Papers by Yang Cao

A Dialogue-based Information Extraction System for Medical Insurance Assessment (2021.findings-acl)

Challenge:	Large Language Models (LLMs) suffer from huge number of parameters, which restricts their deployment on edge devices.
Approach:	They propose two methods that share parameters across attention heads to reduce memory usage and reduce performance drop by using coarse-grained weight sharing rules.
Outcome:	The proposed methods reuse pre-trained weights without retraining and then share, denoted as PostShare.

Copied to clipboard

Shuang Peng, Mengdi Zhou, Minghui Yang, Haitao Mi, Shaosheng Cao, Zujie Wen, Teng Xu, Hongbin Wang, Lei Liu

Beyond the Final Actor: Modeling the Dual Roles of Creator and Editor for Fine-Grained LLM-Generated Text Detection (2026.acl-long)

Challenge:	a new system that integrates advanced NLP technologies for medical insurance assessment is proposed . the average time cost of the procedure is reduced from 55 minutes to 35 minutes .
Approach:	They propose a dialogue-based information extraction system that integrates advanced NLP technologies for medical insurance assessment.
Outcome:	The proposed system reduces the time cost of the procedure from 55 minutes to 35 minutes and saves 30% human resources cost compared with the previous offline procedure.

Copied to clipboard

Yang Li, Qiang Sheng, Zhengjia Wang, Yehan Yang, Danding Wang, Juan Cao

Text Generation

Challenge:	Existing methods to detect large language models (LLMs) use binary or ternary classifications, which can only distinguish pure human/LLM text or collaborative text at best.
Approach:	They propose a fine-grained method that characterizes distinct signatures of creator and editor by using Rhetorical Structure Theory to construct a logic graph for creator's foundation and extracting Elementary Discourse Unit (EDU)-level features for the editor's style.
Outcome:	The proposed method outperforms 12 baselines in identifying fine-grained types with low false alarms, offering a policy-aligned solution for LLM regulation.

VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models (2024.emnlp-main)

Copied to clipboard

Yifei Liu, Jicheng Wen, Yang Wang, Shengyu Ye, Li Lyna Zhang, Ting Cao, Cheng Li, Mao Yang

TURING: an Accurate and Interpretable Multi-Hypothesis Cross-Domain Natural Language Database Interface (2021.acl-demo)

Challenge:	Recent research has focused on pushing weight-only quantization to extremely low-bit due to numerical representation limitations.
Approach:	They propose a vector-based quantization approach that pushes LLMs to extremely low-bit . they propose scalar-based weight quantization that reduces memory requirements and optimizes storage costs .
Outcome:	The proposed method reduces model quantization perplexity by 0.01-0.34 on LLaMA-2, 0.38-0.68 on mistral-7B, 4.41-7.34, on llaMA-3 on QA tasks on average.

Copied to clipboard

Peng Xu, Wenjie Zi, Hamidreza Shahidi, Ákos Kádár, Keyi Tang, Wei Yang, Jawad Ateeq, Harsh Barot, Meidan Alon, Yanshuai Cao

GGP: Glossary Guided Post-processing for Word Embedding Learning (2020.lrec-1)

Challenge:	Existing text-to-SQL semantic parsers cannot achieve high accuracy in cross-database setting . TURING is a NLDB system that can be used to democratize data-driven insights for non-technical users .
Approach:	They propose a TURING system that provides high-precision natural language explanations of SQL queries in a beam.
Outcome:	The proposed system achieves 75.1% execution accuracy and 78.3% top-5 beam execution accuracy on the Spider validation set.

Copied to clipboard

Ruosong Yang, Jiannong Cao, Zhiyuan Wen

Representation Learning

Challenge:	Existing word embedding models require much training time and domain knowledge to improve.
Approach:	They propose a GGP-based word embedding model that incorporates the glossary and learns sense representations.
Outcome:	The proposed model outperforms existing models on topical/functional similarity datasets by 4.1% and 7%.

Unified Thinker: A General Reasoning Core for Image Generation (2026.acl-long)

Copied to clipboard

Sashuai Zhou, Qiang Zhou, Jijin Hu, Hanqing Yang, Yue Cao, Junpeng Ma, Yinchao Ma, Jun Song, Tiezheng Ge, Cheng Yu, Bo Zheng, Zhou Zhao

Gaussian Process based Deep Dyna-Q approach for Dialogue Policy Learning (2021.findings-acl)

Challenge:	generative models struggle with logic-intensive instruction following, exposing a persistent reasoning–execution gap.
Approach:	They propose a task-agnostic reasoning architecture for general image generation . they propose pixel-level feedback to ground the Thinker's policy in pixel feedback .
Outcome:	The proposed system significantly improves image reasoning and generation quality.

Copied to clipboard

Guanlin Wu, Wenqi Fang, Ji Wang, Jiang Cao, Weidong Bao, Yang Ping, Xiaomin Zhu, Zheng Wang

Optimizing Deeper Transformers on Small Datasets (2021.acl-long)

Challenge:	Reinforcement learning (RL) is the main dialogue policy learning method in recent years.
Approach:	They propose a Gaussian Process based Deep Dyna-Q approach to dialogue policy learning . they propose evaluating the quality of experiences generated by the world model using a discriminator .
Outcome:	The proposed approach improves the effectiveness and efficiency of dialogue policy learning by 20% with fewer human-machine interactions.

Copied to clipboard

Peng Xu, Dhruv Kumar, Wei Yang, Wenjie Zi, Keyi Tang, Chenyang Huang, Jackie Chi Kit Cheung, Simon J.D. Prince, Yanshuai Cao

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

Challenge:	a common belief that training deep transformers from scratch requires large datasets is wrong . however, with proper initialization and optimization, the benefits of very deep transformer can carry over to challenging tasks with small datasets.
Approach:	They train 48 layers of transformers from pre-trained RoBERTa and 24 relation-aware layers from scratch.
Outcome:	The proposed scheme achieves state-of-the-art performance on a text-to-sql parsing benchmark . it uses 24 fine-tuned layers from pre-trained RoBERTa and 24 relation-aware layers from scratch .

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

RippleCOT: Amplifying Ripple Effect of Knowledge Editing in Language Models via Chain-of-Thought In-Context Learning (2024.findings-emnlp)

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

Zihao Zhao, Yuchen Yang, Yijiang Li, Yinzhi Cao

SPORTSINTERVIEW: A Large-Scale Sports Interview Benchmark for Entity-centric Dialogues (2022.lrec-1)

Challenge:	et al., 2022: ripple effect challenges knowledge editing for large language models.
Approach:	They propose a method to improve the accuracy of large language models by integrating Chain-of-Thought reasoning into the ICL editing approach.
Outcome:	RIPPLE-COT outperforms the state-of-the-art on the ripple effect, with gains ranging from 7.8% to 87.1%.

Copied to clipboard

Hanfei Sun, Ziyuan Cao, Diyi Yang

Natural Language Interfaces

Challenge:	Existing knowledge grounded dialogue datasets only contain external knowledge from one dimension, which limits the diversity of knowledge sources and may contain unwanted bias.
Approach:	They propose to use two types of external knowledge sources as knowledge grounding in an interview dataset to model human dialogues.
Outcome:	The proposed dataset contains 150K interviews and 34K interviewees . it is larger in size and has more than one dimension of external knowledge linking . however, the performance of the proposed models is far from humans .

An Empirical Study of Frame Selection for Text-to-Video Retrieval (2023.findings-emnlp)

Copied to clipboard

Mengxia Wu, Min Cao, Yang Bai, Ziyin Zeng, Chen Chen, Liqiang Nie, Min Zhang

Uncovering Limitations of Large Language Models in Information Seeking from Tables (2024.findings-acl)

Challenge:	Existing methods for text-to-video retrieval select a subset of frames to represent video content . current methods only explore video contents while ignoring relevancy to texts .
Approach:	They propose to use a subset of frames to represent video content for TVR . they analyze six different frame selection methods to determine their effectiveness .
Outcome:	The proposed method improves retrieval efficiency without sacrificing visual details . the proposed method explores the video contents while ignoring relevancy to texts .

Copied to clipboard

Chaoxu Pang, Yixuan Cao, Chunhao Yang, Ping Luo

Toxicity Detection is NOT all you Need: Measuring the Gaps to Supporting Volunteer Content Moderators through a User-Centric Method (2024.emnlp-main)

Challenge:	Existing benchmarks for Table Information Seeking (TabIS) are lacking in reliable evaluation.
Approach:	They propose a benchmark to evaluate the table information seeking abilities of large language models . they use a single-choice question format instead of a text-based evaluation .
Outcome:	The proposed benchmark is more reliable than existing models and is available online.

Copied to clipboard

Yang Cao, Lovely-Frances Domingo, Sarah Gilbert, Michelle Mazurek, Katie Shilton, Hal Daumé Iii

FFN Lens: How Transformers Divide Labor for Multilingual Tasks (2026.findings-acl)

Challenge:	Existing efforts to automate content moderation have focused on identifying toxic, offensive, and hateful content . yet, it remains unclear whether improvements have addressed the needs of volunteer content moderators .
Approach:	They propose to use a model review to examine the availability of moderators' models to flag violations of various forum rules.
Outcome:	The proposed models perform poorly on a significant portion of the rules.

Copied to clipboard

Jiatong Li, Hailong Cao, Yang Liu

Beyond Memorization: A Rigorous Evaluation Framework for Medical Knowledge Editing (2026.eacl-long)

Challenge:	Large Language Models (LLMs) exhibit strong performance on multilingual tasks, yet the process of constructing predictions in the target language remains under-explored.
Approach:	They propose a novel interpretability method focusing on the Feed-Forward Network (FFN) layers of Large Language Models.
Outcome:	The proposed interpretability method is based on the Feed-Forward Network (FFN) layer of Large Language Models.

Copied to clipboard

Shigeng Chen, Linhao Luo, Zhangchi Qiu, Yanan Cao, Carl Yang, Shirui Pan

Challenge:	Existing knowledge editing methods show promising results on general-domain benchmarks, but their effectiveness in the medical domain remains largely unexplored.
Approach:	They propose a framework to evaluate medical knowledge editing using model-generated rationales as editing targets.
Outcome:	The proposed method improves editing efficacy and generalization in medical models without full retraining.

Unsupervised Dual Paraphrasing for Two-stage Semantic Parsing (2020.acl-main)

Copied to clipboard

Ruisheng Cao, Su Zhu, Chenyu Yang, Chen Liu, Rao Ma, Yanbin Zhao, Lu Chen, Kai Yu

Uncertain Local-to-Global Networks for Document-Level Event Factuality Identification (2021.emnlp-main)

Challenge:	Existing semantic parsing frameworks rely on nontrivial human labor to generate canonical utterances.
Approach:	They propose a framework that uses an unsupervised paraphrase model to parse canonical utterances.
Outcome:	The proposed framework is effective and compatible with supervised training.

Copied to clipboard

Pengfei Cao, Yubo Chen, Yuqing Yang, Kang Liu, Jun Zhao

Challenge:	Existing studies focus on identifying event factuality at sentence level, which leads to conflicts between different mentions of the same event.
Approach:	They propose a document-level event factuality identification model that uses local uncertainty and global structure to model event factuality.
Outcome:	The proposed method outperforms existing models on two widely used datasets.

Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving (2025.emnlp-main)

Copied to clipboard

Chuxue Cao, Mengze Li, Juntao Dai, Jinluan Yang, Zijian Zhao, Shengyu Zhang, Weijie Shi, Chengzhong Liu, Sirui Han, Yike Guo

IW-Bench: Evaluating Large Multimodal Models for Converting Image-to-Web (2025.findings-acl)

Challenge:	Large language models (LLMs) have shown promising first-order logic (FOL) reasoning capabilities with applications in various areas, but their effectiveness in complex mathematical reasoning involving multi-step FOL deductions remains under-explored.
Approach:	They propose a self-adaptive solution that enhances the Diversity and REAsonability of LLMs’ generation strategies by introducing an Axiom-Driven Strategy Diversification mechanism and a Sub-Proposition Error Feedback to help LLM reflect on and correct their proofs.
Outcome:	The proposed model improves diversity and REAsonability of LLMs’ generation strategies by introducing an Axiom-Driven Strategy Diversification mechanism and a Sub-Proposition Error Feedback to help LLM reflect on and correct proofs.

Copied to clipboard

Hongcheng Guo, Wei Zhang, Junhao Chen, Yaonan Gu, Jian Yang, Junjia Du, Shaosheng Cao, Binyuan Hui, Tianyu Liu, Jianxin Ma, Chang Zhou, Zhoujun Li

A Chain-of-Task Framework for Instruction Tuning of LLMs Based on Chinese Grammatical Error Correction (2025.coling-main)

Challenge:	Existing models have been introduced to improve image comprehension, but there is no robust benchmark for imagetoweb conversion.
Approach:	They propose a benchmark to assess imagetoweb conversion proficiency of large multimodal models . they propose to measure layout information of web pages by parsing the Document Object Model tree .
Outcome:	The proposed benchmark measures the layout information of web pages—i.e., the positional relationships between elements—which has been overlooked by prior work.

Copied to clipboard

Xinpeng Liu, Bing Xu, Muyun Yang, Hailong Cao, Conghui Zhu, Tiejun Zhao, Wenpeng Lu

Unveiling Project-Specific Bias in Neural Code Models (2024.lrec-main)

Challenge:	Existing approaches to address Grammatical Error Correction (GEC) tasks are based on large scale labeled data, which leads to extremely high data annotation costs.
Approach:	They propose a Chain-of-Task framework to reduce over-correction in large language models . they propose supervised fine-tuning strategy and an algorithm for automatic dataset annotation .
Outcome:	The proposed framework achieves state-of-the-art on both FCGEC (in-domain) and NaCGEC (out-of domain) test sets.

Copied to clipboard

Zhiming Li, Yanzhou Li, Tianlin Li, Mengnan Du, Bozhi Wu, Yushi Cao, Junzhe Jiang, Yang Liu

Long Text and Multi-Table Summarization: Dataset and Method (2022.findings-emnlp)

Challenge:	Large Language Models (LLMs) based neural code models struggle to generalize effectively to real-world inter-project out-of-distribution data.
Approach:	They propose a Cond-Idf measurement to measure the relatedness of a token with a label and its project-specificness.
Outcome:	The proposed framework improves both inter-project OOD generalization and adversarial robustness while not sacrificing accuracy on intra-project IID data.

Copied to clipboard

Shuaiqi Liu, Jiannong Cao, Ruosong Yang, Zhiyuan Wen

MAIN: Mutual Alignment Is Necessary for instruction tuning (2025.emnlp-main)

Challenge:	Existing document summarization methods focus on the text and filter out the non-textual content. Existing methods cannot meet the requirements of summarizing long text and multiple tables in each report.
Approach:	They propose a dataset for automatic document summarization that uses text and tabular data to produce a concise summary covering the input document's salient information.
Outcome:	The proposed method can produce a concise summary covering the input document's salient information.

Copied to clipboard

Fanyi Yang, Jianfeng Liu, Xin Zhang, Haoyu Liu, Xixin Cao, Yuefeng Zhan, Hao Sun, Weiwei Deng, Feng Sun, Qi Zhang

Mitigating Lost in Multi-turn Conversation via Curriculum RL with Verifiable Accuracy and Abstention Rewards (2026.acl-long)

Challenge:	Instruction tuning has enabled large language models to achieve remarkable performance, yet its success heavily depends on the availability of high-quality instruction-response pairs.
Approach:	They propose a mutual alignment framework which enforces coherence between instructions and responses through mutual constraints.
Outcome:	The proposed framework generalizes well across model architectures and sizes, achieving state-of-the-art performance on LLaMA, Mistral, and Qwen models across diverse benchmarks.

Copied to clipboard

Ming Li, Pei Chen, Zhenhao Zhang, Tao Yang, Xinyang Zhang, Han Li, Tianyu Cao, Ming Zeng, Zhuofeng Wu, Meng Jiang, Huasheng Li, Lihong Li, Bing Yin

Enhancing Automated Essay Scoring Performance via Fine-tuning Pre-trained Language Models with Combination of Regression and Ranking (2020.findings-emnlp)

Challenge:	Large Language Models exhibit strong capabilities in single-turn instruction following but suffer from Lost-in-Conversation (LiC) when instructions are revealed progressively in multi-turn settings, models get "Lost in Conversation"
Approach:	They propose a framework that encourages models to generate correct answers and judge solvability in multi-turn conversations.
Outcome:	The proposed framework improves models' ability to balance problem-solving with abstention . it reduces premature answering behaviors that cause lost-in-conversation (LiC)

Copied to clipboard

Ruosong Yang, Jiannong Cao, Zhiyuan Wen, Youzheng Wu, Xiaodong He

RAG or Learning? Understanding the Limits of LLM Adaptation under Continuous Knowledge Drift in the Real World (2026.findings-acl)

Challenge:	Recent work on sentence prediction tasks uses shallow neural networks to learn essay representations and constrain calculated scores with regression loss or ranking loss.
Approach:	They propose to use a pre-trained language model to learn text representations first and then to constrain the scores with regression loss or ranking loss.
Outcome:	The proposed model outperforms state-of-the-art models on the Automated Student Assessment Prize dataset.

Copied to clipboard

Hanbing Liu, Lang Cao, Yang Li

Information Retrieval

Challenge:	Existing methods to update or supplement large language models struggle under continuous knowledge drift.
Approach:	They propose a dynamic event benchmark and time-aware retrieval baseline that captures how knowledge evolves over time.
Outcome:	The proposed method enables systematic evaluation of model adaptation under continuous knowledge drift.

Incomplete In-context Learning (2026.acl-long)

Copied to clipboard

Wenqiang Wang, Wen Yujia, Yan Xiao, Zhifeng Chen, Yangshijie Zhang, Peng Chen, Mingbo Yang, Xiaochun Cao

The Mirage of Model Editing: Revisiting Evaluation in the Wild (2025.acl-long)

Challenge:	Existing in-context learning assumes the retrieval dataset contains demonstrations for all output label spaces.
Approach:	They propose a framework with train-free and train-based variants to address IICL . they propose to integrate a dataset with labeled demonstrations for each output space .
Outcome:	The proposed framework outperforms existing methods under incomplete retrieval datasets and even outperformed ICL with complete labels.

Copied to clipboard

Wanli Yang, Fei Sun, Jiajun Tan, Xinyu Ma, Qi Cao, Dawei Yin, Huawei Shen, Xueqi Cheng

Question Answering

Challenge:	despite near-perfect results, effectiveness of model editing in real-world applications remains unclear.
Approach:	They propose QAEdit and WILD to better reflect real-world use of model editing . they propose a benchmark aligned with widely used question answering datasets and a task-agnostic evaluation framework .
Outcome:	The proposed QAEdit benchmark and WILD evaluation framework show that current models perform worse than previously reported.

FreeChunker: A Cross-Granularity Chunking Framework (2026.findings-acl)

Copied to clipboard

Zhang Wenxuan, Yuan-Hao Jiang, Yang Cao, Yonghe Wu

Syntactic Text Processing

Challenge:	Existing chunking paradigms rely on static boundary identification, limiting performance . Existing methods rely only on static knowledge, resulting in hallucinated content .
Approach:	They propose a Cross-Granularity Encoding Framework that treats sentences as atomic units and shifts from static chunk segmentation to flexible retrieval supporting arbitrary sentence combinations.
Outcome:	The proposed framework avoids the computational overhead required for semantic boundary detection and enhances adaptability to complex queries.

TongGu: Mastering Classical Chinese Understanding with Knowledge-Grounded Large Language Models (2024.findings-emnlp)

Copied to clipboard

Jiahuan Cao, Dezhi Peng, Peirong Zhang, Yongxin Shi, Yang Liu, Kai Ding, Lianwen Jin

Interactive Learning for LLM Reasoning (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have demonstrated remarkable capability in Natural Language Processing (NLP), but struggle with Classical Chinese Understanding (CCU) Existing models, including general-purpose and preliminary LLMs, lack the ability to address CCU in data-demanding and knowledge-intensive tasks.
Approach:	They propose to use a classical Chinese corpora-based instruction-tuning dataset to unlock the full CCU potential of LLMs.
Outcome:	The proposed model unlocks the full CCU potential of LLMs by preserving its foundational knowledge while maintaining redundancy-aware tuning (RAT) and CCU-RAG.

Copied to clipboard

Hehai Lin, Shilei Cao, Sudong Wang, Haotian Wu, Minzhi Li, Linyi Yang, Juepeng Zheng, Chengwei Qin

RankPrompt: Step-by-Step Comparisons Make Language Models Better Reasoners (2024.lrec-main)

Challenge:	Existing multi-agent learning approaches foster collaboration among Large Language Models (LLMs) yet they still rely on re-executing the MAS during inference.
Approach:	They propose a co-learning framework that integrates Dynamic Interaction and Perception Calibration to enhance LLMs' independent problem-solving ability.
Outcome:	The proposed framework integrates Dynamic Interaction and Perception Calibration to improve LLMs' independent problem-solving ability.

Copied to clipboard

Chi Hu, Yuan Ge, Xiangnan Ma, Hang Cao, Qiang Li, Yonghua Yang, Tong Xiao, Jingbo Zhu

Putting Captions to the Test: Evaluating Video Caption Quality through Multiple-Choice Question Answering (2026.acl-long)

Challenge:	Existing solutions to reasoning tasks require extensive human annotations or fail in scenarios with inconsistent responses.
Approach:	They propose a new method that enables LLMs to self-rank their responses without additional resources.
Outcome:	The proposed method improves reasoning performance of ChatGPT and GPT-4 with 13% improvement over existing methods.

Copied to clipboard

Zizhen Wang, Bo Feng, Zhengfeng Lai, Shiyu Li, Yang Lu, Meng Cao, Ping Huang, Xiaoming Simon Wang

Rethinking Depression Prediction from a Fine-Grained Subscore Modeling Perspective via Multi-Task Learning (2026.acl-long)

Challenge:	Existing metrics for video captioning are based on text-based comparisons with ground-truth references.
Approach:	They propose a reference-free benchmark that assesses video captions based on their utility . they will release the benchmark to facilitate reproducible research .
Outcome:	The proposed benchmark improves on human-verified, fine-grained questions . it correlates significantly better with human judgments than existing metrics .

Copied to clipboard

Zhenguang Wang, Bo Li, Wenhui Tan, Peng Cao, Yang Wang, Jia Duan, Fei Wang, Osmar Zaiane

PGPO: Enhancing Agent Reasoning via Pseudocode-style Planning Guided Preference Optimization (2025.findings-acl)

Challenge:	Existing methods for depression assessment rely on standardized ratings, but they are time-consuming and subject to inter-rater variability.
Approach:	They propose a fine-grained model for subscore prediction via multi-task learning that can be used to predict depression severity using multiple tasks.
Outcome:	The proposed model outperforms baselines and Qwen3-14B direct scoring on the public E-DAIC dataset and to a large-scale private clinical dataset.

Copied to clipboard

Zouying Cao, Runze Wang, Yifei Yang, Xinbei Ma, Xiaoyong Zhu, Bo Zheng, Hai Zhao

ParaCook: On Time-Efficient Planning for Multi-Agent Systems (2026.findings-acl)

Challenge:	Existing LLM agents generate verbose and inefficient natural language plans to guide reasoning, which restricts agents’ ability to generalize across similar tasks.
Approach:	They propose a pseudocode-style planning guide optimization method that captures the structural logic of reasoning and uses two planning-oriented rewards to enhance agent learning.
Outcome:	The proposed method outperforms existing LLM agents on representative agent benchmarks and outperformed the current leading baselines.

Copied to clipboard

Shiqi Zhang, Xinbei Ma, Yunqing Xu, Zouying Cao, Pengrui Lu, Haobo Yuan, Tiancheng Shen, Zhuosheng Zhang, Hai Zhao, Ming-Hsuan Yang

Green & Sustainable NLP

Challenge:	Existing agent benchmarks focus on task completion while neglecting time efficiency in parallel and asynchronous operations.
Approach:	They propose a framework for large language models that allows agents to plan long-horizon tasks in a scalable way.
Outcome:	The proposed framework is based on the Overcooked game and can be used to evaluate time efficiency-aware multi-agent planning.

Multi-Programming Language Sandbox for LLMs (2025.acl-demo)

Copied to clipboard

Shihan Dou, Jiazheng Zhang, Jianxiang Zang, Yunbo Tao, Weikang Zhou, Haoxiang Jia, Shichun Liu, Yuming Yang, Shenxi Wu, Zhiheng Xi, Muling Wu, Rui Zheng, Changze Lv, Limao Xiong, Shaoqing Zhang, Lin Zhang, Wenyu Zhan, Rongxiang Weng, Jingang Wang, Xunliang Cai, Yueming Wu, Ming Wen, Yixin Cao, Tao Gui, Xipeng Qiu, Qi Zhang, Xuanjing Huang

LaCo: Large Language Model Pruning via Layer Collapse (2024.findings-emnlp)

Challenge:	MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for Large Language Models (LLMs).
Approach:	They propose a multi-programming language sandbox that provides unified feedback from compilers and analysis tools for Large Language Models.
Outcome:	The proposed multi-language sandbox can provide comprehensive feedback from compilers and analysis tools for large language models (LLMs).

Copied to clipboard

Yifei Yang, Zouying Cao, Hai Zhao

STAR: SQL Guided Pre-Training for Context-dependent Text-to-SQL Parsing (2022.findings-emnlp)

Challenge:	Existing methods for model quantization, knowledge distillation, and model pruning are limited by hardware support limitations and the need for extensive training.
Approach:	They propose a layer-wise structured pruner that collapses rear model layers into a prior layer and enables a rapid reduction in model size while preserving the model structure.
Outcome:	The proposed pruner outperforms state-of-the-art pruning methods at pruning ratios of 25-30% and maintains an average task performance of over 80% at different pruning ratio.

Copied to clipboard

Zefeng Cai, Xiangyu Li, Binyuan Hui, Min Yang, Bowen Li, Binhua Li, Zheng Cao, Weijie Li, Fei Huang, Luo Si, Yongbin Li

Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgments (2026.acl-long)

Challenge:	Extensive experiments show that STAR outperforms previous pre-training methods and ranks first on the leaderboard . text-to-SQL parsing aims to translate natural language (NL) questions into executable SQL queries .
Approach:	They propose a SQL guided pre-training framework STAR for context-dependent text-to-SQL parsing . they propose two objectives that explore context-dependence of NL utterances and SQL queries .
Outcome:	The proposed framework outperforms existing methods on two downstream benchmarks and ranks first on the leaderboard.

Copied to clipboard

Hao Mi, Qiang Sheng, Shaofei Wang, Beizhe Hu, Yifan Sun, Zhengjia Wang, Hengqi Zeng, Yang Li, Danding Wang, Juan Cao

APPSI-139: A Parallel Corpus of English Application Privacy Policy Summarization and Interpretation (2026.acl-long)

Challenge:	Existing methods for hallucination detection focus on implicit neural uncertainty or explicit symbolic reasoning, ignoring factual hallucinosities.
Approach:	They propose a framework that bridges neural features and symbolic judgments for hallucination detection by leveraging a "meta-judgment" process to map symbolic labels back into the feature space.
Outcome:	Extensive experiments on 4 public datasets, across 4 LLMs, against 8 baselines demonstrate the superiority of LaaB.

Copied to clipboard

Pengyun Zhu, Qiheng Sun, Long Wen, Yanbo Wang, Yang Cao, Junxu Liu, Deyi Xiong, Jinfei Liu, Zhibo Wang, Kui Ren

Decode with Template: Content Preserving Sentiment Transfer (2020.lrec-1)

Challenge:	a lack of high-quality English privacy policy corpus optimized for legal clarity and readability is limiting translation of privacy policies . 139 privacy policies are often considered "incomprehensible" due to technical jargon, legal language, and convoluted grammatical structures.
Approach:	They propose a high-quality English privacy policy corpus annotated by domain experts . they propose APPSI-139 to summarize and interpret privacy policies in English .
Outcome:	The proposed framework outperforms large language models in terms of readability and accuracy.

Copied to clipboard

Zhiyuan Wen, Jiannong Cao, Ruosong Yang, Senzhang Wang

Sentiment Analysis

Challenge:	Existing methods to transfer sentiments for text use only explicit sentiments and templates to remove them from input sentences.
Approach:	They propose a method to transfer sentiments from input sentences to output sentences using templates.
Outcome:	The proposed model significantly outperforms state-of-the-art models in content preservation.

DocAgent: A Multi-Agent System for Automated Code Documentation Generation (2025.acl-demo)

Copied to clipboard

Dayu Yang, Antoine Simoulin, Xin Qian, Xiaoyi Liu, Yuwei Cao, Zhaopu Teng, Grey Yang

Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game (2024.findings-acl)

Challenge:	Existing methods for generating documentation using Large Language Models (LLMs) produce incomplete, unhelpful, or factually incorrect outputs.
Approach:	They propose a novel collaborative system that uses topological code processing for incremental context building to generate documentation by agents.
Outcome:	The proposed system outperforms baselines in completeness, helpfulness, and truthfulness evaluations.

Copied to clipboard

Pengyu Cheng, Yifan Yang, Jian Li, Yong Dai, Tianhao Hu, Peixin Cao, Nan Du, Xiaolong Li

Automatically Select Emotion for Response via Personality-affected Emotion Transition (2021.findings-acl)

Challenge:	Existing methods for training large language models require additional annotations to adjust to shifted distributions.
Approach:	They propose an algorithm that allows LLMs and reward models to update alternatively via a min-max game to improve their alignment.
Outcome:	The proposed framework improves existing alignment baselines in terms of LLM helpfulness and harmlessness.

Copied to clipboard

Zhiyuan Wen, Jiannong Cao, Ruosong Yang, Shuaiqi Liu, Jiaxing Shen

Privacy Risks of Intermediate Representations: Attribute Inference in Distributed LLM Inference (2026.findings-acl)

Challenge:	Existing studies focus on rendering specified emotions in responses, yet the individual difference in emotion expression is overlooked.
Approach:	They propose to equip a dialog system with personality and enable it to select emotions in responses like humans.
Outcome:	The proposed system can select emotions in responses like humans by simulating the emotion transition of humans in conversation.

Copied to clipboard

Yang Lyu, Jin Cao, Yang Xiao, Zhe Sun, Ben Niu, Fenghua Li, Hui LI

LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning (2025.acl-long)

Challenge:	Distributed LLMs avoid raw inputs by transmitting intermediate hidden states, a practice widely assumed to preserve privacy.
Approach:	They propose a distributed inference framework that transmits intermediate hidden states to avoid sending raw inputs by exposing sensitive user attributes.
Outcome:	The proposed approach achieves Top-1 accuracy of 0.997 on CMS, 0.980 on Skytrax, and 0.986 on ECHR.

Copied to clipboard

Jin Jiang, Yuchen Yan, Yang Liu, Jianing Wang, Shuai Peng, Xunliang Cai, Yixin Cao, Mengdi Zhang, Liangcai Gao

Mulan: A Multi-Level Alignment Model for Video Question Answering (2023.findings-emnlp)

Challenge:	LogicPro is a data synthesis method that uses LeetCode-style algorithm problems and their corresponding Program solutions to generate complex logic data.
Approach:	They propose a new method which leverages LeetCode-style algorithm Problems and their corresponding Program solutions to synthesize complex logic data in text format.
Outcome:	The proposed method outperforms existing models for BBH27, LogicBench, DROP, AR-LSAT, and GSM8K, and a wide range of reasoning datasets.

Copied to clipboard

Yu Fu, Cong Cao, Yuling Yang, Yuhai Lu, Fangfang Yuan, Dakui Wang, Yanbing Liu

Visual Data in NLP

Challenge:	Existing methods focus on visual-language alignment at the video level, but they do not account for fine-grained semantic interaction between video and text.
Approach:	They propose a multi-level Alignment Model for Video Question Answering that establishes alignment between visual and textual modalities at the object-level, frame-level and video-level.
Outcome:	The proposed model outperforms state-of-the-art methods even with a small amount of extra visual-language pre-training data and a reduced number of trainable parameters.

TOOL-ED: Enhancing Empathetic Response Generation with the Tool Calling Capability of LLM (2025.coling-main)

Copied to clipboard

Huiying Cao, Yiqun Zhang, Shi Feng, Xiaocui Yang, Daling Wang, Yifei Zhang

Text Generation

Challenge:	Empathetic conversation is a crucial characteristic in daily conversations between individuals.
Approach:	They propose an Emotional Knowledge Tool Calling framework which encapsulates commonsense knowledge bases as empathetic tools, enabling LLMs to integrate external knowledge flexibly.
Outcome:	The proposed framework can generate empathetic responses effectively on the TOOL-ED dataset.

I²B-LPO: Latent Policy Optimization via Iterative Information Bottleneck (2026.acl-long)

Copied to clipboard

Huilin Deng, Hongchen Luo, Yue Zhu, Long Li, Zhuoyue Chen, Xinghao Zhao, Ming LI, Chuyang Zhao, Jihai Zhang, MengChang Wang, Yang Cao, Yu Kang

CLUE: A Chinese Language Understanding Evaluation Benchmark (2020.coling-main)

Challenge:	Existing methods for large language model reasoning suffer from exploration collapse due to the semantic homogeneity of random rollouts.
Approach:	They propose to use latent policy optimization via iterative information bottleneck to optimize reasoning trajectories by diversifying reasoning .
Outcome:	Empirical results show that the proposed method achieves state-of-the-art performance with margins of up to 5.3% in accuracy and 7.4% in diversity metrics.

Copied to clipboard

Liang Xu, Hai Hu, Xuanwei Zhang, Lu Li, Chenjie Cao, Yudong Li, Yechen Xu, Kai Sun, Dian Yu, Cong Yu, Yin Tian, Qianqian Dong, Weitang Liu, Bo Shi, Yiming Cui, Junyi Li, Jun Zeng, Rongzhao Wang, Weijian Xie, Yanting Li, Yina Patterson, Zuoyu Tian, Yiwen Zhang, He Zhou, Shaoweihua Liu, Zhe Zhao, Qipeng Zhao, Cong Yue, Xinrui Zhang, Zhengliang Yang, Kyle Richardson, Zhenzhong Lan

Challenge:	Existing language evaluation benchmarks for English are limited to English . lack of such benchmarks makes it difficult to replicate success in other languages .
Approach:	They introduce a large-scale Chinese language understanding evaluation benchmark . the benchmark uses a set of current state-of-the-art pre-trained Chinese models .
Outcome:	The first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark is released . the benchmark evaluates models across a wide range of tasks on original Chinese text . existing language evaluation benchmarks are mostly limited to English .

Attribution-Based Analysis and Optimization of Modular Agentic Workflows (2026.findings-acl)

Copied to clipboard

Yingxuan Yang, Bo Huang, Siyuan Qi, Chao Feng, Haoyi Hu, Yuxuan Zhu, Jinbo Hu, Haoran Zhao, Ziyi He, Xiao Liu, ZongYu Wang, Muning Wen, Lin Qiu, Xuezhi Cao, Xunliang Cai, Yong Yu, Weinan Zhang

Challenge:	Large Language Models (LLMs) have driven the rise of agentic workflows . yet, how can we attribute performance gains to individual upgrades and their interactions?
Approach:	They propose a game-theoretic framework that models component upgrades as players and evaluates component coalitions to compute Shapley values.
Outcome:	The proposed framework provides interaction-aware attribution and recommendation for model allocation under a fixed workflow structure.

Sentiment Word Aware Multimodal Refinement for Multimodal Sentiment Analysis with ASR Errors (2022.findings-acl)

Copied to clipboard

Yang Wu, Yanyan Zhao, Hao Yang, Song Chen, Bing Qin, Xiaohuan Cao, Wenting Zhao

Visual Prompt Tuning for Few-Shot Text Classification (2022.coling-1)

Challenge:	Existing models for multimodal sentiment analysis are limited in their capacity to be deployed in the real world.
Approach:	They propose a model that can dynamically refine erroneous sentiment words by leveraging multimodal sentiment clues.
Outcome:	The proposed model surpasses the state-of-the-art models on three datasets.

Copied to clipboard

Jingyuan Wen, Yutian Luo, Nanyi Fei, Guoxing Yang, Zhiwu Lu, Hao Jiang, Jie Jiang, Zhao Cao

EpiGEN: An Efficient Multi-Api Code GENeration Framework under Enterprise Scenario (2024.lrec-main)

Challenge:	Existing work on pretraining models for text classification uses image encoders instead of visual prompts.
Approach:	They propose a method to deploy large-scale pre-trained models in the prompt-tuning paradigm in few-shot learning.
Outcome:	The proposed method outperforms the most recent prompt-tuning methods on five public text classification datasets.

Copied to clipboard

Sijie Li, Sha Li, Hao Zhang, Shuyang Li, Kai Chen, Jianyong Yuan, Yi Cao, Lvqing Yang

CODEMENV: Benchmarking Large Language Models on Code Migration (2025.findings-acl)

Challenge:	Existing approaches to large language models fail to meet expectations for code generation tasks . existing approaches are faced with drawbacks of high resource consumption and inadequate handling of multi-API tasks.
Approach:	They propose an Efficient multi-Api code GENeration framework that uses private APIs to pre-train LLMs.
Outcome:	The proposed framework shows good acceptability and readability on single-GPU tasks compared to fully fine-tuned LLMs with a larger number of parameters.

Copied to clipboard

Keyuan Cheng, Xudong Shen, Yihao Yang, TengyueWang TengyueWang, Yang Cao, Muhammad Asif Ali, Hanbin Wang, Lijie Hu, Di Wang

Mitigating Exposure Bias in Grammatical Error Correction with Data Augmentation and Reweighting (2023.eacl-main)

Challenge:	Large language models (LLMs) have demonstrated remarkable proficiency in handling a wide range of tasks within the software engineering domain, but their ability to perform code migration—adapting code to different environments—remains underexplored.
Approach:	They propose a benchmark to evaluate large language models’ performance in handling code migration tasks.
Outcome:	The proposed benchmark comprises 922 data points across 19 Python and Java packages and offers three tasks to systematically evaluate code migration: identifying version-incompatible functions, determining function changes, and adapting code to target environments.

Copied to clipboard

Hannan Cao, Wenmian Yang, Hwee Tou Ng

Jailbreaking Safeguarded Text-to-Image Models via Large Language Models (2026.findings-eacl)

Challenge:	Existing approaches to grammatical error correction (GEC) use sequence-to-sequence models, but there is an exposure bias problem.
Approach:	They propose a data manipulation approach to overcome the exposure bias problem in seq2seq GEC . they propose augmentation methods to mimic decoder input and reweighting methods to automatically balance the importance of each kind of augmented samples.
Outcome:	The proposed method improves on benchmark GEC datasets.

Copied to clipboard

Zhengyuan Jiang, Yuepeng Hu, Yuchen Yang, Yinzhi Cao, Neil Zhenqiang Gong

Recall and Learn: A Memory-augmented Solver for Math Word Problems (2021.findings-emnlp)

Challenge:	Text-to-image models generate harmful content when unsafe prompts are submitted . authors propose a method to jailbreak text-to image models with safety guardrails .
Approach:	They propose a method to jailbreak text-to-image models with safety guardrails . they use a fine-tuned large language model to generate adversarial prompts based on unsafe prompts.
Outcome:	The proposed method bypasses safety guardrails and outperforms existing no-box attacks . the proposed method generates adversarial prompts efficiently after fine-tuning the model .

Copied to clipboard

Shifeng Huang, Jiawei Wang, Jiao Xu, Da Cao, Ming Yang

Beyond Surface-Level Patterns: An Essence-Driven Defense Framework Against Jailbreak Attacks in LLMs (2025.findings-acl)

Challenge:	Existing methods for solving math word problems are based on template-based generation which results in limited generalization capability.
Approach:	They propose a human-like analogical learning method for the math word problem . it uses modules of memory, representation, analogy, and reasoning to make a new exercise .
Outcome:	The proposed method outperforms state-of-the-art models on two well-known datasets.

Copied to clipboard

Shiyu Xiang, Ansen Zhang, Yanfei Cao, Fan Yang, Ronghao Chen

Specialization through Collaboration: Understanding Expert Interaction in Mixture-of-Expert Large Language Models (2026.eacl-long)

Challenge:	Existing methods focus on surface-level patterns, overlooking the deeper attack essences.
Approach:	They propose an Essence-Driven Defense Framework Against Jailbreak Attacks in Aligned Large Language Models that extracts the "attack essence" from a diverse set of known attack instances and stores it in an offline vector database.
Outcome:	The proposed framework outperforms existing methods by reducing the Attack Success Rate by at least 20%, underscoring its superior robustness against jailbreak attacks.

Copied to clipboard

Yuanbo Tang, Naifan Zhang, Yan Tang, Meixuan Chen, Shuhan Huang, Tingyu Cao, Yang Li

Curr-ReFT: Overcoming Training Bottlenecks in Small-scale Vision-Language Models via Curriculum Reinforcement Finetuning (2025.findings-emnlp)

Challenge:	Mixture-of-Experts (MoE) based large language models are popular for multitasking . however, whether each expert can specialize to a task remains unclear .
Approach:	They propose to use a dictionary learning approach to analyze expert collaboration mechanisms in MoE LLMs.
Outcome:	The proposed model outperforms existing methods by 2.5% while enabling 50% expert reduction.

Copied to clipboard

Huilin Deng, Ding Zou, Xinghao Zhao, Rui Ma, Yanming Guo, Yang Cao, Yu Kang

EoT: Evolution of Thoughts for Complex Reasoning Tasks (2025.findings-emnlp)

Challenge:	State-of-the-art vision-language models require massive scaling that limits practical deployment.
Approach:	They propose to use supervised fine-tuning to train small-scale vision-language models but face out-of-domain collapse when trained with traditional supervised learning (SFT).
Outcome:	Experiments show that curr-reFT achieves state-of-the-art performance across visual tasks in both in- and out-of domain settings and benchmarks.

Copied to clipboard

Qin Hua, Jiaqi Sun, Shiyou Qian, Dingyu Yang, Jian Cao, Guangtao Xue

Forewarned is Forearmed: Pre-Synthesizing Jailbreak-like Instructions to Enhance LLM Safety Guardrail to Potential Attacks (2025.findings-emnlp)

Challenge:	Existing studies focus on ensuring behavior fidelity, factuality or reliability in generated reasoning processes, but they neglect the simultaneous optimization of all three aspects for each thought.
Approach:	They propose a thought assessment method that is sensitive to knowledge and LLM behaviors . they use three scorers to evaluate each thought by considering domain context, semantic alignment, and behavior impact.
Outcome:	The proposed framework outperforms advanced approaches in knowledge-based complex tasks.

Copied to clipboard

Sheng Liu, Qiang Sheng, Danding Wang, Yang Li, Guang Yang, Juan Cao

Grammatical Error Correction with Contrastive Learning in Low Error Density Domains (2021.findings-emnlp)

Challenge:	Despite advances in improving large language model (LLM) to refuse to answer malicious instructions, LLMs remain vulnerable to jailbreak attacks where attackers generate instructions with distributions differing from safety alignment corpora.
Approach:	They propose a framework that leverages embedding space distribution analysis to generate jailbreak-like instructions.
Outcome:	The proposed framework shows significant decreases in attack success rate on Qwen2.5, Llama3.1, and Llma3.2 without compromising their utility.

Copied to clipboard

Hannan Cao, Wenmian Yang, Hwee Tou Ng

Sibyl: Empowering Empathetic Dialogue Generation in Large Language Models via Sensible and Visionary Commonsense Inference (2025.coling-main)

Challenge:	grammatical error correction (GEC) is a text generation task . performance on low error density domains where texts written by native speakers can be improved.
Approach:	They propose a contrastive learning approach to encourage the GEC model to assign a higher probability to a correct sentence while reducing the probability of incorrect sentences that the model tends to generate.
Outcome:	The proposed approach significantly improves the performance of GEC models in low error density domains.

Copied to clipboard

Lanrui Wang, Jiangnan Li, Chenxu Yang, Zheng Lin, Hongyin Tang, Huan Liu, Yanan Cao, Jingang Wang, Weiping Wang

The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmas (2025.emnlp-main)

Challenge:	Recent studies have focused on integrating commonsense knowledge into chatbots to enhance their ability to understand and generate dialogue responses.
Approach:	They propose a framework that integrates commonsense knowledge into chatbots to enable them to elicit more empathetic responses.
Outcome:	The proposed framework enables LLMs to uncover the implicit requirements of the conversation, aiming to elicit more empathetic responses.

Copied to clipboard

Ya Wu, Qiang Sheng, Danding Wang, Guang Yang, Yifan Sun, Zhengjia Wang, Yuyan Bu, Juan Cao

ATG: Benchmarking Automated Theorem Generation for Generative Language Models (2024.findings-naacl)

Challenge:	Existing evaluations of LLMs' moral reasoning capabilities rely on single-step evaluations, ignoring how models adapt to evolving ethical challenges.
Approach:	They propose a framework to evaluate evolving moral judgments of large language models (LLMs) using multi-step moral dilemma questionnaires.
Outcome:	The proposed framework enables a fine-grained analysis of how LLMs adjust their moral reasoning across escalating dilemmas.

Copied to clipboard

Xiaohan Lin, Qingxing Cao, Yinya Huang, Zhicheng Yang, Zhengying Liu, Zhenguo Li, Xiaodan Liang

Domain-Lifelong Learning for Dialogue State Tracking via Knowledge Preservation Networks (2021.emnlp-main)

Challenge:	Existing generative language models (LMs) can generate new or reusable theorems, but their ability to generate new theorels is under-explored.
Approach:	They propose to use Metamath library to generate new theorems that can be saved as reusable knowledge for future theoretical proving.
Outcome:	The proposed benchmark evaluates whether an agent can generate valuable (and possibly brand new) theorems that are applicable for downstream theoretic proving as reusable knowledge.

Copied to clipboard

Qingbin Liu, Pengfei Cao, Cao Liu, Jiansong Chen, Xunliang Cai, Fan Yang, Shizhu He, Kang Liu, Jun Zhao

Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers (2024.findings-acl)

Challenge:	Existing offline DST models require a fixed dataset to train . Existing domain-lifelong learning methods are impractical in real-world applications .
Approach:	They propose a domain-lifelong learning method to continuously train a DST model on new data to learn incessantly emerging new domains while avoiding catastrophically forgetting old learned domains.
Outcome:	The proposed method outperforms state-of-the-art lifelong learning methods by 4.25% and 8.27% on the MultiWOZ and the SGD benchmarks.

Copied to clipboard

Haowen Pan, Yixin Cao, Xiaozhi Wang, Xun Yang, Meng Wang

PAD: A Robustness Enhancement Ensemble Method via Promoting Attention Diversity (2024.lrec-main)

Challenge:	Existing methods to identify key neurons for interpretability of multi-modal large language models are unclear.
Approach:	They propose a method to identify key neurons for interpretability by multi-modal large language models.
Outcome:	The proposed method improves conventional works upon efficiency and applied range by removing needs of costly gradient computation.

Copied to clipboard

Yuting Yang, Pei Huang, Feifei Ma, Juan Cao, Jintao Li

MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)

Challenge:	Existing approaches to enhance robustness of deep neural networks focus on perturbation . weak robustness is a problem for many types of adversarial attacks, authors say .
Approach:	They propose a lightweight framework for enhancing robustness by perturbing parameters of a model and diversifying adversarial example distributions among different models.
Outcome:	The proposed method can improve robustness against adversarial attacks while maintaining accuracy on clean data.

Copied to clipboard

Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie

SLIM: Stealthy Low-Coverage Black-Box Watermarking via Latent-Space Confusion Zones (2026.findings-acl)

Challenge:	Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models.
Approach:	They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts.
Outcome:	The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings .

Copied to clipboard

Hengyu WU, Yang Cao

Augmenting Reasoning Capabilities of LLMs with Graph Structures in Knowledge Base Question Answering (2024.findings-emnlp)

Challenge:	Training data is a critical asset in Large Language Model (LLM) development and is often proprietary.
Approach:	They propose a framework that allows per-user data provenance verification under strict black-box access.
Outcome:	The proposed framework achieves ultra-low coverage capability, strong black-box verification performance, and great scalability while preserving both stealthiness and model utility.

Copied to clipboard

Yuhang Tian, Dandan Song, Zhijing Wu, Changzhi Zhou, Hao Wang, Jun Yang, Jing Xu, Ruanmin Cao, HaoYu Wang

Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts? (2024.acl-long)

Challenge:	Recent work uses Large Language Models (LLMs) for semantic parsing to address Knowledge Base Question Answering tasks.
Approach:	They propose a framework that augments reasoning capabilities of LLMs with Graph Structures in Knowledge Base Question Answering to retrieve question-related graph structures.
Outcome:	The proposed framework outperforms existing methods on GrailQA and WebQSP under the few-shot setting.

Copied to clipboard

Hexiang Tan, Fei Sun, Wanli Yang, Yuanzhuo Wang, Qi Cao, Xueqi Cheng

UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter Efficient Fine-Tuning of Large Models (2025.acl-long)

Challenge:	Recent advances in augmenting Large Language Models (LLMs) with auxiliary information have significantly revolutionized their efficacy in knowledge-intensive tasks.
Approach:	They propose a systematic framework to identify whether LLMs’ responses are attributed to either generated or retrieved contexts.
Outcome:	The proposed framework identifies whether LLMs’ responses are attributed to either generated or retrieved contexts.

Copied to clipboard

Xueyan Zhang, Jinman Zhao, Zhifei Yang, Yibo Zhong, Shuhao Guan, Linbo Cao, Yining Wang

Text Anomaly Detection with Simplified Isolation Kernel (2025.findings-emnlp)

Challenge:	Existing methods such as LoRA and VeRA use a low-rank approximation method that reduces the number of trainable parameters without compromising performance.
Approach:	They propose a parameter-efficient fine-tuning approach that leverages a low-rank approximation method that reduces the number of trainable parameters without compromising performance.
Outcome:	The proposed approach outperforms existing methods on GLUE and E2E benchmarks and is effective in instruction-tuning large language models and image classification models.

Copied to clipboard

Yang Cao, Sikun Yang, Yujiu Yang, Lianyong Qi, Ming Liu

KBioXLM: A Knowledge-anchored Biomedical Multilingual Pretrained Language Model (2023.findings-emnlp)

Challenge:	High-dimensional dense embeddings extracted by large language models pose memory requirements and high computation time.
Approach:	They propose a method that maps high-dimensional dense embeddings to lower-dimensional sparse representations while preserving crucial anomaly characteristics.
Outcome:	The proposed method achieves better detection performance than 11 SOTA anomaly detection algorithms while maintaining computational efficiency and low memory cost.

Copied to clipboard

Lei Geng, Xu Yan, Ziqiang Cao, Juntao Li, Wenjie Li, Sujian Li, Xinjie Zhou, Yang Yang, Jun Zhang

Multilinguality

Challenge:	Existing models for multilingual biomedical training are monolingual, resulting in limited cross-lingual capability.
Approach:	They propose a model that transforms a multilingual biomedical corpus into a biomedically domain using a knowledge-anchored approach.
Outcome:	The proposed model outperforms monolingual and multilingual models in cross-lingual scenarios.

We Need to Talk About Reproducibility in NLP Model Comparison (2023.emnlp-main)

Copied to clipboard

Yan Xue, Xuefei Cao, Xingli Yang, Yu Wang, Ruibo Wang, Jihong Li

Large-Scale Corpus Construction and Retrieval-Augmented Generation for Ancient Chinese Poetry: New Method and Data Insights (2025.findings-naacl)

Challenge:	Existing studies show that standard splits produce low reproducible and unreliable conclusions . reproducibility of empirical experimental conclusions is a problem in NLP domain .
Approach:	They propose to transform the reproducibility of a model comparison into a probabilistic function . they propose to use a regularized corpus splitting strategy to estimate the model's performance .
Outcome:	The proposed estimator achieves a high SNR and significantly increases reproducibility.

Copied to clipboard

Yang Liu, Lan Lan, Jiahuan Cao, Hiuyi Cheng, Kai Ding, Lianwen Jin

Information Retrieval

Challenge:	Ancient Chinese poetry presents unique challenges for Large Language Models due to data scarcity and limited ability of general LLMs when dealing with ACP.
Approach:	They propose a specialized Retrieval-Augmented Generation framework to improve LLMs' performance . they use 1.1 million ancient poems and 990K related texts to address hallucination issues .
Outcome:	The proposed framework improves performance of LLMs in ancient Chinese poetry domain from 49.2% to 89.0%.

STAIR: Learning Sparse Text and Image Representation in Grounded Tokens (2023.emnlp-main)

Copied to clipboard

Chen Chen, Bowen Zhang, Liangliang Cao, Jiguang Shen, Tom Gunter, Albin Jose, Alexander Toshev, Yantao Zheng, Jonathon Shlens, Ruoming Pang, Yinfei Yang

Representation Learning

Challenge:	State-of-the-art contrastive learning models like CLIP and ALIGN are less interpretable and suffer from inferior accuracy than dense representations.
Approach:	They extend CLIP and ALIGN models to build a sparse semantic representation that is interpretable and easy to integrate with existing retrieval systems.
Outcome:	The proposed model outperforms CLIP and ALIGN models on image and text retrieval tasks with a 4.9% and +4.3% improvement on COCO-5k textimage and imagetext retrieval respectively.

SAMem: State-Aware Memory as a Fine-Grained Memory for LLM Agents in Decision-Making (2026.findings-acl)

Copied to clipboard

Tong Wang, Pei Xu, Shiyue Cao, Likun Yang, Daipeng Li, Jianbin Jiao, Kaiqi Huang

Bridging the Domain Gaps in Context Representations for k-Nearest Neighbor Neural Machine Translation (2023.acl-long)

Challenge:	Existing experiential memory approaches rely on task-level memory, but this lacks the situational alignment required for complex multi-step decision-making.
Approach:	They propose a new fine-grained memory paradigm that aligns memory retrieval with the current state instead of storing and reusing globally shared experiences.
Outcome:	Experiments on complex decision-making benchmarks show that the proposed state-aware memory outperforms existing experiential memory approaches and significantly improves task-solving efficiency.

Copied to clipboard

Zhiwei Cao, Baosong Yang, Huan Lin, Suhang Wu, Xiangpeng Wei, Dayiheng Liu, Jun Xie, Min Zhang, Jinsong Su

Machine Translation

Challenge:	Existing methods to improve k-Nearest neighbor machine translation (kNN-MT) are based on the ability to non-parametrically adapt to new domains.
Approach:	They propose a method to boost the datastore retrieval of k-Nearest neighbor machine translation by reconstructing the original datastore.
Outcome:	The proposed method boosts the retrieval and translation quality of k-Nearest neighbor machine translation by reconstructing the original datastore.

Red Teaming Large Reasoning Models (2026.acl-long)

Copied to clipboard

Jiawei Chen, Yang Yang, Chao Yu, Yu Tian, Zhi Cao, Xue Yang, Linghao Li, Hang Su, Zhaoxia Yin

AscendKernelGen: LLM-Driven Kernel Generation for NPUs (2026.findings-acl)

Challenge:	Large Reasoning Models (LRMs) have emerged as a powerful advancement in multi-step reasoning tasks, but they introduce safety and reliability risks, such as CoT-hijacking and prompt-induced inefficiencies.
Approach:	They propose a unified benchmark to assess the trustworthiness of Large Reasoning Models.
Outcome:	The proposed benchmark evaluates truthfulness, safety and efficiency on 26 models.

Copied to clipboard

Xinzi Cao, Jianyang Zhai, Pengfei Li, Zhiheng Hu, Cen Yan, null Mubingxu, Guanghuan Fang, Bin She, Jiayu Li, Yihan Su, Dongyang Tao, Feidiao Yang, Chang-Dong Wang, Yutong Lu, Weicheng Xue, Bin Zhou, Yonghong Tian

Challenge:	Neural Processing Units (NPUs) are critical for AI infrastructure, but their development remains a bottleneck due to vendor-specific Domain-Specific Languages (DSLs).
Approach:	They propose a framework for NPU kernel development that bridges the gap in hardware-specific coding . compiler success on complex Level-2 kernels improves from 0% to 95.5%, they say .
Outcome:	The proposed framework bridges the gap in hardware-specific coding, showing a near-zero success rate on complex kernels.

Efficient k-Nearest-Neighbor Machine Translation with Dynamic Retrieval (2024.findings-acl)

Copied to clipboard

Yan Gao, Zhiwei Cao, Zhongjian Miao, Baosong Yang, Shiyu Liu, Min Zhang, Jinsong Su

Information Retrieval

Challenge:	Existing models for non-parametric domain adaptation lack kNN retrieval at each timestep, leading to substantial time overhead.
Approach:	They propose a kNN-MT-based model that uses a domain-specific translation knowledge store to interpolate the prediction distribution of the model.
Outcome:	The proposed model significantly extends kNN-MT with dynamic retrieval on widely-used datasets.

XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation (2020.emnlp-main)

Copied to clipboard

Yaobo Liang, Nan Duan, Yeyun Gong, Ning Wu, Fenfei Guo, Weizhen Qi, Ming Gong, Linjun Shou, Daxin Jiang, Guihong Cao, Xiaodong Fan, Ruofei Zhang, Rahul Agrawal, Edward Cui, Sining Wei, Taroon Bharti, Ying Qiao, Jiun-Hung Chen, Winnie Wu, Shuguang Liu, Fan Yang, Daniel Campos, Rangan Majumder, Ming Zhou

Multilinguality

Challenge:	XGLUE provides a benchmark dataset to train large-scale cross-lingual pre-trained models . XCLUE provides 11 diversified tasks that cover both understanding and generation scenarios .
Approach:	They introduce a new benchmark dataset to train large-scale cross-lingual pre-trained models using multilingual and bilingual corpora.
Outcome:	The proposed dataset is labeled in English and includes only natural language understanding tasks.

Global Context or Local Detail? Adaptive Visual Grounding for Hallucination Mitigation (2026.findings-acl)

Copied to clipboard

Yubo Jiang, Xin Yang, Abudukelimu Wuerkaixi, Zheming Yuan, Xuxin Cheng, Cao Liu, Ke Zeng, Fengying Xie, Zhiguo Jiang, Haopeng Zhang

Plug-and-Play Data Module for Code RL: Adaptive Ambiguity Replay (2026.findings-acl)

Challenge:	Large vision–language models suffer from object-existence hallucinations when multi-step deliberation decouples from visual evidence.
Approach:	They propose a framework that allocates visual computation by uncertainty . they propose highlighting retains global context, while selective zoom-in performs local verification.
Outcome:	The proposed framework reduces the complexity of multimodal reasoning by minimizing the operator trade-off.

Copied to clipboard

Jianqing Zhang, Wei Xia, Zhezheng Hao, Hong Wang, Hande Dong, Qiang Lin, Yang Liu, Jian Cao, Qiang Yang

Business as Rulesual: A Benchmark and Framework for Business Rule Flow Modeling with LLMs (2026.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

Chen Yang, Ruping Xu, Ruizhe Li, Bin Cao, Jing Fan

When 20 Agents Fail to Sort: The Distributed Sorting Benchmark for Scalable Multi-Agent Systems (2026.findings-acl)

Challenge:	Existing benchmarks for extracting structured procedural knowledge from unstructured business documents are limited by simplistic schemas and shallow logical dependencies.
Approach:	They propose a framework for extracting structured procedural knowledge from unstructured business documents . they propose BREX, a carefully curated benchmark comprising 409 real-world business documents and 2,855 expert-annotated rules .
Outcome:	The proposed framework outperforms standard prompts in rule extraction and execution.

Copied to clipboard

Xin Yang, Junhao Wang, Bintao Tang, Xuxin Cheng, Cao Liu, Ke Zeng, Wenyuan Jiang

Challenge:	MAS-BENCH isolates coordination under explicit communication constraints . CAMOC significantly improves coordination success and efficiency across backends .
Approach:	They propose a distributed-sorting benchmark that isolates coordination under explicit communication constraints.
Outcome:	MAS-BENCH improves coordination success and efficiency across backends . CAMOC significantly improves efficiency under shared-state interaction .

HS-GC: Holistic Semantic Embedding and Global Contrast for Effective Text Clustering (2024.lrec-main)

Copied to clipboard

Chen Yang, Bin Cao, Jing Fan

Text Clustering

Challenge:	In this paper, we introduce Holistic Semantic Embedding and Global Contrast (HS-GC) to learn the instance- and cluster-level representations.
Approach:	They propose a novel loss function that exploits different layers of semantic information in a deep neural network to provide a more holistic semantic text representation.
Outcome:	The proposed model outperforms the state-of-the-art model on five text datasets and improves clustering accuracy of 5.9% and 3.2% on the StackOverflow and TREC datasets.

Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs (2025.emnlp-main)

Copied to clipboard

Dayu Yang, Tianyang Liu, Daoan Zhang, Antoine Simoulin, Xiaoyi Liu, Yuwei Cao, Zhaopu Teng, Xin Qian, Grey Yang, Jiebo Luo, Julian McAuley

SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding (2022.coling-1)

Challenge:	Recent breakthrough models like OpenAI-o1 and DeepSeek-R1 show powerful task-solving capabilities, particularly advances in reasoning.
Approach:	They propose future research directions that may deepen the synergy, ultimately advancing LLM performance in both complex reasoning and code intelligence.
Outcome:	The proposed research may deepen the synergy, ultimately advancing LLM performance in both complex reasoning and code intelligence.

Copied to clipboard

Wanwei He, Yinpei Dai, Binyuan Hui, Min Yang, Zheng Cao, Jianbo Dong, Fei Huang, Luo Si, Yongbin Li

Aligning Large Multimodal Models with Factually Augmented RLHF (2024.findings-acl)

Challenge:	Existing methods for dialog understanding only consider self-augmented dialogs as positive samples and treat all other dialogs like negative ones.
Approach:	They propose a tree-structured pre-trained conversation model which learns dialog representations from limited labeled dialogs and large-scale unlabeled dialog corpora via semi-supervised contrastive pre-training.
Outcome:	The proposed model can achieve state-of-the-art results on the DialoGLUE benchmark.

Copied to clipboard

Zhiqing Sun, Sheng Shen, Shengcao Cao, Haotian Liu, Chunyuan Li, Yikang Shen, Chuang Gan, Liangyan Gui, Yu-Xiong Wang, Yiming Yang, Kurt Keutzer, Trevor Darrell

SafeLawBench: Towards Safe Alignment of Large Language Models (2025.findings-acl)

Challenge:	Large Multimodal Models (LMMs) are built across modalities and the misalignment between two modality can result in "hallucination" . developing LMMs faces challenges such as a lack of data and a limited number of data sets.
Approach:	They propose a new algorithm that augments the reward model with additional factual information such as image captions and ground-truth multi-choice options.
Outcome:	The proposed approach improves on the LLaVA-Bench dataset with the 96% performance level of the text-only GPT-4 and an improvement of 60% on MMHAL-BENCH over other baselines.

Copied to clipboard

Chuxue Cao, Han Zhu, Jiaming Ji, Qichao Sun, Zhenghao Zhu, Wu Yinyu, Josef Dai, Yaodong Yang, Sirui Han, Yike Guo

SciAgent: Tool-augmented Language Models for Scientific Reasoning (2024.emnlp-main)

Challenge:	Recent studies indicate that large language models (LLMs) may exhibit risks, including threats to the protection of private data and the generation of hallucinations.
Approach:	They propose to evaluate LLMs from a legal perspective using the SafeLawBench benchmark.
Outcome:	The proposed framework categorizes safety risks into three levels based on legal standards and includes 24,860 multi-choice questions and 1,106 open-domain question-answering tasks.

Copied to clipboard

Yubo Ma, Zhibin Gou, Junheng Hao, Ruochen Xu, Shuohang Wang, Liangming Pan, Yujiu Yang, Yixin Cao, Aixin Sun

When Slower Isn’t Truer: Inverse Scaling Law of Truthfulness in Multimodal Reasoning (2026.findings-acl)

Challenge:	SciAgent surpasses other LLMs with the comparable size by more than 8.0% in absolute accuracy.
Approach:	They propose a tool-augmented scientific reasoning setting that supplements LLMs with scalable toolsets and builds a benchmark to evaluate LLM’s abilities with tool assistance.
Outcome:	The proposed setting augments LLMs with scalable toolsets and shifts the focus from pursuing an omniscient problem solver to a proficient tool-user.

Copied to clipboard

Sitong Fang, Wenjing Cao, Jiahao Li, Xuyao Wang, Chi-Min Chan, Sirui Han, Juntao Dai, Yike Guo, Yaodong Yang, Jiaming Ji

From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms (2026.findings-acl)

Challenge:	a study of slow reasoning models for multimodal reasoning finds that they are more prone to fabricating plausible yet false details when confronted with incomplete or misleading visual inputs.
Approach:	They conduct the first systematic study of the inverse scaling law in slow-thinking paradigms for multimodal reasoning.
Outcome:	The findings suggest that slower reasoning models are more prone to fabricating false details . the study analyzed 5,000-sample hierarchical prompt dataset by 50 participants .

Copied to clipboard

Jinghao Luo, Yuchen Tian, Chuxue Cao, Ziyang Luo, Hongzhan Lin, Kaixin Li, Chuyi Kong, Ruichao Yang, Jing Ma

Challenge:	Large Language Models (LLMs)-based agents have fundamentally reshaped artificial intelligence . however, the inherent statelessness of LLMs hinders their ability to maintain logical consistency across complex, multi-step tasks .
Approach:	They propose a framework for LLM agent memory mechanisms that formalizes the development process into three stages: storage, reflection, and experience.
Outcome:	The proposed framework breaks the development process into three stages . it analyzes the need for long-range consistency, challenges in dynamic environments, and the ultimate goal of continual learning.

LESA: Learnable LLM Layer Scaling-Up (2025.acl-long)

Copied to clipboard

Yifei Yang, Zouying Cao, Xinbei Ma, Yao Yao, Zhi Chen, Libo Qin, Hai Zhao

HeteroSpec: Leveraging Contextual Heterogeneity for Efficient Speculative Decoding (2026.acl-long)

Challenge:	Existing methods for depth scaling-up rely on empirical heuristic rules for layer duplication, resulting in poor initialization and slower convergence during continual pre-training.
Approach:	They propose a method for learning latent parameters between layers by concatenating parameters from each layer and applying Singular Value Decomposition.
Outcome:	Experiments show that LESA outperforms baseline models with less than half the cost of existing methods.

Copied to clipboard

Siran Liu, Yang Ye, Qianchao Zhu, Zane Cao, Yongchao He

Green & Sustainable NLP

Challenge:	Autoregressive decoding limits the inference throughput of Large Language Models due to its sequential dependency.
Approach:	They propose a framework that allocates verification effort in proportion to candidate uncertainty.
Outcome:	Speculative decoding achieves an average speedup over state-of-the-art methods . a small subset of high-confidence predictions accounts for most successful verifications .

MCS-Bench: A Comprehensive Benchmark for Evaluating Multimodal Large Language Models in Chinese Classical Studies (2025.acl-long)

Copied to clipboard

Yang Liu, Jiahuan Cao, Hiuyi Cheng, Yongxin Shi, Kai Ding, Lianwen Jin

Diversity and Consistency: Exploring Visual Question-Answer Pair Generation (2021.findings-emnlp)

Challenge:	Multimodal Large Language Models (MLLMs) have advanced visual and language understanding, but their potential in Chinese Classical Studies (CCS) remains underexplored due to the lack of specialized benchmarks.
Approach:	They propose to develop a multimodal benchmark specifically designed for Chinese Classical Studies across multiple subdomains to bridge this gap.
Outcome:	The proposed benchmark spans seven core subdomains with a total of 45 meticulously designed tasks.

Copied to clipboard

Sen Yang, Qingyu Zhou, Dawei Feng, Yang Liu, Chao Li, Yunbo Cao, Dongsheng Li

FinEval: A Chinese Financial Domain Knowledge Evaluation Benchmark for Large Language Models (2025.naacl-long)

Challenge:	Existing tasks to generate question-answer pairs from visual images are under-explored.
Approach:	They propose a task that targets question-answer pair generation from visual images.
Outcome:	The proposed model can generate diverse or consistent QAPs on two benchmarks.

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

M2Edit: Locate and Edit Multi-Granularity Knowledge in Multimodal Large Language Model (2025.emnlp-main)

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

Yang Zhou, Pengfei Cao, Yubo Chen, Qingbin Liu, Dianbo Sui, Xi Chen, Kang Liu, Jun Zhao

Multi-level Adaptive Contrastive Learning for Knowledge Internalization in Dialogue Generation (2023.emnlp-main)

Challenge:	Existing knowledge editing methods for MLLMs lack multi-granularity knowledge . existing knowledge editing approaches lack multimodality knowledge and generalize to multimodal data.
Approach:	They propose a multimodal knowledge editing method which integrates key knowledge layers within MLLMs and collaboratively edits them.
Outcome:	The proposed method improves visual generality performance on knowledge data of different granularities.

Copied to clipboard

Chenxu Yang, Zheng Lin, Lanrui Wang, Chong Tian, Liang Pang, Jiangnan Li, Qirong Ho, Yanan Cao, Weiping Wang

EvoWiki: Evaluating LLMs on Evolving Knowledge (2025.acl-long)

Challenge:	Existing knowledge-grounded dialogue generation models struggle with dull and repetitive outputs, a problem commonly termed as text degeneration.
Approach:	They propose a framework that allows the model to "cheat" the objective by duplicating knowledge segments in a superficial pattern matching based on overlap.
Outcome:	The proposed framework can be applied to a WoW dataset and shows that it works across models and decoding strategies.

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

Highlight-Transformer: Leveraging Key Phrase Aware Attention to Improve Abstractive Multi-Document Summarization (2021.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

Shuaiqi Liu, Jiannong Cao, Ruosong Yang, Zhiyuan Wen

Ambiguous Learning from Retrieval: Towards Zero-shot Semantic Parsing (2023.acl-long)

Challenge:	Existing models do not consider key phrases in determining attention weights of self-attention . Existing work does not consider the importance of key phrases when determining weights .
Approach:	They propose a model with highlighting mechanism to assign greater attention weights to key phrases . they propose two structures of highlighting attention for each head and the multihead highlighting . experimental results show that their proposed model significantly outperforms the baseline model .
Outcome:	The proposed model outperforms the baseline models on a multi-news dataset.

Copied to clipboard

Shan Wu, Chunlei Xin, Hongyu Lin, Xianpei Han, Cao Liu, Jiansong Chen, Fan Yang, Guanglu Wan, Le Sun

LDEDE: LRP-Driven Efficient Detection and Editing Framework for LLM Privacy Neurons (2026.findings-acl)

Challenge:	Existing neural semantic parsers require a large amount of training data which is expensive and difficult to obtain.
Approach:	They propose a framework for a supervised retrieval system based on pretrained language models . they propose ambiguous supervision to improve the precision and coverage of the task .
Outcome:	The proposed approach outperforms state-of-the-art zero-shot parsing methods in ambiguous supervision.

Copied to clipboard

Zhao Zhengyuan, Cao Lifeng, null Sunhaodong, Shi Haotian, Du Xuehui, Liu Aodi, Niu Lanjie, Yang Xiaocheng

Representative Demonstration Selection for In-Context Learning with Two-Stage Determinantal Point Process (2023.emnlp-main)

Challenge:	Existing privacy protection methods fail to cover context-dependent sensitive information and are prone to performance degradation.
Approach:	They propose a Layer-wise Relevance Propagation-driven framework for efficient privacy neuron detection and editing.
Outcome:	The proposed framework achieves 80% higher efficiency than gradient attribution methods while reducing leakage risks of Phone, Email, and medical privacy by 42.7%–73.5% on average and cutting computational time by 60%–90%.

Copied to clipboard

Zhao Yang, Yuanzhe Zhang, Dianbo Sui, Cao Liu, Jun Zhao, Kang Liu