols are included .
Outcome:	The proposed model achieves comparable performance to leading models and serves as an "open cookbook" reproducible training data, rigorous experimental ablation results, and detailed training protocols are also included in the model.

Copied to clipboard

Yizhe Zeng, Wei Zhang, Yunpeng Li, Juxin Xiao, Xiao Wang, Yuling Liu

Chinese MentalBERT: Domain-Adaptive Pre-training on Social Media for Chinese Mental Health Text Analysis (2024.findings-acl)

Challenge:	Existing CoT backdoor attacks manipulate intermediate reasoning steps to steer the model toward incorrect answers, but these corrupted reasoning traces are readily detected by prevalent process-monitoring defenses.
Approach:	They propose a backdoor attack that exploits the model's post-output space to preserve clean CoTs while selectively steering the final answer toward a specific target.
Outcome:	Experiments show that MirageBD achieves over 90% success rate across four datasets and five models with a poison ratio of only 5%.

Copied to clipboard

Wei Zhai, Hongzhi Qi, Qing Zhao, Jianqiang Li, Ziqi Wang, Han Wang, Bing Yang, Guanghui Fu

Zero-Shot Cross-Domain Aspect-Based Sentiment Analysis via Domain-Contextualized Chain-of-Thought Reasoning (2025.findings-emnlp)

Challenge:	Existing models for language analysis are inadequate for specialized domains like psychology.
Approach:	They have enriched a Chinese social media database with psychological lexicons to enhance its applicability to psychological text analysis.
Outcome:	The proposed model performed better on six public datasets and provided relevant predictions given the masked sentences.

Copied to clipboard

Chuming Shen, Wei Wei, Dong Wang, Zhong-Hao Wang

CorefQA: Coreference Resolution as Query-based Span Prediction (2020.acl-main)

Challenge:	Cross-domain aspect-based sentiment analysis (ABSA) aims to learn specific knowledge from a source domain to perform various tasks on a target domain.
Approach:	a new framework is proposed to learn specific knowledge from a source domain . the framework uses domain adaptation techniques to transfer domain-agnostic features .
Outcome:	a new learning framework for cross-domain aspect-based sentiment analysis is proposed . it effectively eliminates dependency on target-domain annotations, authors say .

Copied to clipboard

Wei Wu, Fei Wang, Arianna Yuan, Fei Wu, Jiwei Li

Revisiting Weak-to-Strong Generalization in Theory and Practice: Reverse KL vs. Forward KL (2025.findings-acl)

Challenge:	Existing coreference resolution models suffer from mention proposal.
Approach:	They propose a query-based span prediction task that can retrieve mentions left out at the mention proposal stage.
Outcome:	The proposed model can retrieve mentions left out at the mention proposal stage and improve generalization capability using existing question answering datasets.

Copied to clipboard

Wei Yao, Wenkai Yang, Ziqiao Wang, Yankai Lin, Yong Liu

Linguistics & Cognitive NLP

Challenge:	Weak-to-strong generalization is a promising approach to guide stronger systems, but its effectiveness is constrained by the inherent imperfections of weak model supervision.
Approach:	They propose a theoretically grounded approach that replaces forward KL divergence with reverse KL, which prioritizes high-confidence predictions.
Outcome:	The proposed approach replaces forward KL divergence with reverse KL, reducing the influence of unreliable weak supervision.

SWING: Balancing Coverage and Faithfulness for Dialogue Summarization (2023.findings-eacl)

Copied to clipboard

Kung-Hsiang Huang, Siffi Singh, Xiaofei Ma, Wei Xiao, Feng Nan, Nicholas Dingwall, William Yang Wang, Kathleen McKeown

Large Language Models Can Be Contextual Privacy Protection Learners (2024.emnlp-main)

Challenge:	Existing approaches to dialogue summarization rely on features of conversation data.
Approach:	They propose to use natural language inference models to improve coverage and faithfulness . they use fine-grained training signals to encourage model to generate missing content .
Outcome:	The proposed model achieves higher faithfulness and coverage while maintaining conciseness compared to prior methods.

Copied to clipboard

Yijia Xiao, Yiqiao Jin, Yushi Bai, Yue Wu, Xianjun Yang, Xiao Luo, Wenchao Yu, Xujiang Zhao, Yanchi Liu, Quanquan Gu, Haifeng Chen, Wei Wang, Wei Cheng

Adaptive Reinforcement Tuning Language Models as Hard Data Generators for Sentence Representation (2024.lrec-main)

Challenge:	Large Language Models (LLMs) have demonstrated remarkable linguistic comprehension and generation capability, but when applied to specialized industries, they face challenges such as hallucination, insufficient domain knowledge, and failing to incorporate the latest domain knowledge.
Approach:	They propose a paradigm for fine-tuning LLMs that effectively injects domain-specific knowledge while safeguarding inference-time data privacy.
Outcome:	The proposed model protects private data while enhancing the model's knowledge.

Copied to clipboard

Bo Xu, Yifei Wu, Shouang Wei, Ming Du, Hongya Wang

Bridging the Gap between Synthetic and Natural Questions via Sentence Decomposition for Semantic Parsing (2023.tacl-1)

Challenge:	Existing methods use contrastive learning (CL) to learn effective sentence representations, but require extensive human annotation.
Approach:	They propose a reinforcement learning approach for fine-tuning small-parameter LLMs to generate high-quality hard contrastive data without human feedback.
Outcome:	The proposed method achieves state-of-the-art on seven semantic text similarity tasks.

Copied to clipboard

Yilin Niu, Fei Huang, Wei Liu, Jianwei Cui, Bin Wang, Minlie Huang

Debiasing LLMs by Masking Unfairness-Driving Attention Heads (2026.findings-acl)

Challenge:	Existing methods to train a parser to perform zero-shot learning are limited by the lack of training data.
Approach:	They propose a decomposition-based method to unify the sentence structures of questions . their method can generalize to natural questions with novel text expressions .
Outcome:	The proposed method improves on synthetic data and on complex web questions with novel expressions.

Copied to clipboard

Tingxu Han, Wei Song, Ziqi Ding, Ziming Li, Chunrong Fang, Yuekang Li, Dongfang Liu, Zhenyu Chen, Zhenting Wang

StructuralLM: Structural Pre-training for Form Understanding (2021.acl-long)

Challenge:	Existing work probes when biased outputs appear, but gives little insight into the mechanisms that generate them, leaving existing mitigations largely fragile.
Approach:	They propose a lightweight debiasing framework that detects bias heads and selectively masks only those heads that activate under DA and CoT.
Outcome:	The proposed framework reduces unfairness by 391.9%- 534.5% in both one- and two-turn dialogues.

Copied to clipboard

Chenliang Li, Bin Bi, Ming Yan, Wei Wang, Songfang Huang, Fei Huang, Luo Si

CIRAG: Construction–Integration Retrieval and Adaptive Generation for Multi-hop Question Answering (2026.acl-long)

Challenge:	Existing pre-trained language models focus on text-only representation, neglecting cell-level layout information.
Approach:	They propose a pre-training approach to leverage cell and layout information from scanned documents.
Outcome:	The proposed model achieves state-of-the-art in various downstream tasks . it uses 2Dposition embeddings to model word-level layout information .

Copied to clipboard

Zili Wei, Yilin Wang, Xiaocui Yang, Shi Feng, Weidong Bao, Daling Wang, Zihan Wang, Yifei Zhang

QAEncoder: Towards Aligned Representation Learning in Question Answering Systems (2025.acl-long)

Challenge:	Existing methods for iterative retrieval-augmented generation (iRAG) suffer from greedy single-path expansion and granularity–demand mismatch .
Approach:	They propose a model that constructs candidate triples and history-conditionally integrates them to distill core triples to generate the next-hop query.
Outcome:	The proposed model mitigates the greedy single-path expansion and granularity–demand mismatch by preserving multiple plausible evidence chains.

Copied to clipboard

Zhengren Wang, Qinhan Yu, Shida Wei, Zhiyu Li, Feiyu Xiong, Xiaoxing Wang, Simin Niu, Hao Liang, Wentao Zhang

Serial Contrastive Knowledge Distillation for Continual Few-shot Relation Extraction (2023.findings-acl)

Challenge:	Modern QA systems entail retrieval-augmented generation (RAG) for accurate and trustworthy responses, but the inherent gap between user queries and relevant documents hinders precise matching.
Approach:	They propose a retrieval-augmented generation (RAG)-based approach to bridge this gap by attaching document fingerprints to the embedding to estimate the expectation of potential queries.
Outcome:	Experiments across diverse datasets, languages, and embedding models confirm the proposed solution is simple-yet-effective with zero additional index storage, retrieval latency, training costs, or catastrophic forgetting and hallucination issues.

Copied to clipboard

Xinyi Wang, Zitao Wang, Wei Hu

Bridging the Gap between Pre-Training and Fine-Tuning for Commonsense Generation (2023.findings-eacl)

Challenge:	Existing models for few-shot relation extraction (RE) are not suitable for continual few-sshot RE.
Approach:	They propose a new model to train a model for new relations with few labeled training data.
Outcome:	The proposed model outperforms state-of-the-art models on two benchmark datasets.

Copied to clipboard

Haoran Yang, Yan Wang, Piji Li, Wei Bi, Wai Lam, Chen Xu

Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference (2026.acl-long)

Challenge:	Existing methods focusing on this task usually concatenate the concatened concepts words as the inputs of a pre-trained language model (PLM) however, in pre-training, the input is often corrupted sentences with correct word order.
Approach:	They propose a two-stage framework to improve the ability of pre-trained language models to deal with masked sentences with incorrect word order and a special token to make the input distribution more similar to the one used in pre-training.
Outcome:	The proposed method is able to generate a sentence containing all given concepts and correctly describe the relations between concepts.

Copied to clipboard

Baihui Liu, Kaiyuan Tian, Wei Wang, Zhaoning Zhang, Linbo Qiao, Dongsheng Li

A Survey of Inductive Reasoning for Large Language Models (2026.acl-long)

Challenge:	Existing approaches that reduce expert activations lead to severe model performance degradation.
Approach:	They propose a framework that optimizes budget allocation coordinately at layer and token levels to minimize model performance degradation.
Outcome:	The proposed framework achieves 1.15 prefill and 1.34 decode speedups on DeepSeek-V2-Lite at half of the original budget.

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

BASS: Boosting Abstractive Summarization with Unified Semantic Graph (2021.acl-long)

Challenge:	Inductive reasoning is an important task for large language models (LLMs).
Approach:	They propose a survey of inductive reasoning for large language models . they categorize methods into three main areas: post-training enhancement, test-time exploration, and data augmentation.
Outcome:	The proposed method improves inductive reasoning in large language models.

Copied to clipboard

Wenhao Wu, Wei Li, Xinyan Xiao, Jiachen Liu, Ziqiang Cao, Sujian Li, Hua Wu, Haifeng Wang

DABERT: Dual Attention Enhanced BERT for Semantic Matching (2022.coling-1)

Challenge:	Abstractive summarization for long-document or multi-document remains challenging for Seq2Seq as it does not analyze long-distance relations in text.
Approach:	They propose a framework for Boosting Abstractive Summarization based on a unified Semantic graph which aggregates co-referent phrases distributing across a long range of context and conveys rich relations between phrases.
Outcome:	The proposed framework improves document representation and summary generation process by leveraging the graph structure.

Copied to clipboard

Sirui Wang, Di Liang, Jian Song, Yuntao Li, Wei Wu

Explainable Recommendation with Personalized Review Retrieval and Aspect Learning (2023.acl-long)

Challenge:	Existing models for semantic sentence matching lack the ability to capture subtle differences.
Approach:	They propose to use a Transformer-based pre-trained language model to capture fine-grained differences in sentence pairs by introducing a dual attention module and a fusion module to learn the aggregation of difference and affinity features.
Outcome:	The proposed method is able to capture fine-grained differences in sentence pairs.

Copied to clipboard

Hao Cheng, Shuo Wang, Wensheng Lu, Wei Zhang, Mingyang Zhou, Kezhong Lu, Hao Liao

MixLLM: Dynamic Routing in Mixed Large Language Models (2025.naacl-long)

Challenge:	Recent years have witnessed a growing interest in the development of explainable recommendation models.
Approach:	They propose a model that combines prediction and generation tasks to produce more persuasive explanations by obtaining additional information from the training sets.
Outcome:	The proposed model outperforms state-of-the-art models on three datasets and shows that it is more persuasive than previous models.

Copied to clipboard

Xinyuan Wang, Yanchi Liu, Wei Cheng, Xujiang Zhao, Zhengzhang Chen, Wenchao Yu, Yanjie Fu, Haifeng Chen

PASUM: A Pre-training Architecture for Social Media User Modeling Based on Text Graph (2024.lrec-main)

Challenge:	Large Language Models (LLMs) exhibit potential artificial generic intelligence, however, their usage is costly with high response latency.
Approach:	They develop a dynamic contextual-bandit-based routing system for query-LLM assignment that leverages query tags to enhance query embeddings.
Outcome:	The proposed model maximizes response quality and minimizes cost and latency.

Copied to clipboard

Kun Wu, Xinyi Mou, Lanqing Xue, Zhenzhe Ying, Weiqiang Wang, Qi Zhang, Xuanjing Huang, Zhongyu Wei

Advancing Sequential Numerical Prediction in Autoregressive Models (2025.acl-short)

Challenge:	Existing studies have incorporated different digital traces to better learn the representations of social media users, limited by overloaded text information and hard-to-collect social network information.
Approach:	They propose a Pre-training Architecture for Social Media User Modeling based on Text Graph and combine microblogs to represent social media users based upon the text graph model.
Outcome:	The proposed framework can represent users based on text even without social network information on microblogs.

Copied to clipboard

Xiang Fei, Jinghui Lu, Qi Sun, Hao Feng, Yanjie Wang, Wei Shi, An-Lan Wang, Jingqun Tang, Can Huang

Challenge:	Autoregressive models are the de facto choice for sequence generation tasks, but standard approaches treat digits as independent tokens and apply cross-entropy loss, overlooking the coherent structure of numerical sequences.
Approach:	They propose a novel approach to entropy loss by extending the Earth Mover’s Distance to preserve ordinal relationships between numerical values and sequence-level to penalize the overall discrepancy between predicted and actual sequences.
Outcome:	Extensive experiments show that NTIL improves numerical prediction and integrates effectively with LLMs/MLLMs.

Joint Multi-Label Attention Networks for Social Text Annotation (N19-1)

Copied to clipboard

Hang Dong, Wei Wang, Kaizhu Huang, Frans Coenen

Challenge:	Present research shows that title metadata could affect social annotation.
Approach:	They propose a title-guided attention network for document annotation with user-generated tags that separates the title from the content of a document and applies a semantic-based loss regulariser over each sentence in the content.
Outcome:	The proposed approach outperforms the Bi-GRU and Hierarchical Attention Network (HAN) on two open datasets with 10%-30% reduction in training time.

mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections (2022.emnlp-main)

Copied to clipboard

Chenliang Li, Haiyang Xu, Junfeng Tian, Wei Wang, Ming Yan, Bin Bi, Jiabo Ye, He Chen, Guohai Xu, Zheng Cao, Ji Zhang, Songfang Huang, Fei Huang, Jingren Zhou, Luo Si

Language-agnostic BERT Sentence Embedding (2022.acl-long)

Challenge:	Existing pre-trained vision-language models suffer from inefficiency and linguistic signal overwhelmed by long visual sequences in cross-modal alignment.
Approach:	They propose a vision-language foundation model with cross-modal skip-connections that can be pre-trained end-to-end on large-scale image-text pairs with both discriminative and generative objectives.
Outcome:	The proposed model achieves state-of-the-art results on a wide range of vision-language downstream tasks, including image captioning, image-text retrieval, visual grounding and visual question answering.

Copied to clipboard

Fangxiaoyu Feng, Yinfei Yang, Daniel Cer, Naveen Arivazhagan, Wei Wang

Supervised Gradual Machine Learning for Aspect-Term Sentiment Analysis (2023.tacl-1)

Challenge:	Existing methods for learning bilingual sentence embeddings are not well explored.
Approach:	They propose to combine best methods for learning multilingual sentence embeddings with pre-trained models to achieve 83.7% bi-text retrieval accuracy over 112 languages on Tatoeba.
Outcome:	The proposed model achieves 83.7% bi-text retrieval accuracy over 112 languages on Tatoeba, above the 65.5% achieved by LASER.

Copied to clipboard

Yanyan Wang, Qun Chen, Murtadha H.M. Ahmed, Zhaoqiang Chen, Jing Su, Wei Pan, Zhanhuai Li

SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Check (2020.acl-main)

Challenge:	Recent work shows that Aspect-Term Sentiment Analysis (ATSA) can be performed by Gradual Machine Learning (GML) but the current unsupervised solution is limited by inaccurate knowledge conveyance.
Approach:	They propose a supervised approach which leverages binary polarity relations between instances to enable supervised knowledge conveyance.
Outcome:	The proposed approach outperforms pure DNN solutions on real benchmark data.

Copied to clipboard

Xingyi Cheng, Weidi Xu, Kunlong Chen, Shaohua Jiang, Feng Wang, Taifeng Wang, Wei Chu, Yuan Qi

An Effective and Efficient Entity Alignment Decoding Algorithm via Third-Order Tensor Isomorphism (2022.acl-long)

Challenge:	Existing methods to detect and correct spelling errors in Chinese take external input or just heuristic rules.
Approach:	They propose to incorporate phonological and visual similarity knowledge into Chinese language models by using a specialized graph convolutional network.
Outcome:	The proposed method outperforms existing models on three human-annotated datasets.

Copied to clipboard

Xin Mao, Meirong Ma, Hao Yuan, Jianchao Zhu, ZongYu Wang, Rui Xie, Wei Wu, Man Lan

Multiview Identifiers Enhanced Generative Retrieval (2023.acl-long)

Challenge:	Existing methods focus on graph representation learning, but decoding is a key part of the process.
Approach:	They propose an EA Decoding Algorithm via Third-order Tensor Isomorphism (DATTI) they combine two sets of isomorphic equations to enhance the decoding process .
Outcome:	The proposed algorithm can deliver significant performance improvements even on the most advanced methods while the extra required time is less than 3 seconds.

Copied to clipboard

Yongqi Li, Nan Yang, Liang Wang, Furu Wei, Wenjie Li

ComRAG: Retrieval-Augmented Generation with Dynamic Vector Stores for Real-time Community Question Answering in Industry (2025.acl-industry)

Challenge:	Current approaches use a numeric ID or text piece as the identifier, but these identifieres cannot cover a passage’s content well.
Approach:	They propose a new type of identifier that is generated based on the content of a passage and could integrate contextualized information that text pieces lack.
Outcome:	The proposed approach performs the best in generative retrieval on three public datasets.

Copied to clipboard

Qinwen Chen, Wenbiao Tao, Zhiwei Zhu, Mingfan Xi, Liangzhong Guo, Yuan Wang, Wei Wang, Yunshi Lan

Beyond Static Personas: Situational Personality Steering for Large Language Models (2026.findings-acl)

Challenge:	Existing methods for Community Question Answering (CQA) focus on static knowledge, limiting their applicability to real-world scenarios.
Approach:	They propose a retrieval-augmented generation framework for real-time industrial CQA that integrates static knowledge with dynamic historical QA pairs via a centroid-based memory mechanism.
Outcome:	The proposed framework outperforms baselines on three industrial CQA datasets and achieves 25.9% improvement in vector similarity, reducing latency by 8.7%–23.3%, and lowering chunk growth from 20.23% to 2.06% over iterations.

Copied to clipboard

Zesheng Wei, Mengxiang Li, Zilei Wang, Yang Deng

Word Form Matters: LLMs’ Semantic Reconstruction under Typoglycemia (2025.findings-acl)

Challenge:	Existing personalization methods rely on static personality modeling to achieve optimal performance.
Approach:	They propose a training-free framework for advanced situational personality steering that incorporates situation-dependent behavior patterns within LLM personalities through analysis of persona neurons.
Outcome:	The proposed framework surpasses baselines on PersonalityBench and SPBench, demonstrating generalization and robustness to complex, unseen situations and different models architecture.

Copied to clipboard

Chenxi Wang, Tianle Gu, Zhongyu Wei, Lang Gao, Zirui Song, Xiuying Chen

Challenge:	Typoglycemia is a phenomenon where people can read words even when the middle letters of the words are scrambled.
Approach:	They propose a reliable metric to quantify the degree of semantic reconstruction and validate its effectiveness.
Outcome:	The proposed metric quantifies the degree of semantic reconstruction and validates its effectiveness.

Agent-based Substructure Counting under Local Differential Privacy (2026.acl-long)

Copied to clipboard

Yuting Zhang, Kai Wang, Wei Ni, Ying Zhang, Wenjie Zhang

Differentiable Data Augmentation for Contrastive Sentence Representation Learning (2022.emnlp-main)

Challenge:	Recent studies have demonstrated the ability of Large Language Models (LLMs) to process graph problems.
Approach:	They propose to decompose substructure counting into node-level tasks distributed among node agents and embed the knowledge of distributed algorithms and DP frameworks in the curator agent and privacy controller.
Outcome:	Extensive experiments on 6 real-world datasets validate the effectiveness of the proposed framework for substructure counting tasks under edge local differential privacy (LDP).

Copied to clipboard

Tianduo Wang, Wei Lu

PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models (2023.findings-acl)

Challenge:	a contrastive learning framework is used to fine-tune pre-trained language models with unlabeled sentences or labeled sentences.
Approach:	They propose a method that makes hard positives from unlabeled sentences . they use a prefix attached to a model to allow for differentiable data augmentation .
Outcome:	The proposed method yields significant improvements over existing methods under semi-supervised and supervised settings.

Copied to clipboard

Zhuocheng Gong, Jiahao Liu, Qifan Wang, Yang Yang, Jingang Wang, Wei Wu, Yunsen Xian, Dongyan Zhao, Rui Yan

Learning under Label Proportions for Text Classification (2023.findings-emnlp)

Challenge:	Quantization is a viable solution for pre-trained language models, but most existing methods are task-specific and require customized training and quantization with a large number of trainable parameters.
Approach:	They propose a "quantize before fine-tuning" framework that allows for quantization with a large number of trainable parameters on each individual task.
Outcome:	The proposed framework is compatible with quantization-aware training and post-training quantization and corrects quantization errors.

Copied to clipboard

Jatin Chauhan, Xiaoxuan Wang, Wei Wang

Text Classification

Challenge:	Using a set of data samples with ground truth labels, learning from label proportions is infeasible in many cases.
Approach:	They propose a setup where the data is provided in an aggregate form called bags and only the proportion of samples belonging to each class as the ground truth.
Outcome:	The proposed model achieves better results than baselines in almost 87% of the configurations.

From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognition (2025.emnlp-main)

Copied to clipboard

Tianduo Wang, Lu Xu, Wei Lu, Shanbo Cheng

GUI0: Self-Evolving Foundational GUI Agents in Super App Ecosystems (2026.acl-long)

Challenge:	Recent advances in Automatic Speech Recognition (ASR) have been fueled by massive speech corpora, but extending coverage to diverse languages with limited resources remains a formidable challenge.
Approach:	They propose a pipeline that converts large-scale text corpora into synthetic speech using off-the-shelf text-to-speech (TTS) models.
Outcome:	The proposed pipeline generates 500,000 hours of synthetic speech in ten languages and achieves transcription error reductions of over 30%.

Copied to clipboard

Xinyi Wang, Wei Dai, Kyle Qiao, Ke Wang, Peng Chen, Gang Cao, null Kangqin, Zhongpu Wang, Xiaode Zhang, Yanming Liu, Jihao Gu, Jingtao Xu, Gong Zhi

VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization (2026.acl-long)

Challenge:	Automated interaction with graphical user interfaces (GUIs) is central to general artificial intelligence, but remains challenging within Super App ecosystems.
Approach:	They propose a framework synergizing autonomous data synthesis with dual-agent co-evolution . GUI0 establishes a domain-aware foundation model via synthesized corpora and employs curriculum-driven reinforcement learning .
Outcome:	The proposed framework outperforms Gemini-2.5-Pro and Claude-4-Sonnet in the SuperAPP benchmark and has universal efficacy across base models.

Copied to clipboard

Dingyu Yao, Chenxu Yang, Zhengyang Tong, Zheng Lin, Wei Liu, Jian Luan, Weiping Wang

Document-level Causal Relation Extraction with Knowledge-guided Binary Question Answering (2024.findings-emnlp)

Challenge:	Existing quantization methods for large language models suffer performance degradation at ultra-low bit-widths due to key cache outliers.
Approach:	They propose a vector quantization method that suppresses outliers in the key cache and reduces memory access overhead.
Outcome:	The proposed method outperforms baseline quantization methods across long-context understanding and mathematical reasoning tasks while minimizing memory access overhead.

Copied to clipboard

Zimu Wang, Lei Xia, Wei Xjtlu, Xinya Du

Candidate Soups: Fusing Candidate Results Improves Translation Quality for Non-Autoregressive Translation (2022.emnlp-main)

Challenge:	Existing research on Event-Event Causal Relation Extraction (ECRE) has highlighted the lack of document-level modeling and causal hallucinations.
Approach:	They propose a Knowledge-guided binary Question Answering method with event structures for ECRE that utilizes cross-task knowledge in IE.
Outcome:	The proposed method achieves state-of-the-art on the MECI and MAVEN-ERE datasets.

Copied to clipboard

Huanran Zheng, Wei Zhu, Pengfei Wang, Xiaoling Wang

LLMs + Persona-Plug = Personalized LLMs (2025.acl-long)

Challenge:	Existing methods to improve NAT model's performance but do not fully utilize it.
Approach:	They propose a non-autoregressive translation method which can obtain high-quality translations while maintaining the inference speed of NAT models.
Outcome:	The proposed method outperforms the autoregressive translation model on three translation tasks with 7.6 speedup.

Copied to clipboard

Jiongnan Liu, Yutao Zhu, Shuting Wang, Xiaochi Wei, Erxue Min, Yu Lu, Shuaiqiang Wang, Dawei Yin, Zhicheng Dou

mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data (2025.findings-acl)

Challenge:	Large language models (LLMs) have demonstrated extraordinary capabilities in natural language understanding, generation, and reasoning.
Approach:	They propose a plug-and-play LLM model that embeds a user-specific embedding for each individual by modeling her historical contexts through a lightweight plug-in user embedder module.
Outcome:	Experiments on various tasks in the language model personalization (LaMP) benchmark show that the proposed model significantly outperforms existing personalized LLM approaches.

Copied to clipboard

Haonan Chen, Liang Wang, Nan Yang, Yutao Zhu, Ziliang Zhao, Furu Wei, Zhicheng Dou

MessToClean: Evidence-Grounded Structure-Preserving Reconstruction for Real-World Degraded Exam Paper Images (2026.acl-long)

Challenge:	Multimodal embedding models encode multimedia inputs into latent vector representations.
Approach:	They propose to synthesize multimodal multilingual data using a multimodal large language model . they identify three criteria for high-quality synthetic multimodal data .
Outcome:	The proposed model outperforms existing models on the MMEB Benchmark and the XTD benchmark.

Copied to clipboard

Jiayi Tuo, Cheng Tang, Zihan Wang, Chenyue Zhou, Yao Li, Yanbiao Ma, Chao Wang, Wei Dai, Mingxuan Wang, Shitong Qin, Ziwei Zhao

Assessing Factual Reliability of Large Language Model Knowledge (2024.naacl-long)

Challenge:	Existing Multimodal Large Language Models (MLLMs) fail under RDEI, leading to disrupted structure and evidence-unsupported hallucinations.
Approach:	They propose a backbone-agnostic, evidence-driven pipeline that treats off-the-shelf MLLMs as interchangeable components to improve stem consistency and figure consistency.
Outcome:	The proposed pipeline improves stem consistency by 1.01-3.18%, figure consistency by 0.50-49.16%, and refusal F1 by 1.06-10.88% across question types.

Copied to clipboard

Weixuan Wang, Barry Haddow, Alexandra Birch, Wei Peng

SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing (2022.acl-long)

Challenge:	Factual knowledge of LLMs is typically evaluated using accuracy, yet this metric does not capture the vulnerability of LRMs to hallucination-inducing factors like prompt and context variability.
Approach:	They propose a metric designed to measure LLMs’ factual reliability by comparing the distance between the probability distributions of a valid output and its counterparts produced by the same LLM probing the same fact using different styles of prompts and contexts.
Outcome:	The proposed metric measures the distance between the probability distributions of a valid output and its counterparts produced by the same LLM probing the same fact using different styles of prompts and contexts.

Copied to clipboard

Junyi Ao, Rui Wang, Long Zhou, Chengyi Wang, Shuo Ren, Yu Wu, Shujie Liu, Tom Ko, Qing Li, Yu Zhang, Zhihua Wei, Yao Qian, Jinyu Li, Furu Wei

Consistency Regularization for Cross-Lingual Fine-Tuning (2021.acl-long)

Challenge:	Existing work shows that pre-trained models can improve in various natural language processing tasks.
Approach:	They propose a unified-modal encoder-decoder framework that pre-trains speech-text representations using large-scale unlabeled speech and text data.
Outcome:	The proposed framework is superior to existing models on speech-to-text processing tasks.

Copied to clipboard

Bo Zheng, Li Dong, Shaohan Huang, Wenhui Wang, Zewen Chi, Saksham Singhal, Wanxiang Che, Ting Liu, Xia Song, Furu Wei

SocioBench: Modeling Human Behavior in Sociological Surveys with Large Language Models (2025.emnlp-main)

Challenge:	Experimental results show that consistency regularization improves cross-lingual fine-tuning . pre-trained cross-linguistic models can transfer task-specific supervision from one language to the other .
Approach:	They propose to improve cross-lingual fine-tuning with consistency regularization . they use example consistency regularized to penalize prediction sensitivity to four types of data augmentations .
Outcome:	The proposed method improves cross-lingual fine-tuning across tasks . it can be generalized to other target languages without additional training .

Copied to clipboard

Jia Wang, Ziyu Zhao, Tingjuntao Ni, Zhongyu Wei

Chinese Metaphorical Relation Extraction: Dataset and Models (2023.findings-emnlp)

Challenge:	Large language models (LLMs) lack large-scale, systematically constructed benchmarks for evaluating their alignment with real-world social attitudes.
Approach:	They propose a benchmark to assess LLMs' alignment with real-world social attitudes . they find LLM models achieve only 30–40% accuracy when simulating individuals .
Outcome:	The proposed benchmark shows that LLMs achieve only 30% accuracy when simulating individuals in complex survey scenarios.

Copied to clipboard

Guihua Chen, Tiantian Wu, MiaoMiao Cheng, Xu Han, Jiefu Gong, Shijin Wang, Wei Song

Multi-Stage Balanced Distillation: Addressing Long-Tail Challenges in Sequence-Level Knowledge Distillation (2024.findings-emnlp)

Challenge:	Metaphor identification is a core task in metaphor processing, which involves recognizing and analyzing metaphorical expressions in text.
Approach:	They propose a new formulation of metaphor identification as a relation extraction problem . they use a dataset to analyze metaphorical relations between two spans, a target and a source .
Outcome:	The proposed model can capture the properties of the target and source in Chinese sentences.

Copied to clipboard

Yuhang Zhou, Jing Zhu, Paiheng Xu, Xiaoyu Liu, Xiyao Wang, Danai Koutra, Wei Ai, Furong Huang

GenProve: Learning to Generate Text with Fine-Grained Provenance (2026.acl-long)

Challenge:	Knowledge distillation (KD) is a promising solution for large language models, but their deployment remains computationally expensive.
Approach:	They propose a framework which iteratively balances training data within a fixed computational budget and enables the transfer of knowledge from expensive teacher LLMs to smaller student models.
Outcome:	The proposed framework achieves state-of-the-art performance across diverse long-tailed datasets, enhancing both the efficiency and efficacy of the distilled models.

Copied to clipboard

Jingxuan Wei, Xingyue Wang, Yanghaoyu Liao, Jie Dong, Yuchen Liu, Caijun Jia, Bihui Yu, Junnan Zhu

“The Boating Store Had Its Best Sail Ever”: Pronunciation-attentive Contextualized Pun Recognition (2020.acl-main)

Challenge:	Existing methods for large language models (LLMs) are coarse-grained and fail to distinguish between direct quotes and complex reasoning.
Approach:	They propose a framework that combines supervised fine-tuning and group relative policy optimization to generate fluent answers while simultaneously producing sentence-level provenance triples.
Outcome:	The proposed framework outperforms 14 strong large language models in joint evaluation.

Copied to clipboard

Yichao Zhou, Jyun-Yu Jiang, Jieyu Zhao, Kai-Wei Chang, Wei Wang

Syntactic Text Processing

Challenge:	Identifying and modeling puns is challenging as they involve implicit semantic or phonological tricks.
Approach:	They propose a method to detect puns in a sentence and then locate them in it . they propose to capture phonetic associations between the context and phonetic symbols .
Outcome:	The proposed method outperforms state-of-the-art methods in pun detection and location tasks.

ConnPrompt: Connective-cloze Prompt Learning for Implicit Discourse Relation Recognition (2022.coling-1)

Copied to clipboard

Wei Xiang, Zhenglin Wang, Lu Dai, Bang Wang

UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation (2023.emnlp-main)

Challenge:	Existing paradigms for Implicit Discourse Relation Recognition (IDRR) do not exploit linguistic evidence embedded in the pre-training process.
Approach:	They propose a new paradigm to detect and classify relation sense between two text segments without an explicit connective.
Outcome:	The proposed method significantly outperforms the state-of-the-art algorithms even with fewer training data.

Copied to clipboard

Daixuan Cheng, Shaohan Huang, Junyu Bi, Yuefeng Zhan, Jianfeng Liu, Yujing Wang, Hao Sun, Furu Wei, Weiwei Deng, Qi Zhang

Coarse-to-Fine Grounded Memory for LLM Agent Planning (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) have impressive capabilities but need for task-specific prompt engineering can hinder their generalization.
Approach:	They propose a lightweight and versatile retriever that automatically retrieves prompts for a given zero-shot task input.
Outcome:	The proposed model is universally applicable across tasks and models . it mitigates hallucination problem in chatGPT, and it improves even the strongest LLMs.

Copied to clipboard

Wei Yang, Jinwei Xiao, Hongming Zhang, Qingyang Zhang, Yanna Wang, Bo Xu

Challenge:	Existing methods to enhance LLM with offline experiences or online trajectory analysis focus on single-granularity memory derived from dynamic environmental interactions.
Approach:	They propose a framework that grounds coarse-to-fine memories with LLM to enable flexible adaptation to diverse scenarios.
Outcome:	Extensive experiments on AlfWorld, Webshop and ScienceWorld show that the proposed framework outperforms baselines and comprehensively optimizes memory-enhanced LLM Agent system.

IDEA: An Interpretable and Editable Decision-Making Framework for LLMs via Verbal-to-Numeric Calibration (2026.findings-acl)

Copied to clipboard

Yanji He, Yuxin Jiang, Yiwen Wu, Bo Huang, Jiaheng Wei, Wei Wang

Event Detection from Social Media for Epidemic Prediction (2024.naacl-long)

Challenge:	Existing approaches fail to integrate domain expert insights beyond simple prompting.
Approach:	They propose a framework that extracts LLM decision knowledge into an interpretable parametric model over semantically meaningful factors.
Outcome:	Experiments show that IDEA outperforms DeepSeek R1 and GPT-5.2 in accuracy and accuracy.

Copied to clipboard

Tanmay Parekh, Anh Mac, Jiarui Yu, Yuxuan Dong, Syed Shahriar, Bonnie Liu, Eric Yang, Kuan-Hao Huang, Wei Wang, Nanyun Peng, Kai-Wei Chang

Multi-Grained Knowledge Distillation for Named Entity Recognition (2021.naacl-main)

Challenge:	Social media is an easy-to-access platform providing timely updates about societal trends and events.
Approach:	They propose a framework to extract epidemic-related events from social media posts to provide early warnings.
Outcome:	The proposed framework can detect epidemic events for three unseen epidemics of Monkeypox, Zika, and Dengue while existing models fail miserably.

Copied to clipboard

Xuan Zhou, Xiao Zhang, Chenyang Tao, Junya Chen, Bing Xu, Wei Wang, Jing Xiao

MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers (2021.findings-acl)

Challenge:	Pre-trained big models have delivered top performance in Seq2seq modeling, but their deployments in real-world applications are often hindered by excessive computations and memory demands.
Approach:	They propose a distillation scheme to efficiently transfer knowledge from big models to their cheaper counterparts.
Outcome:	The proposed scheme maximizes the assimilation of knowledge from the teacher model to the student model.

Copied to clipboard

Wenhui Wang, Hangbo Bao, Shaohan Huang, Li Dong, Furu Wei

OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use (2025.acl-long)

Challenge:	Existing work on deep self-attention distillation for natural language processing tasks is limited by computational resources and latency.
Approach:	They generalize deep self-attention distillation in MINILM by using only self- attention relation distillation for taskagnostic compression of pretrained Transformers.
Outcome:	The proposed model outperforms the state-of-the-art in a multilingual and multilingual teacher model.

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

Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm Perspective (2025.acl-long)

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.

Copied to clipboard

Yiyao Yu, Yuxiang Zhang, Dongdong Zhang, Xiao Liang, Hengyuan Zhang, Xingxing Zhang, Mahmoud Khademi, Hany Hassan Awadalla, Junjie Wang, Yujiu Yang, Furu Wei

Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation (2023.findings-emnlp)

Challenge:	Existing work shows that LLMs rely on single-paradigm reasoning that limits their effectiveness across diverse tasks.
Approach:	They propose a new framework that integrates multiple reasoning paradigms to enable synergistic collaboration.
Outcome:	The proposed model outperforms current SOTA models in theorem proving tasks and the MATH benchmark in arithmetic tasks.

Copied to clipboard

Heming Xia, Tao Ge, Peiyi Wang, Si-Qing Chen, Furu Wei, Zhifang Sui

Clear Up Confusion: Iterative Differential Generation for Fine-grained Intent Detection with Contrastive Feedback (2025.coling-main)

Challenge:	Experimental results show draft-then-verify paradigm can achieve around 5x speedup for the popular Transformer architectures with comparable generation quality to beam search decoding.
Approach:	They propose to use Spec-Drafter and Spec Verification to accelerate autoregressive (AR) decoding by combining a model optimized for efficient and accurate drafting and a reliable method for verifying the drafted tokens efficiently.
Outcome:	The proposed method achieves 5x speedup on seq2seq tasks with comparable generation quality to beam search decoding, refreshing the impression that draft-then-verify paradigm introduces only 1.4x2x speed up.

Copied to clipboard

Feng Zhang, Wei Chen, Meng Gao, Fei Ding, Tengjiao Wang, Jiahui Yao, Jiabin Zheng

Improving Neural Abstractive Document Summarization with Structural Regularization (D18-1)

Challenge:	Recent studies on fine-grained intent detection have focused on collecting large-scale and high-quality samples via crowdsourcing resulting in data scarcity.
Approach:	They propose an iterative differential generation framework with contrastive feedback to generate high-quality pseudo samples and accurately capture the crucial nuances in target class distribution.
Outcome:	The proposed framework generates high-quality pseudo samples and captures crucial nuances in target class distribution.

Copied to clipboard

Wei Li, Xinyan Xiao, Yajuan Lyu, Yuanzhuo Wang

An Electoral Approach to Diversify LLM-based Multi-Agent Collective Decision-Making (2024.emnlp-main)

Challenge:	Recent advances in document summarization fail to capture long-term structure of documents and multi-sentence summaries, resulting in information loss and repetitions.
Approach:	They propose to leverage structural information of documents and multi-sentence summaries to improve document summarization performance.
Outcome:	The proposed model outperforms state-of-the-art models on document summarization tasks.

Copied to clipboard

Xiutian Zhao, Ke Wang, Wei Peng

Adapt-and-Distill: Developing Small, Fast and Effective Pretrained Language Models for Domains (2021.findings-acl)

Challenge:	Recent advances in large language models have sparked interest in collaborative LLM agents.
Approach:	They propose to integrate various ordinal preferential voting mechanisms into LLMs to improve reasoning capabilities and robustness.
Outcome:	The proposed method improves reasoning capabilities and robustness of leading LLMs without complex system designs.

Copied to clipboard

Yunzhi Yao, Shaohan Huang, Wenhui Wang, Li Dong, Furu Wei

Denoising based Sequence-to-Sequence Pre-training for Text Generation (D19-1)

Challenge:	Large pre-trained models suffer from domain shift and are not optimal for specific domains.
Approach:	They propose a general approach to developing small, fast and effective pretrained models for specific domains by adapting off-the-shelf general pretrained model and performing task-agnostic knowledge distillation in target domains.
Outcome:	The proposed approach achieves better performance over the BERT BASE model in domain-specific tasks while 3.3 smaller and 5.1 faster than the BRT BASE.

Copied to clipboard

Liang Wang, Wei Zhao, Ruoyu Jia, Sujian Li, Jingming Liu

A Bayesian Topic Model for Human-Evaluated Interpretability (2022.lrec-1)

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.

Copied to clipboard

Justin Wood, Corey Arnold, Wei Wang

TEPrompt: Task Enlightenment Prompt Learning for Implicit Discourse Relation Recognition (2023.findings-acl)

Challenge:	Topic modeling is an effective way to analyze unstructured textual data.
Approach:	They propose to combine nonparametric and weakly-supervised topic models to produce interpretable topics.
Outcome:	The proposed model outperforms weakly-supervised models in the field of topic modeling.

Copied to clipboard

Wei Xiang, Chao Liang, Bang Wang

SOAPTriage: SOAP-Guided Multi-View Clinical Text Modeling Framework for Automated ESI Prediction (2026.acl-long)

Challenge:	Existing prompt learning models for IDRR use multiple-prompt decisions from three different yet much similar connective prediction templates.
Approach:	They propose to fuse three related tasks to fuse the learned features of auxiliary tasks to create a prompt learning model that can be used to boost the main task.
Outcome:	The proposed model outperforms the ConnPrompt in the training phase and in the testing phase.

Copied to clipboard

Enming Wang, Jianlei Wang, Xueping Peng, Hongjiao Guan, Yinglong Wang, Sibo Wei, Jianbin Guo, Ruifeng Xu, Wenpeng Lu

LongEmbed: Extending Embedding Models for Long Context Retrieval (2024.emnlp-main)

Challenge:	Emergency departments rely on the Emergency Severity Index (ESI) to assess patient acuity and prioritize care.
Approach:	They propose a SOAP-guided multi-view clinical text modeling framework for automated ESI prediction based on the SOAP paradigm .
Outcome:	The proposed framework outperforms prompting-based, multi-agent, and encoder-based baselines.

Copied to clipboard

Dawei Zhu, Liang Wang, Nan Yang, Yifan Song, Wenhao Wu, Furu Wei, Sujian Li

ToolRerank: Adaptive and Hierarchy-Aware Reranking for Tool Retrieval (2024.lrec-main)

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.

Copied to clipboard

Yuanhang Zheng, Peng Li, Wei Liu, Yang Liu, Jian Luan, Bin Wang

LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context Scenarios (2025.acl-long)

Challenge:	Recent studies have proposed tool learning, which augments LLMs with external tools.
Approach:	They propose an adaptive and hierarchy-aware reranking method to refine retrieval results by truncating the retrieval result related to seen and unseen tools at different positions.
Outcome:	The proposed method improves retrieval results, leading to better execution results generated by the LLM.

Copied to clipboard

Xiaodong Wu, Minhao Wang, Yichen Liu, Xiaoming Shi, He Yan, Lu Xiangju, Junmin Zhu, Wei Zhang

Phrase-level Self-Attention Networks for Universal Sentence Encoding (D18-1)

Challenge:	Existing benchmarks rarely focus on instruction-following in long-context scenarios or stability on different inputs.
Approach:	They propose a scalable dataset to evaluate LLMs’ instruction-following capabilities and stability across long contexts.
Outcome:	The proposed method evaluates LLMs’ instruction-following capabilities and stability across long contexts.

Copied to clipboard

Wei Wu, Houfeng Wang, Tianyu Liu, Shuming Ma

CompTab: A Comprehensive Benchmark for Real-World TableQA with Complex Reasoning and Irregular Tables (2026.acl-long)

Challenge:	Phrase-level self-attention networks (PSAN) can capture context dependencies at the phrase level instead of the sentence level.
Approach:	They propose to perform self-attention across words inside a phrase to capture context dependencies at the phrase level and use the gated memory updating mechanism to refine each word’s representation hierarchically with longer-term context dependency captured in a larger phrase.
Outcome:	The proposed model can achieve state-of-the-art performance across a plethora of NLP tasks including binary and multi-class classification, natural language inference and sentence similarity.

Copied to clipboard

Zhen Yang, Wei Du, Jie Wang, Wenze Zhou, Xiangfeng Meng, Zhengyang Wang, Suping Sun, Ziwei Du, Haodong Zou, Jie Chen, Yongbin Liu, Shicheng Tan, Jiahao Ying, Shu Zhao

Query2doc: Query Expansion with Large Language Models (2023.emnlp-main)

Challenge:	Existing benchmarks focus on well-structured tables and fail to reflect irregular structures and complex reasoning commonly encountered in real-world scenarios.
Approach:	They propose a benchmark to evaluate TableQA under complex reasoning and irregular table conditions.
Outcome:	The proposed framework improves generalization and realism of large language models under complex and irregular table conditions.

Copied to clipboard

Liang Wang, Nan Yang, Furu Wei

GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theory (2024.emnlp-main)

Challenge:	Existing methods for sparse and dense retrieval have limited success on popular datasets.
Approach:	They propose a query expansion approach that generates pseudo-documents by few-shot prompting large language models and then expands the query with generated pseudo-docs.
Outcome:	The proposed method boosts the performance of BM25 on ad-hoc IR datasets by 3% to 15% without any model fine-tuning.

Copied to clipboard

Wei Fan, Haoran Li, Zheye Deng, Weiqi Wang, Yangqiu Song

Dialect-SQL: An Adaptive Framework for Bridging the Dialect Gap in Text-to-SQL (2025.emnlp-main)

Challenge:	Existing research studies privacy by exploring various privacy attacks, defenses, and evaluations within narrowly predefined patterns.
Approach:	They propose a framework that leverages the theory of contextual integrity as a bridge to help LLMs understand the complex contexts for judicial assessing privacy violations.
Outcome:	The proposed framework bridges the theory of contextual integrity as a bridge, creating numerous synthetic scenarios grounded in relevant privacy statutes (e.g., HIPAA).

Copied to clipboard

Jie Shi, Xi Cao, Bo Xu, Jiaqing Liang, Yanghua Xiao, Jia Chen, Peng Wang, Wei Wang

M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions (2024.acl-long)

Challenge:	Existing Text-to-SQL research focuses on specific database systems, limiting adaptability to different dialects.
Approach:	They propose a framework that employs Object Relational Mapping (ORM) code as an intermediate language to bridge this gap.
Outcome:	The proposed framework outperforms existing methods that generate SQL queries directly.

Copied to clipboard

Zheng Wang, Shu Teo, Jieer Ouyang, Yongjun Xu, Wei Shi

What Would Happen Next? Predicting Consequences from An Event Causality Graph (2024.findings-emnlp)

Challenge:	Existing methods for retrieving relevant memories from an external database are coarse-grained and can cause noise and focus on crucial memories.
Approach:	They propose a multiple partition paradigm for RAG where each database partition serves as a basic unit for execution.
Outcome:	The proposed framework outperforms baseline methods on three language generation tasks on seven datasets.

Copied to clipboard

Chuanhong Zhan, Wei Xiang, Liang Chao, Bang Wang

StyleDGPT: Stylized Response Generation with Pre-trained Language Models (2020.findings-emnlp)

Challenge:	Existing script event prediction task forcasts the subsequent event based on an event script chain, but the evolution of historical events is more complicated in real world scenarios.
Approach:	They propose a Causality Graph Event Prediction task that forecasts consequential event based on an Event Causity Graph (ECG).
Outcome:	The proposed model outperforms the advanced competitors for the CGEP task.

Copied to clipboard

Ze Yang, Wei Wu, Can Xu, Xinnian Liang, Jiaqi Bai, Liran Wang, Wei Wang, Zhoujun Li

IoTMigrator: LLM-driven Embedded IoT Code Migration across Different OSes for Cloud-device Integration (2025.findings-emnlp)

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.

Copied to clipboard

null Yq, Kaijie Gong, Yi Gao, Hao Wang, Wei Dong

Challenge:	Neither outline-based code generation nor common code translation techniques can adequately address this challenge, despite their prevalence in existing systems.
Approach:	They have developed an algorithm that employs a multi-agent pipeline to handle embedded code migration under the TSL paradigm.
Outcome:	The proposed algorithm outperforms the baseline by 50.5% for pass rate and 13.0% for completeness across all tasks in RIOT and Zephyr.

False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize (2026.findings-acl)

Copied to clipboard

Cheng Wang, Zeming Wei, Qin Liu, Wenxuan Zhou, Muhao Chen

Guess What I am Thinking: A Benchmark for Inner Thought Reasoning of Role-Playing Language Agents (2025.findings-emnlp)

Challenge:	Recent work has leveraged probing-based approaches to study the separability of malicious and benign inputs in Large Language Models’ internal representations.
Approach:	They propose to use probing-based methods to study separability of malicious and benign inputs in LLMs' internal representations to detect harmful and benign content.
Outcome:	The proposed methods show that they learn superficial patterns rather than semantic harmfulness.

Copied to clipboard

Rui Xu, Mingyu Wang, Xintao Wang, Dakuan Lu, Xiaoyu Tan, Wei Chu, Xu Yinghui

Leveraging Declarative Knowledge in Text and First-Order Logic for Fine-Grained Propaganda Detection (2020.emnlp-main)

Challenge:	Recent advances in Large Language Models (LLMs)-based Role-Playing Language Agents (RPLAs) have attracted broad attention in various applications.
Approach:	They propose a benchmark for evaluating character thought generation using literature . they propose 'MIRROR' which generates character thoughts by retrieving memories, predicting character reactions, and synthesizing motivations.
Outcome:	The proposed benchmark outperforms existing methods in evaluating character thought generation.

Copied to clipboard

Ruize Wang, Duyu Tang, Nan Duan, Wanjun Zhong, Zhongyu Wei, Xuanjing Huang, Daxin Jiang, Ming Zhou

Challenge:	Existing methods for fine-grained propaganda detection are not based on input-output data, but instead use declarative knowledge to detect propagandistic text fragments.
Approach:	They propose a method to inject declarative knowledge of fine-grained propaganda techniques into training data to get better representations of propagandistic texts.
Outcome:	The proposed method achieves superior performance on a large dataset for propaganda detection.

UnifiedVisual: A Framework for Constructing Unified Vision-Language Datasets (2025.emnlp-main)

Copied to clipboard

Pengyu Wang, Shaojun Zhou, Chenkun Tan, Xinghao Wang, Wei Huang, Zhen Ye, Zhaowei Li, Botian Jiang, Dong Zhang, Xipeng Qiu

Bitnet.cpp: Efficient Edge Inference for Ternary LLMs (2025.acl-long)

Challenge:	Existing datasets address understanding and generation in isolation, limiting the performance of unified vision large language models.
Approach:	They propose a dataset that facilitates mutual enhancement between multimodal understanding and generation.
Outcome:	The proposed framework integrates diverse visual and textual inputs and outputs, enabling comprehensive cross-modal reasoning and precise text-to-image alignment.

Copied to clipboard

Jinheng Wang, Hansong Zhou, Ting Song, Shijie Cao, Yan Xia, Ting Cao, Jianyu Wei, Shuming Ma, Hongyu Wang, Furu Wei

FinEval: A Chinese Financial Domain Knowledge Evaluation Benchmark for Large Language Models (2025.naacl-long)

Challenge:	1-bit large language models have spurred interest in ternary LLMs, but efficient edge inference is still scarce.
Approach:	They propose an inference system optimized for 1-bit large language models . they propose a new library that facilitates sub-2-bits-per-weight inference .
Outcome:	The proposed inference system achieves 6.25x speed increase over full-precision baselines and 2.32x over low-bit baselines.

Copied to clipboard

Xin Guo, Haotian Xia, Zhaowei Liu, Hanyang Cao, Zhi Yang, Zhiqiang Liu, Sizhe Wang, Jinyi Niu, Chuqi Wang, Yanhui Wang, Xiaolong Liang, Xiaoming Huang, Bing Zhu, Zhongyu Wei, Yun Chen, Weining Shen, Liwen Zhang

ItiNera: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning (2024.emnlp-industry)

Challenge:	Large language models have demonstrated outstanding performance in various natural language processing tasks, but their security capabilities in the financial domain have not been explored.
Approach:	They propose to use a benchmark to evaluate large language models' financial domain knowledge and practical abilities.
Outcome:	The proposed benchmark evaluates large language models' financial domain knowledge and practical abilities.

Copied to clipboard

Yihong Tang, Zhaokai Wang, Ao Qu, Yihao Yan, Zhaofeng Wu, Dingyi Zhuang, Jushi Kai, Kebing Hou, Xiaotong Guo, Jinhua Zhao, Zhan Zhao, Wei Ma

Detecting Customer Complaint Escalation with Recurrent Neural Networks and Manually-Engineered Features (N19-2)

Challenge:	Existing urban itinerary planning studies focus on traditional tourism, but they lack the precision and accuracy needed to create a personalized itinerary.
Approach:	They propose an open-domain urban itinerary planning system that integrates spatial optimization with large language models to provide customized urban itineraries based on user needs.
Outcome:	The proposed system can generate personalized urban itineraries based on user needs and scale with existing methods.

Copied to clipboard

Wei Yang, Luchen Tan, Chunwei Lu, Anqi Cui, Han Li, Xi Chen, Kun Xiong, Muzi Wang, Ming Li, Jian Pei, Jimmy Lin

Challenge:	e-commerce companies often have the option of escalating complaints by filing grievances with a government authority . this is detrimental to an ecommerce company, but this problem is challenging to solve by integrating recurrent neural networks with manually-engineered features.
Approach:	They propose a model that integrates recurrent neural networks with manually-engineered features to identify cases where the customer expresses such an intent.
Outcome:	The proposed model outperforms baseline models and provides better recall and triage for specialized agents.

MeNTi: Bridging Medical Calculator and LLM Agent with Nested Tool Calling (2025.naacl-long)

Copied to clipboard

Yakun Zhu, Shaohang Wei, Xu Wang, Kui Xue, Shaoting Zhang, Xiaofan Zhang

Learning to Retrieve In-Context Examples for Large Language Models (2024.eacl-long)

Challenge:	Large Language Models (LLMs) have been widely used in medicine but are limited in their ability to fully address the complexities of the real world.
Approach:	They propose a universal agent architecture for Large Language Models that integrates a specialized medical toolkit and employs meta-tool and nested calling mechanisms to enhance LLM tool utilization.
Outcome:	The proposed framework improves the accuracy and performance of medical calculators in complex medical scenarios.

Copied to clipboard

Liang Wang, Nan Yang, Furu Wei

Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence (2025.emnlp-main)

Challenge:	Existing approaches to improve in-context learning performance are highly sensitive to the quality of the incontext examples provided.
Approach:	They propose a framework to iteratively train dense retrievers that can identify high-quality in-context examples for large language models.
Outcome:	The proposed model improves performance by retrieving examples with similar patterns, and the gains are consistent across LLMs of varying sizes.

Copied to clipboard

Yijiong Yu, Wei Wang, Ran Chen, Ji Pei

Beyond Sentence-level Labels: Integrating Conversational Context and Personal Experience for Natural Emotional Expression (2026.findings-acl)

Challenge:	Existing methods for parallelizable reasoning tasks are inefficient, says a new study . generating lengthy reasoning sequences is computationally expensive and time-consuming, says the study authors .
Approach:	They propose a method that decodes multiple tokens per forward pass using a tree-like attention mask . their method achieves nearly 100% speedup in decoding while basically maintaining the answer quality .
Outcome:	Experimental results show that the method achieves nearly 100% speedup in decoding while maintaining the answer quality.

Copied to clipboard

Haiyang Sun, Chenyang Le, Wei Wang, Leying Zhang, Chuang Li, Bing Han, Chenda Li, Mengxiao Bi, Yanmin Qian

CFinBench: A Comprehensive Chinese Financial Benchmark for Large Language Models (2025.naacl-long)

Challenge:	Existing systems rely on sentence-level labels, which fails to capture the subtle nuances of human affect.
Approach:	They propose to use a large-scale, context-aware speech corpus derived from multi-speaker audiobooks to generate a speech that is human-like.
Outcome:	The proposed model outperforms existing methods in terms of emotional expression accuracy and naturalness.

Copied to clipboard

Ying Nie, Binwei Yan, Tianyu Guo, Hao Liu, Haoyu Wang, Wei He, Binfan Zheng, Weihao Wang, Qiang Li, Weijian Sun, Yunhe Wang, Dacheng Tao

What Makes a Good Order of Examples in In-Context Learning (2024.findings-acl)

Challenge:	Large language models (LLMs) have achieved remarkable performance on various NLP tasks, yet their potential in more challenging task like finance, has not been fully explored.
Approach:	They propose a benchmark to assess the financial knowledge of large language models (LLMs) in China.
Outcome:	The proposed benchmark is the most comprehensive evaluation benchmark to date for LLMs in finance.

Copied to clipboard

Qi Guo, Leiyu Wang, Yidong Wang, Wei Ye, Shikun Zhang

Investigating and Enhancing Vision-Audio Capability in Omnimodal Large Language Models (2025.findings-acl)

Challenge:	Large language models (LLMs) demonstrate impressive few-shot learning capabilities via in-context learning (ICL).
Approach:	They propose to use unlabeled data to evaluate order performance . they propose to filter out subsets of orders with label fairness and select the most influential order for each test instance.
Outcome:	The proposed method is superior over strong baselines and validates generalizability across settings.

Copied to clipboard

Rui Hu, Delai Qiu, Shuyu Wei, Jiaming Zhang, Yining Wang, Shengping Liu, Jitao Sang

MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings (2026.acl-long)

Challenge:	Recent years have witnessed significant advancements in large language models (LLMs) but still struggle with integrating vision and audio.
Approach:	They propose a self-knowledge distillation method to improve vision-audio capabilities of OLLMs by learning from the vision-text components.
Outcome:	The proposed method improves vision-audio capabilities of OLLMs by learning from vision-text components, which improves interaction between audio and images and results in improved performance on multimodal tasks.

Copied to clipboard

Haonan Chen, Hong Liu, Yuping Luo, Liang Wang, Nan Yang, Furu Wei, Zhicheng Dou

MM-ChatAlign: A Novel Multimodal Reasoning Framework based on Large Language Models for Entity Alignment (2024.findings-emnlp)

Challenge:	Existing approaches to embed multimodal models face limitations such as suboptimal causal attention in VLMs and limited diversity in training objectives and data.
Approach:	They propose a framework for transforming pre-trained VLMs into bidirectional multimodal embedding models.
Outcome:	The proposed model improves performance across MMEB and ViDoRe-v2 benchmarks and exhibits strong scalability with both model size and training data on MMEF.

Copied to clipboard

Xuhui Jiang, Yinghan Shen, Zhichao Shi, Chengjin Xu, Wei Li, Huang Zihe, Jian Guo, Yuanzhuo Wang

Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs (2024.acl-long)

Challenge:	Existing MMEA methods rely on knowledge representation learning (KRL) to measure the similarity of entity embeddings.
Approach:	They propose a framework that utilizes the visual reasoning abilities of MLLMs for multimodal entity alignment.
Outcome:	The proposed framework integrates the visual reasoning abilities of MLLMs for multimodal entity alignment.

Copied to clipboard

Siyuan Wang, Zhongyu Wei, Yejin Choi, Xiang Ren

A Novel Cascade Binary Tagging Framework for Relational Triple Extraction (2020.acl-main)

Challenge:	Large language models (LLMs) have impressive human-like performance across various reasoning tasks, but their mastery of underlying inferential rules falls short of human capabilities.
Approach:	They propose a logic scaffolding inferential rule generation framework to construct an infer- ential rule base, ULogic, comprising both primitive and compositional rules across five domains.
Outcome:	The proposed model improves the ability to generate accurate, complex and abstract conclusions and premises and improves various commonsense reasoning tasks.

Copied to clipboard

Zhepei Wei, Jianlin Su, Yue Wang, Yuan Tian, Yi Chang

SessionIntentBench: A Multi-task Inter-session Intention-shift Modeling Benchmark for E-commerce Customer Behavior Understanding (2026.findings-acl)

Challenge:	Existing approaches to extract relational triples from unstructured text are inadequate to solve the overlapping triple problem.
Approach:	They propose a cascade binary tagging framework that models relations as functions that map subjects to objects in a sentence.
Outcome:	The proposed framework outperforms state-of-the-art methods on two datasets . it outperformed baseline methods by 17.5 and 30.2 absolute gains .

Copied to clipboard

Yuqi Yang, Weiqi Wang, Baixuan Xu, Wei Fan, Qing Zong, Chunkit Chan, Zheye Deng, Xin Liu, Yifan Gao, Changlong Yu, Chen Luo, Yang Li, Zheng Li, Qingyu Yin, Bing Yin, Yangqiu Song

At Your Own PACE: A Causal Framework for Evaluating EQ in LLMs (2026.findings-acl)

Challenge:	Existing models fail to capture and model customer intention effectively because of insufficient information exploitation and only apparent information like descriptions and titles are used.
Approach:	They propose to exploit existing session data to capture and model intention in E-commerce product purchase sessions using a multimodal benchmark.
Outcome:	The proposed framework can bridge the gap between intention understanding in simplified research cases like co-buy intention and more complex yet practical scenarios like session history.

Copied to clipboard

Lei Lyu, Shengling Wang, Ke Chao, Yichao Wei

Challenge:	Emotional Quotient (EQ) has emerged as a competency for seamless human-AI integration.
Approach:	They propose a framework for a closed-loop EQ evaluation using a PACE taxonomy to define four dimensions of LLM EQ.
Outcome:	The proposed framework achieves high alignment of 89.31% with human preferences while maintaining robust consistency of 83.6%.

Training a Better Chinese Spelling Correction Model via Prior-knowledge Guided Teacher (2024.findings-acl)

Copied to clipboard

Chi Wei, Shaobin Huang, Rongsheng Li, Naiyu Yan, Rui Wang

QRMeM: Unleash the Length Limitation through Question then Reflection Memory Mechanism (2024.findings-emnlp)

Challenge:	Chinese Spelling Correction models are prone to over-correct and poor generalization for error patterns outside the standard distribution.
Approach:	They propose a teacher network guided by prior knowledge for distillation learning of CSC models.
Outcome:	The proposed method significantly enhances the CSC model’s language modeling capabilities, crucial for minimizing over-correction.

Copied to clipboard

Bo Wang, Heyan Huang, Yixin Cao, Jiahao Ying, Wei Tang, Chong Feng

Instruction-Tuning Data Synthesis from Scratch via Web Reconstruction (2025.findings-acl)

Challenge:	Existing methods for processing large textual content face insufficient adaptation to task-specific needs and missing multi-segmentation relationships.
Approach:	They propose a question then reflection memory mechanism which integrates a dual-structured memory pool and a structured graph guidance to facilitate a reflective trial-and-error approach for navigating and identifying relevant segments.
Outcome:	The proposed model achieves superior performance on multiple-choice questions and multi-doc QA.

Copied to clipboard

Yuxin Jiang, Yufei Wang, Chuhan Wu, Xinyi Dai, Yan Xu, Weinan Gan, Yasheng Wang, Xin Jiang, Lifeng Shang, Ruiming Tang, Wei Wang

Improving Event Representation via Simultaneous Weakly Supervised Contrastive Learning and Clustering (2022.acl-long)

Challenge:	Existing methods for generating and curating high-quality instruction-tuning data rely heavily on the quality of seed data or strong assumptions about the structure and content of web documents.
Approach:	They propose a fully automated framework for synthesizing high-quality instruction-tuning (IT) data directly from raw web documents with minimal assumptions.
Outcome:	The proposed framework outperforms state-of-the-art baselines by 16.65% across four instruction-following benchmarks.

Copied to clipboard

Jun Gao, Wei Wang, Changlong Yu, Huan Zhao, Wilfred Ng, Ruifeng Xu

Ideology Takes Multiple Looks: A High-Quality Dataset for Multifaceted Ideology Detection (2023.emnlp-main)

Challenge:	Existing work exploits easily accessible co-occurrence information of events to learn event representations.
Approach:	They propose a weakly supervised contrastive learning method and a prototype-based clustering method for event representation learning.
Outcome:	The proposed framework outperforms baselines on Hard Similarity and Transitive Sentence Similarity tasks.

Copied to clipboard

Songtao Liu, Ziling Luo, Minghua Xu, Lixiao Wei, Ziyao Wei, Han Yu, Wei Xiang, Bang Wang

Challenge:	Existing datasets for the ID task only label a text as ideologically left- or right-leaning as a whole, regardless whether the text containing one or more different issues.
Approach:	They construct an ideological schema for a multifaceted ideology detection task using MITweet and an English Twitter dataset.
Outcome:	The proposed task uses a MITweet dataset with 12,594 English Twitter posts, each annotated with a Relevance and an Ideology label for all twelve facets.

SADA: Bridging In-Context Learning and Fine-Tuning via State-Aligned Distillation Adapters (2026.acl-long)

Copied to clipboard

Wenhao Gao, Tianlong Wang, Wei Jia, Linhao Zhang, Aiwei Liu, Miao Fan, Zhou Xiao

Knowledge Association with Hyperbolic Knowledge Graph Embeddings (2020.emnlp-main)

Challenge:	Prompt-based in-context learning and parameter fine-tuning are dominant paradigms for incorporating external information into large language models, but they incur high inference costs or require expensive retraining.
Approach:	They propose to convert prompts into temporary adapter weights to bridge this gap by converting prompts to temporary adapters.
Outcome:	The proposed model outperforms baselines on long-context language modeling and downstream NLU and summarization benchmarks while significantly reducing memory footprint and latency.

Copied to clipboard

Zequn Sun, Muhao Chen, Wei Hu, Chengming Wang, Jian Dai, Wei Zhang

Privacy Evaluation Benchmarks for NLP Models (2024.findings-emnlp)

Challenge:	Existing methods for knowledge graphs (KGs) depend on high embedding dimensions and hierarchical structures to achieve expressiveness.
Approach:	They propose a hyperbolic relational graph neural network for KG embedding and capture knowledge associations with a high-dimensional transformation.
Outcome:	Experiments on entity alignment and type inference show the proposed method is effective and efficient.

Copied to clipboard

Wei Huang, Yinggui Wang, Cen Chen

Investigating Human and LLMs’ Decisions in Unverifiable Environments: A Case Study with GitHub Activity Overview (2026.findings-acl)

Challenge:	Several kinds of privacy attacks are studied in depth, but they are non-systematic and lack a comprehensive understanding of the impact caused by the attacks.
Approach:	They propose a privacy attack and defense evaluation benchmark in the field of NLP . they propose an improved attack method and a chained framework for privacy attacks .
Outcome:	The proposed framework can be chained to achieve a higher-level attack objective.

Copied to clipboard

Zheng Jiang, Wei Wang, Gaowei Zhang, Yang Feng, Yi Wang

Evaluating Instructively Generated Statement by Large Language Models for Directional Event Causality Identification (2025.findings-acl)

Challenge:	examining the behaviors of Large Language Models as artificial social actors is underexplored, especially in unverifiable scenarios where conventional benchmarking has little to help improve their abilities.
Approach:	They propose a method to collect, compare, and reason about human and LLMs' decisions in an unverifiable scenario and use it to examine their behaviors.
Outcome:	The proposed method compared human and LLM decisions in an unverifiable scenario on GitHub and found that proprietary LLMs behave more like humans than open-source LLM systems.

Copied to clipboard

Wei Xiang, Chuanhong Zhan, Qing Zhang, Bang Wang

CSR-Bench: Benchmarking LLM Agents in Deployment of Computer Science Research Repositories (2025.naacl-long)

Challenge:	Existing studies focus on identifying existence of causality between two event mentions, but the direction of causalities is crucial for understanding the causal relation.
Approach:	They propose to instruct a GLM to generate causality statements and identify directional event causality by evaluating the generated statements.
Outcome:	The proposed method significantly outperforms state-of-the-art methods even with fewer training data.

Copied to clipboard

Yijia Xiao, Runhui Wang, Luyang Kong, Davor Golac, Wei Wang

Challenge:	Large Language Models (LLMs) have demonstrated significant advances in computer science research . current agent-related applications include code writing, code base generation, code correction and more.
Approach:	They propose a benchmark to assess the effectiveness of Large Language Models (LLMs) they propose GitHub agent framework that automates deployment of GitHub repositories .
Outcome:	The proposed framework improves the deployment of GitHub code repositories and thereby boosts developer productivity.

SampleMix: A Sample-wise Pre-training Data Mixing Strategy by Coordinating Data Quality and Diversity (2025.findings-emnlp)

Copied to clipboard

Xiangyu Xi, Deyang Kong, Jian Yang, Jiawei Yang, Zhengyu Chen, Wei Wang, Jingang Wang, Xunliang Cai, Shikun Zhang, Wei Ye

Identifying while Learning for Document Event Causality Identification (2024.acl-long)

Challenge:	Existing methods for pretraining data mixing for large language models neglect significant inter-domain overlaps and commonalities, failing to control the global diversity of the constructed training dataset.
Approach:	They propose a sample-wise data mixture approach that performs global cross-domain sampling by systematically evaluating the quality and diversity of each sample.
Outcome:	The proposed method exceeds existing domain-based methods in multiple downstream tasks and perplexity assessments.

Copied to clipboard

Cheng Liu, Wei Xiang, Bang Wang

Challenge:	Existing studies focus on causality existence, but ignore causal direction.
Approach:	They propose a new identifying while learning mode for the ECI task that takes care of the causal direction and updates events’ representations for boosting next round of causality identification.
Outcome:	The proposed method outperforms the state-of-the-art methods on two public datasets.

TeCES: Collaborative Geometric Knowledge Representation Framework under Evolving Fact Snapshots (2026.acl-long)

Copied to clipboard

Jiujiang Guo, Zhengliang Guo, Kai Wang, Meiyang Wang, Dehua Peng, Shaozu Yuan, Chengyin Hu, Shuan Ai, Yiwei Wei

ASR-EC Benchmark: Evaluating Large Language Models on Chinese ASR Error Correction (2025.emnlp-industry)

Challenge:	Existing knowledge graphs represent static facts but lack collaborative modeling of both . e.g., existing knowledge graph models lack a framework for integrating snapshots into knowledge graph.
Approach:	They propose a framework for high-fidelity modeling of evolving snapshots using concept of snapshots.
Outcome:	The proposed framework outperforms existing models on six benchmarks.

Copied to clipboard

Victor Junqiu Wei, Weicheng Wang, Di Jiang, Yuanfeng Song, Lu Wang

TED-TTS: Training-Free Intra-Utterance Emotion and Duration Control for Text-to-Speech Synthesis (2026.acl-long)

Challenge:	Automatic Speech Recognition (ASR) systems have a substantial number of erroneous recognition due to environmental noise, ambiguity, etc.
Approach:	They use a benchmark dataset to analyze ASR errors in the Chinese language . they then apply large language models to correct ASR error correction .
Outcome:	The proposed method is based on a dataset of ASR errors in the Chinese language . it shows prompting is not effective for ASR error correction .

Copied to clipboard

Qifan Liang, Yuansen Liu, Ruixin Wei, Nan Lu, Junchuan Zhao, Ye Wang

PIPER: Benchmarking and Prompting Event Reasoning Boundary of LLMs via Debiasing-Distillation Enhanced Tuning (2025.acl-long)

Challenge:	Existing controllable Text-to-Speech methods limited to inter-utterance-level control . utterance expressiveness remains a challenge in building human-like TTS synthesis systems .
Approach:	They propose a training-free controllable framework for pretrained zero-shot TTS to enable intra-utterance emotion and duration expression.
Outcome:	The proposed framework achieves state-of-the-art intra-utterance consistency while maintaining baseline-level speech quality.

Copied to clipboard

Zhicong Lu, Changyuan Tian, PeiguangLi PeiguangLi, Li Jin, Sirui Wang, Wei Jia, Ying Shen, Guangluan Xu

Automatic Essay Scoring Incorporating Rating Schema via Reinforcement Learning (D18-1)

Challenge:	Existing studies on Large Language Models (LLMs) have failed to evaluate their performance in event reasoning with a single event relational type or reasoning format.
Approach:	They propose a benchmark to evaluate LLMs' event reasoning capability using a single event relational type or reasoning format.
Outcome:	The proposed model improves on 10K diverse instruction-tuning demonstrations to alleviate event reasoning-oriented data scarcity.

Copied to clipboard

Yucheng Wang, Zhongyu Wei, Yaqian Zhou, Xuanjing Huang

Challenge:	Existing systems for automatic essay scoring are trained to predict the score of each essay at a time without considering rating schema.
Approach:	They propose a reinforcement learning framework that incorporates quadratic weighted kappa as guidance to optimize the scoring system.
Outcome:	Experiments on benchmark datasets show the proposed framework is effective.

Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation (2025.emnlp-main)

Copied to clipboard

Song Wang, Zihan Chen, Peng Wang, Zhepei Wei, Zhen Tan, Yu Meng, Cong Shen, Jundong Li

Text Clustering

Challenge:	Large language models (LLMs) lack robustness in knowledge-intensive tasks due to noisy or irrelevant retrieved data.
Approach:	They propose a multi-agent debate-based RAG framework that integrates external knowledge sources into large language models to improve their accuracy.
Outcome:	The proposed framework is unsupervised and leverages pretrained LLMs without fine-tuning, making it easily adaptable to various tasks.

Ranking-Based Autoencoder for Extreme Multi-label Classification (N19-1)

Copied to clipboard

Bingyu Wang, Li Chen, Wei Sun, Kechen Qin, Kefeng Li, Hui Zhou

cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree (2025.findings-emnlp)

Challenge:	Existing methods to solve label dependency and noisy labeling problems are limited . experimental results show the proposed method is competitive to state-of-the-art methods .
Approach:	They propose a deep learning XML method with word-vector-based self-attention followed by ranking-based AutoEncoder architecture to solve these problems.
Outcome:	The proposed method is competitive to state-of-the-art methods on benchmark datasets.

Copied to clipboard

Yilin Zhang, Xinran Zhao, Zora Zhiruo Wang, Chenyang Yang, Jiayi Wei, Tongshuang Wu

Syntactic Text Processing

Challenge:	Existing line-based chunking heuristics often break semantic structures, splitting functions or merging unrelated code.
Approach:	They propose a structure-aware method that breaks large AST nodes into smaller chunks . this method generates self-contained, semantically coherent units across programming languages .
Outcome:	The proposed method boosts Recall@5 by 4.3 points on RepoEval retrieval and Pass@1 by 2.67 points on SWE-bench generation.

Route Sparse Autoencoder to Interpret Large Language Models (2025.emnlp-main)

Copied to clipboard

Wei Shi, Sihang Li, Tao Liang, Mingyang Wan, Guojun Ma, Xiang Wang, Xiangnan He

EvoWiki: Evaluating LLMs on Evolving Knowledge (2025.acl-long)

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.

Copied to clipboard

Wei Tang, Yixin Cao, Yang Deng, Jiahao Ying, Bo Wang, Yizhe Yang, Yuyue Zhao, Qi Zhang, Xuanjing Huang, Yu-Gang Jiang, Yong Liao

Challenge:	Existing knowledge evolution benchmarks are static and fail to capture the evolving nature of LLMs and knowledge.
Approach:	They propose an evolving dataset that categorizes information into stable, evolved, and uncharted states.
Outcome:	The proposed dataset is auto-updatable and enables evaluation of continuously changing knowledge and newly released LLMs.

EquiBench: Benchmarking Large Language Models’ Reasoning about Program Semantics via Equivalence Checking (2025.emnlp-main)

Copied to clipboard

Anjiang Wei, Jiannan Cao, Ran Li, Hongyu Chen, Yuhui Zhang, Ziheng Wang, Yuan Liu, Thiago S. F. X. Teixeira, Diyi Yang, Ke Wang, Alex Aiken

Fusion or Defusion? Flexible Vision-and-Language Pre-Training (2023.findings-acl)

Challenge:	EquiBench is a new benchmark to evaluate large language models' ability to reason about program semantics . Unlike natural language, code is executable.
Approach:	They propose a benchmark to evaluate large language models through equivalence checking . EquiBench consists of 2400 program pairs across four languages and six categories .
Outcome:	The proposed benchmark consists of 2400 program pairs across four languages and six categories.

Copied to clipboard

Rongyi Sun, Ziran Li, Yifeng Ding, Qifan Wang, Jingang Wang, Haitao Zheng, Wei Wu, Yunsen Xian

Making Pretrained Language Models Good Long-tailed Learners (2022.emnlp-main)

Challenge:	Existing approaches to vision-and-language pretraining (VLP) lack effectiveness and efficiency in downstream multimodal tasks.
Approach:	They propose a flexible vision-and-language pre-training model by incorporating cross-modal fusions into a dual-encoder architecture and a cross-module knowledge transfer strategy to guide the training process.
Outcome:	The proposed model is well-equipped with effectiveness and efficiency compared with other strong VLP models.

Copied to clipboard

Chen Zhang, Lei Ren, Jingang Wang, Wei Wu, Dawei Song

Dual Class Knowledge Propagation Network for Multi-label Few-shot Intent Detection (2023.acl-long)

Challenge:	Prompt-tuning has shown appealing performance in few-shot classification . however, it is less promising in long-tailed classification due to long tail .
Approach:	They propose to use prompt-tuning to make pretrained language models at least good long-tailed learners by bridging the gap between prompt- and commonly used finetun.
Outcome:	The proposed method makes pretrained language models at least good long-tailed learners, bridging the gap between prompt-tuning and finetunation.

Copied to clipboard

Feng Zhang, Wei Chen, Fei Ding, Tengjiao Wang

DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing (2026.acl-long)

Challenge:	Existing studies on multi-label intent detection are confused by the identical representation of the utterance with multiple labels and overlook the intrinsic intra-class and inter-class relations.
Approach:	They propose a dual class knowledge propagation network to learn well-separated representations for utterances with multiple intents.
Outcome:	The proposed method outperforms baselines on two multi-label intent datasets by a large margin.

Copied to clipboard

Qian Cao, Yahui Liu, Wei Bi, Yi Zhao, Ruihua Song, Xiting Wang, Ruiming Tang, Guorui Zhou, Han Li

Challenge:	Existing methods for enhancing large language models (LLMs) lack explicit mechanisms for guiding diverse exploration and instead prioritize efficiency and performance over diversity.
Approach:	They propose a reinforcement learning-based framework that decomposes the generation process into explicitly planned intermediate steps and introduces divergence at the planning phase based on diversity variation.
Outcome:	The proposed method significantly outperforms existing baselines on creative writing benchmarks on a semi-structured long chain-of-thought (CoT) it introduces divergence at the planning phase based on diversity variation, alongside a group-aware diversity reward to encourage distinct trajectories.

TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)

Copied to clipboard

Xiao Wang, Qin Liu, Tao Gui, Qi Zhang, Yicheng Zou, Xin Zhou, Jiacheng Ye, Yongxin Zhang, Rui Zheng, Zexiong Pang, Qinzhuo Wu, Zhengyan Li, Chong Zhang, Ruotian Ma, Zichu Fei, Ruijian Cai, Jun Zhao, Xingwu Hu, Zhiheng Yan, Yiding Tan, Yuan Hu, Qiyuan Bian, Zhihua Liu, Shan Qin, Bolin Zhu, Xiaoyu Xing, Jinlan Fu, Yue Zhang, Minlong Peng, Xiaoqing Zheng, Yaqian Zhou, Zhongyu Wei, Xipeng Qiu, Xuanjing Huang

Task-Oriented Clustering for Dialogues (2021.findings-emnlp)

Challenge:	Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction.
Approach:	They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack.
Outcome:	The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses.

Copied to clipboard

Chenxu Lv, Hengtong Lu, Shuyu Lei, Huixing Jiang, Wei Wu, Caixia Yuan, Xiaojie Wang

OpenRLHF: A Ray-based Easy-to-use, Scalable and High-performance RLHF Framework (2025.emnlp-demos)

Challenge:	Existing methods for task-oriented dialogue clustering are difficult to apply directly due to inherent differences between them.
Approach:	They propose a Dialogue Task Clustering Network model for task-oriented clustering . they use context-aware utterance representations and cross-dialogue utterrance cluster representations .
Outcome:	The proposed model outperforms baselines on three public datasets on all metrics.

Copied to clipboard

Jian Hu, Xibin Wu, Wei Shen, Jason Klein Liu, Weixun Wang, Songlin Jiang, Haoran Wang, Hao Chen, Bin Chen, Wenkai Fang, null Xianyu, Yu Cao, Haotian Xu, Yiming Liu

LONG2RAG: Evaluating Long-Context & Long-Form Retrieval-Augmented Generation with Key Point Recall (2024.findings-emnlp)

Challenge:	Existing RLHF frameworks face inference bottlenecks and complexity barriers restricting their accessibility for newcomers.
Approach:	They propose an open-source RLHF framework that can be used to train large language models.
Outcome:	The proposed framework achieves superior training efficiency with speedups ranging from 1.22 to 1.68 across different model sizes compared to state-of-the-art frameworks, while requiring significantly fewer lines of code for implementation.

Copied to clipboard

Zehan Qi, Rongwu Xu, Zhijiang Guo, Cunxiang Wang, Hao Zhang, Wei Xu

MotifAgent: Learning Molecular Assembly through Multi-Agent Collaboration for Chemical Language Understanding (2026.findings-acl)

Challenge:	Retrieval-augmented generation (RAG) is a promising approach to address limitations of fixed knowledge in large language models.
Approach:	They propose a benchmark and a metric to assess LLMs' ability to generate long-form responses that exploit retrieved information.
Outcome:	The proposed benchmarks lack a comprehensive evaluation method to assess LLMs' ability to generate long-form responses that effectively exploits retrieved information.

Copied to clipboard

Jinjia Feng, Wenda Wang, Zhewei Wei

Challenge:	Existing approaches to molecular understanding are limited to static motif recognition without understanding connection rules governing how motifs assemble into valid topological structures.
Approach:	They propose a multi-agent reinforcement learning framework inspired by emergent collective intelligence to solve a problem where each motif is represented by an agent sharing a common LLM backbone.
Outcome:	Extensive experiments show that the proposed framework surpasses specialized expert models in molecular understanding tasks.

iTAG: Inverse Design for Natural Text Generation with Accurate Causal Graph Annotations (2026.acl-long)

Copied to clipboard

Wenshuo Wang, Boyu Cao, Nan Zhuang, Wei Li

Prompt-based Zero-shot Text Classification with Conceptual Knowledge (2023.acl-srw)

Challenge:	Lack of causally annotated text data for use as ground truth hinders causal discovery . early template-based generation methods sacrifice text naturalness in exchange for high annotation costs .
Approach:	They propose a method which performs real-world concept assignment to nodes before converting causal graphs into text.
Outcome:	The proposed method shows high annotation accuracy and naturalness across extensive tests.

Copied to clipboard

Yuqi Wang, Wei Wang, Qi Chen, Kaizhu Huang, Anh Nguyen, Suparna De

KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models (2024.acl-long)

Challenge:	Existing approaches to pre-training language models rely on verbalizers to translate the predicted vocabulary to task-specific labels.
Approach:	They propose a framework that incorporates conceptual knowledge for text classification in the extreme zero-shot setting.
Outcome:	The proposed framework outperforms prompt-based approaches on four widely-used datasets for sentiment analysis and topic detection on the same experimental settings.

Copied to clipboard

Zhuohao Yu, Chang Gao, Wenjin Yao, Yidong Wang, Wei Ye, Jindong Wang, Xing Xie, Yue Zhang, Shikun Zhang

DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimization (2023.acl-long)

Challenge:	Existing methods to detect contaminated texts focus on quantifying contamination status instead of accurately gauging model performance.
Approach:	They propose a Knowledge-grounded Interactive Evaluation framework which incorporates an LLM-powered “interactor” role for the first time to accomplish a dynamic contamination-resilient evaluation.
Outcome:	The proposed framework is based on a question in a standard LLM benchmark and can be used to evaluate models in real-world conversations.

Copied to clipboard

SongYang Gao, Shihan Dou, Yan Liu, Xiao Wang, Qi Zhang, Zhongyu Wei, Jin Ma, Ying Shan

Neural Machine Translation with Heterogeneous Topic Knowledge Embeddings (2021.emnlp-main)

Challenge:	Existing adversarial training methods require multi-step gradient ascents or word substitutions to obtain adversarials, which impairs the effectiveness of adversariarial training.
Approach:	They propose a procedure for instead adversarial training with only clean data that estimates the adversarials loss by perturbing the input data’s probability distribution rather than their embeddings.
Outcome:	The proposed procedure reduces time consumption by up to 70% compared to current best-performing adversarial training methods.

Copied to clipboard

Weixuan Wang, Wei Peng, Meng Zhang, Qun Liu

DANCE: Diversity-attended Dynamic Caching with Asymmetric Quantization for Test-time Adaptation of Vision-Language Models (2026.findings-acl)

Challenge:	Existing NMT models can handle meaning ambiguities based on local contexts, but it remains a challenge to translate words in implicit collocations.
Approach:	They propose heterogeneous ways of embedding topic information into NMT models . they propose to incorporate topic knowledge embeddable into the NMT model .
Outcome:	The proposed methods outperform baselines on English -> German and English => French translation tasks.

Copied to clipboard

Shunge Zou, Changhu Wang, Wei Ju, Ziyue Qiao, Xiao Luo

LAiW: A Chinese Legal Large Language Models Benchmark (2025.coling-main)

Challenge:	Existing approaches to test-time adaptation of vision-language models measure prediction entropy but these samples tend to approach prototypes with limited coverage of data distributions.
Approach:	They propose a new approach for test-time adaptation of vision-language models . they construct a dynamic cache to store diversity-aware test samples .
Outcome:	The proposed approach is more efficient than current methods on augmented visual models.

Copied to clipboard

Yongfu Dai, Duanyu Feng, Jimin Huang, Haochen Jia, Qianqian Xie, Yifang Zhang, Weiguang Han, Wei Tian, Hao Wang

Unleashing Low-Bit Inference on Ascend NPUs: A Comprehensive Evaluation of HiFloat Formats (2026.acl-industry)

Challenge:	Xie et al., 2023) show that large language models (LLMs) can generate legal text, but lack the legal syllogism . legal experts are cautious about their practical application due to the opaque nature of the LLMs.
Approach:	They propose a Chinese legal LLM benchmark structured around the legal syllogism . they evaluate LLMs across three levels of capability, each reflecting a more complex stage of legal .
Outcome:	The proposed benchmark identifies that LLMs lack the legal syllogism, which hinders trust and understanding from legal experts.

Copied to clipboard

Pengxiang Zhao, Hui-Ling Zhen, Xing Li, Han Bao, Weizhe Lin, Zhiyuan Yang, Yu Zi Wei, Xin Wang, Mingxuan Yuan, Xianzhi Yu, Zhenhua Dong

Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling (2025.emnlp-main)

Challenge:	Low-bit floating-point formats like MXFP and NVFP4 offer new opportunities for precision and efficiency.
Approach:	They evaluate HiFloat (HiF8 and HiF4), a family of floating-point formats tailored for Ascend NPUs.
Outcome:	The proposed formats excel with high-variance data and are compatible with state-of-the-art quantization frameworks.

Copied to clipboard

Minghui Li, Hao Zhang, Yechao Zhang, Wei Wan, Shengshan Hu, Pei Xiaobing, Jing Wang

How Do Large Language Models Perform on PDE Discovery: A Coarse-to-fine Perspective (2025.findings-emnlp)

Challenge:	Experimental results show superior cross-model transferability . Prompt injection attacks are among the most critical threats .
Approach:	They propose an activations-guided prompt injection attack framework to address the impracticality of existing white-box/gray-box methods and the poor transferability of black-box approaches.
Outcome:	The proposed framework achieves 49.6% success rate and 34.6% improvement over human-crafted prompts on five mainstream LLMs.

Copied to clipboard

Xiao Luo, Changhu Wang, Yizhou Sun, Wei Wang

FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models (2024.emnlp-demo)

Challenge:	Existing methods to identify partial differential equations using large language models suffer from performance degradation under extreme data scarcity.
Approach:	They propose a framework to use large language models to identify underlying partial differential equations out of very limited observations of a physical system.
Outcome:	The proposed framework is based on a coarse-to-fine paradigm to discover PDEs out of very limited observations of a physical system.

Copied to clipboard

Zhuohao Yu, Chang Gao, Wenjin Yao, Yidong Wang, Zhengran Zeng, Wei Ye, Jindong Wang, Yue Zhang, Shikun Zhang

DPF-CM: A Data Processing Framework with Privacy-Preserving Vector Databases for Chinese Medical LLMs Training and Deployment (2025.findings-emnlp)

Challenge:	Large language models (LLMs) have revolutionized natural language processing with impressive performance across various tasks.
Approach:	They propose a framework for automated evaluations of large language models . they open-source their code at https://github.com/WisdomShell/FreeEval .
Outcome:	The framework is open-source and can be used to develop and validate new evaluation methods.

Copied to clipboard

Wei Huang, Anda Cheng, Zhao Zhang, Yinggui Wang

Gen-SQL: Efficient Text-to-SQL By Bridging Natural Language Question And Database Schema With Pseudo-Schema (2025.coling-main)

Challenge:	a new framework for training data processing for Chinese medical language models is proposed . experimental results show that the framework significantly improves model accuracy .
Approach:	They propose a data processing framework for Chinese medical language models training and deployment . the framework is based on a question-oriented model training strategy and privacy preservation .
Outcome:	The proposed framework significantly improves model accuracy and reduces privacy leakage by 27%.

Copied to clipboard

Jie Shi, Bo Xu, Jiaqing Liang, Yanghua Xiao, Jia Chen, Chenhao Xie, Peng Wang, Wei Wang

Improving Event Definition Following For Zero-Shot Event Detection (2024.acl-long)

Challenge:	Recent studies have shifted paradigms and leveraged Large Language Models (LLMs) to tackle the challenging task of Text-to-SQL.
Approach:	They propose a framework that leverages large language models to generate SQL queries . they exploit prior knowledge from the LLM to enhance embedding-based retriever .
Outcome:	The proposed method improves embedding-based retriever and reduces cost.

Copied to clipboard

Zefan Cai, Po-Nien Kung, Ashima Suvarna, Mingyu Ma, Hritik Bansal, Baobao Chang, P. Jeffrey Brantingham, Wei Wang, Nanyun Peng

The PGNSC Benchmark: How Do We Predict Where Information Spreads? (2024.findings-acl)

Challenge:	Existing approaches on zero-shot event detection train models on datasets annotated with known event types and prompt them with unseen event definitions.
Approach:	They propose to train models to better follow event definitions by using an automatic generated Diverse Event Definition dataset.
Outcome:	The proposed model outperforms existing models on three open benchmarks on zero-shot event detection.

Copied to clipboard

Alexander Taylor, Wei Wang

Challenge:	Social networks have become ideal vehicles for news dissemination because posted content is easily able to reach users beyond a news outlet’s direct audience.
Approach:	They propose a benchmark that builds information pathways based on the audiences of influential news sources and uses their content to characterize the communities.
Outcome:	The proposed benchmark builds information pathways based on the audiences of influential news sources and uses their content to characterize the communities.

QCRD: Quality-guided Contrastive Rationale Distillation for Large Language Models (2025.emnlp-main)

Copied to clipboard

Wei Wang, Zhaowei Li, Qi Xu, YiQing Cai, Hang Song, Qi Qi, Ran Zhou, Zhida Huang, Tao Wang, Li Xiao

AraMUS: Pushing the Limits of Data and Model Scale for Arabic Natural Language Processing (2023.findings-acl)

Challenge:	Recent research has focused on smaller, task-specific models enhanced by distilling knowledge from LLMs, but the diversity and quality of negative knowledge remains understudied.
Approach:	They propose a quality-guided contrastive rationale distillation framework that aims to enhance reasoning capabilities through contrastive knowledge learning.
Outcome:	The proposed method consistently outperforms existing distillation techniques yielding higher-quality rationales.

Copied to clipboard

Asaad Alghamdi, Xinyu Duan, Wei Jiang, Zhenhai Wang, Yimeng Wu, Qingrong Xia, Zhefeng Wang, Yi Zheng, Mehdi Rezagholizadeh, Baoxing Huai, Peilun Cheng, Abbas Ghaddar

DICE: Data-Efficient Clinical Event Extraction with Generative Models (2023.acl-long)

Challenge:	Developing monolingual large Pre-trained Language Models (PLMs) is shown to be very successful in handling different tasks in Natural Language Processing (NLP).
Approach:	They present AraMUS, the largest Arabic PLM with 11B parameters trained on 529GB of high-quality Arabic textual data.
Outcome:	The proposed model achieves state-of-the-art performance on a diverse set of Arabic classification and generative tasks.

Copied to clipboard

Mingyu Derek Ma, Alexander Taylor, Wei Wang, Nanyun Peng

Towards Unified Representations of Knowledge Graph and Expert Rules for Machine Learning and Reasoning (2022.aacl-main)

Challenge:	EE tasks target specific domains with vague entity boundaries, resulting in a lack of training data.
Approach:	They propose a robust and data-efficient generative model for clinical event extraction . they frame event extraction as a conditional generation problem and introduce a contrastive learning objective to decide the boundaries of biomedical mentions.
Outcome:	The proposed model is robust and data-efficient for clinical event extraction . it trains an auxiliary mention identification task and event extraction tasks to better identify entity mention boundaries .

Copied to clipboard

Zhepei Wei, Yue Wang, Jinnan Li, Zhining Liu, Erxin Yu, Yuan Tian, Xin Wang, Yi Chang

OntoGuard: Enforcing Action Admissibility for LLM Agents in Complex Interactive Environments (2026.findings-acl)

Challenge:	Empirical study shows superiority of proposed method over time-tested knowledge-driven and data-driven methods.
Approach:	They propose a cognitive knowledge graph that unifies expert rules and relational facts as the substrate of machine learning and reasoning models.
Outcome:	Empirical results show the proposed method superior to time-tested methods . the proposed model can perform both learning and reasoning with labeled data .

Copied to clipboard

Pengxiang Liu, Tao Ren, Wei Xiong, Tingrui Yang, Junjie Wang, Jun HU

Challenge:	Existing approaches to large language models (LLMs) are limited by their ability to enforce environmental and behavioral admissibility.
Approach:	They propose an ontological framework to guard LLM agents by enforcing environmental and behavioral admissibility.
Outcome:	Experiments on ScienceWorld and VirtualHome show that OntoGuard can enforce environmental and behavioral admissibility while preventing invalid actions.

VECO: Variable and Flexible Cross-lingual Pre-training for Language Understanding and Generation (2021.acl-long)

Copied to clipboard

Fuli Luo, Wei Wang, Jiahao Liu, Yijia Liu, Bin Bi, Songfang Huang, Fei Huang, Luo Si

DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generation (2022.acl-long)

Challenge:	Existing work in multilingual pretraining relies on the shared vocabulary and bilingual contexts to encourage the correlation across languages.
Approach:	They propose to plug a cross-attention module into a Transformer encoder to explicitly build the interdependence between languages.
Outcome:	The proposed model outperforms existing models on XTREME and English-to-French translation datasets.

Copied to clipboard

Wei Chen, Yeyun Gong, Song Wang, Bolun Yao, Weizhen Qi, Zhongyu Wei, Xiaowu Hu, Bartuer Zhou, Yi Mao, Weizhu Chen, Biao Cheng, Nan Duan

Optimizing Chinese Lexical Simplification Across Word Types: A Hybrid Approach (2024.emnlp-main)

Challenge:	Existing pre-trained dialog models shed light on various downstream tasks in natural language processing (NLP).
Approach:	They propose a dialog pre-training framework that introduces latent variables into the enhanced encoder-decoder pre-train framework to increase relevance and diversity of responses.
Outcome:	The proposed model achieves state-of-the-art on personaChat, DailyDialog, and DSTC7-AVSD datasets.

Copied to clipboard

ZiHao Xiao, Jiefu Gong, Shijin Wang, Wei Song

CodeM: Less Data Yields More Versatility via Ability Matrix (2024.findings-acl)

Challenge:	Expensive large language models outperform small models in simplifying complex content words and Chinese idioms from the dictionary.
Approach:	They propose to use a retrieval-based interpretation augmentation strategy to refine small models to simplify complex content words and Chinese idioms.
Outcome:	The proposed framework outperforms large language models in Chinese Lexical Simplification (CLS) and improves on OOD models.

Copied to clipboard

Daoguang Zan, Ailun Yu, Wei Liu, Bo Shen, Shaoxin Lin, Yongshun Gong, Yafen Yao, Yan Liu, Bei Guan, Weihua Luo, Yongji Wang, Qianxiang Wang, Lizhen Cui

Challenge:	Recent efforts to train code large language models have been booming recently . however, this will incur significant costs in constructing data and training model considering the countless downstream scenarios.
Approach:	They propose a data construction strategy which decouples code LLMs’ abilities into two dimensions and constructs a lightweight training corpus that only covers a subset of target scenarios.
Outcome:	The proposed model can train a multilingual multitasking model using less data and training data.

Towards Accurate and Consistent Evaluation: A Dataset for Distantly-Supervised Relation Extraction (2020.coling-main)

Copied to clipboard

Tong Zhu, Haitao Wang, Junjie Yu, Xiabing Zhou, Wenliang Chen, Wei Zhang, Min Zhang

QuadrupletBERT: An Efficient Model For Embedding-Based Large-Scale Retrieval (2021.naacl-main)

Challenge:	Distant Supervision (DS) generates large-scale annotated data but has wrong labels that result in incorrect evaluation scores during testing.
Approach:	They build a dataset using DS-generated data as training data and hire annotators to label test data.
Outcome:	The proposed dataset NYTH has a much larger test set and performs more accurate and consistent evaluation.

Copied to clipboard

Peiyang Liu, Sen Wang, Xi Wang, Wei Ye, Shikun Zhang

InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training (2021.naacl-main)

Challenge:	Existing methods for large-scale query-document retrieval are expensive and require sparse handcrafted features.
Approach:	They propose a quadrupletBERT model for effective and efficient retrieval using pre-trained language models like BERT.
Outcome:	The proposed model improves retrieval phase and leverages distances between simple negative and hard negative instances to obtain better embeddings.

Copied to clipboard

Zewen Chi, Li Dong, Furu Wei, Nan Yang, Saksham Singhal, Wenhui Wang, Xia Song, Xian-Ling Mao, Heyan Huang, Ming Zhou

Multi-Perspective Context Aggregation for Semi-supervised Cloze-style Reading Comprehension (C18-1)

Challenge:	Existing methods for learning cross-lingual representations are lacking in the field of NLP.
Approach:	They propose a framework that formulates cross-lingual language model pre-training as maximizing mutual information between multilingual-multi-granularity texts.
Outcome:	The proposed approach improves cross-lingual transferability on benchmarks.

Copied to clipboard

Liang Wang, Sujian Li, Wei Zhao, Kewei Shen, Meng Sun, Ruoyu Jia, Jingming Liu

AdapThink: Adaptive Thinking Preferences for Reasoning Language Models (2026.findings-acl)

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.

Copied to clipboard

Wenyue Xu, Xu Wan, Wei Wang, Wenqi Huang, Wotao Yin, Shengjie Zhao, Mingyang Sun

Memory-augmented Query Reconstruction for LLM-based Knowledge Graph Reasoning (2025.findings-acl)

Challenge:	Recent research has highlighted a significant inefficiency associated with the slow thinking paradigm . models often overthink simple tasks while underthinking complex challenges .
Approach:	They propose a framework for adaptive reasoning preference control that dynamically adjusts reflection preferences based on group-level distributional statistics of reasoning length and reflection intensity.
Outcome:	The proposed framework reduces average response length by 17.1%-21.4% while improving performance by 6.12-6.59 points under 32K token budgets.

Copied to clipboard

Mufan Xu, Gewen Liang, Kehai Chen, Wei Wang, Xun Zhou, Muyun Yang, Tiejun Zhao, Min Zhang

Mobile-R1: Towards Interactive Capability for VLM-Based Mobile Agent via Systematic Training (2026.acl-long)

Challenge:	Existing methods that confuse tool utilization with knowledge reasoning harm readability and give rise to tool invocation hallucinations.
Approach:	They propose to decouple LLM from tool invocation tasks by establishing a memory module with explicit descriptions of query statements and a query memory module to facilitate the KGQA process.
Outcome:	The proposed method achieves state-of-the-art on WebQSP and CWQ benchmarks.

Copied to clipboard

Jihao Gu, Qihang Ai, Yingyao Wang, Pi Bu, Jingxuan Xing, Yue Cao, Zekun Zhu, Wei Jiang, Ziming Wang, Yingxiu Zhao, Ming-Liang Zhang, Jun Song, Yuning Jiang, Bo Zheng

Imitation Learning for Non-Autoregressive Neural Machine Translation (P19-1)

Challenge:	Existing approaches to training agents for visual-language models trap them in local optima, hindering exploration and error correction with the environment.
Approach:	They propose a hierarchical training recipe that bridges atomic action execution and strategic task completion.
Outcome:	The proposed training recipe bridges atomic action execution and strategic task completion.

Copied to clipboard

Bingzhen Wei, Mingxuan Wang, Hao Zhou, Junyang Lin, Xu Sun

OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval (2025.acl-long)

Challenge:	Existing non-autoregressive translation models lack parallel decoding, which is a bottleneck for NMT decoding.
Approach:	They propose a framework for non-autoregressive machine translation that emulates the autoregressive model by sampling sentence length in parallel.
Outcome:	The proposed model achieves 31.85 BLEU on WMT16 RoEn and 30.68 BLUE on IWSLT16 EnDe on the IWSLD16, WMT14 and WMT15 datasets.

Copied to clipboard

Wei Yang, Jingjing Fu, Rui Wang, Jinyu Wang, Lei Song, Jiang Bian

FuseSearch: Learning Adaptive Parallel Execution for Efficient Code Localization (2026.findings-acl)

Challenge:	Existing methods for Knowledge-Based Visual Question Answering lack multimodal retrieval . large language models (LLMs) have demonstrated remarkable generalization and reasoning capabilities in text-based systems.
Approach:	They propose a multimodal vision-language retrieval-augmented generation system that harmonizes multiple modalities and modality to enhance retrieval.
Outcome:	The proposed system achieves state-of-the-art retrieval performance and competitive answers on InfoSeek and Encyclopedic-VQA benchmarks.

Copied to clipboard

Ke Xu, Siyang Xiao, Ming Liang, Yichen Yu, Zhixiang Wang, Jingxuan Xu, Dajun Chen, Wei Jiang, Yong Li

Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings (2025.findings-acl)

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.

Copied to clipboard

Yuanhe Zhang, Zhenhong Zhou, Wei Zhang, Xinyue Wang, Xiaojun Jia, Yang Liu, Sen Su

TANet: Thread-Aware Pretraining for Abstractive Conversational Summarization (2022.findings-naacl)

Challenge:	Existing studies on white-box attacks focus on black-box LLMs, leaving black- box scenarios underexplored.
Approach:	They propose an automated algorithm designed for black-box LLMs that constructs the DoS Attack Tree and expands the node coverage to achieve effectiveness under black- box conditions.
Outcome:	The proposed algorithm can be used to build a DoS Attack Tree and expand the node coverage to achieve effectiveness under black-box conditions.

Copied to clipboard

Ze Yang, Christian Wang, Zhoujin Tian, Wei Wu, Zhoujun Li

IntelliCockpitBench: A Comprehensive Benchmark to Evaluate VLMs for Intelligent Cockpit (2025.findings-acl)

Challenge:	Existing pre-trained language models are difficult to apply to abstractive conversational summarization tasks.
Approach:	They propose a thread-aware Transformer-based network that incorporates contextual dependency into the conversational summarization model.
Outcome:	The proposed model can be applied to real conversations using a large-scale pretraining dataset.

Copied to clipboard

Liang Lin, Siyuan Chai, Jiahao Wu, Hongbing Hu, Xiaotao Gu, Hao Hu, Fan Zhang, Wei Wang, Dan Zhang

Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models (2025.emnlp-main)

Challenge:	Visual Question Answering (VQA) is a key task in vehicular systems.
Approach:	They propose a benchmark that encompasses diverse automotive scenarios . they use images from front, side, and rear cameras, various road types, weather conditions, and interior views .
Outcome:	The proposed benchmark includes images from front, side, and rear cameras, various road types, weather conditions, and interior views.

Copied to clipboard

Pu Jian, Junhong Wu, Wei Sun, Chen Wang, Shuo Ren, Jiajun Zhang