Papers by An Zhang

LaMP-Val: Large Language Models Empower Personalized Valuation in Auction (2025.findings-emnlp)

Challenge:	Existing work on adversarial attack to improve performance of NLSM tasks has not been done.
Approach:	They propose a general two-stage training framework to enhance neural models with Vulnerability via adversarial attack.
Outcome:	The proposed framework improves neural models with Vulnerability via adversarial attack on NLSM datasets.

Copied to clipboard

Jie Sun, Tianyu Zhang, Houcheng Jiang, Kexin Huang, Xiang Shu, Zhibo Zhu, Lintao Ma, Xingyu Lu, Jun Zhou, Junkang Wu, Chi Luo, An Zhang, Jiancan Wu, Xiang Wang

Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs (2025.acl-long)

Challenge:	Currently, most research focuses on the bidding algorithms used within auction mechanisms.
Approach:	They propose a personalized valuation framework that integrates Large Language Models to incorporate personalized semantic preference into users valuation process.
Outcome:	The proposed framework incorporates Large Language Models to incorporate personalized semantic preference into users valuation process.

Copied to clipboard

Weixiang Zhao, Yulin Hu, Yang Deng, Jiahe Guo, Xingyu Sui, Xinyang Han, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu

ProtT3: Protein-to-Text Generation for Text-based Protein Understanding (2024.acl-long)

Challenge:	Existing role-play fine-tuning techniques improve role adaptability but may degrade safety performance, especially for villainous characters.
Approach:	They propose safety-aware Role-Play Fine-Tuning (SaRFT) to balance role-playing capabilities and safety.
Outcome:	The proposed method outperforms state-of-the-art baselines under both LoRA and full-parameter fine-tuning settings.

Copied to clipboard

Zhiyuan Liu, An Zhang, Hao Fei, Enzhi Zhang, Xiang Wang, Kenji Kawaguchi, Tat-Seng Chua

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models (2025.naacl-long)

Challenge:	Language Models excel in understanding textual descriptions of proteins, but struggle to process texts.
Approach:	They propose a framework for Protein-to-Text Generation for Text-based Protein Understanding that integrates a PLM as its protein understanding module.
Outcome:	The proposed framework surpasses existing baselines and is highly efficient in protein-to-text generation.

Copied to clipboard

Bang An, Shiyue Zhang, Mark Dredze

AgentV-RL: Scaling Reward Modeling with Agentic Verifier (2026.findings-acl)

Challenge:	Efforts to ensure the safety of large language models (LLMs) include safety fine-tuning, evaluation, and red teaming.
Approach:	They conduct a comparative analysis of RAG and non-RAG frameworks with eleven LLMs to examine how RAG can make models less safe and change their safety profile.
Outcome:	The proposed methods are less effective than those used for non-RAG settings.

Copied to clipboard

Jiazheng Zhang, Ziche Fu, Zhiheng Xi, Wenqing Jing, Mingxu Chai, Wei He, Guoqiang Zhang, Chenghao Fan, Chenxin An, Wenxiang Chen, Zhicheng Liu, Haojie Pan, Dingwei Zhu, Tao Gui, Qi Zhang, Xuanjing Huang

Hello Again! LLM-powered Personalized Agent for Long-term Dialogue (2025.naacl-long)

Challenge:	Existing approaches to improve LLM reasoning are limited in complex domains and lack external grounding makes verifiers unreliable on computation-intensive tasks.
Approach:	They propose a framework that transforms reward modeling into a multi-turn, tool-augmented deliberative process.
Outcome:	The proposed framework surpasses state-of-the-art ORMs by 25.2% under parallel and sequential TTS.

Copied to clipboard

Hao Li, Chenghao Yang, An Zhang, Yang Deng, Xiang Wang, Tat-Seng Chua

Natural Language Interfaces

Challenge:	Existing dialogue systems focus on brief single-session interactions, neglecting real-world needs for long-term companionship and personalized interactions.
Approach:	They propose a model-agnostic framework for long-term dialogue agents . they use event summary and persona management to enable reasoning .
Outcome:	The proposed framework incorporates three independently tunable modules dedicated to event perception, persona extraction, and response generation.

LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification (2026.acl-long)

Copied to clipboard

Penghui Yang, Cunxiao Du, Fengzhuo Zhang, Haonan Wang, Tianyu Pang, Chao Du, Bo An

Green & Sustainable NLP

Challenge:	Large Language Models (LLMs) can process extremely long contexts, requiring efficient inference over extended inputs.
Approach:	They propose a model that uses a constant-sized key-value cache to train long-context models.
Outcome:	Experimental results show that LongSpec achieves 3.26x speedup over strong Flash Attention baselines and 2.34x wall clock time on four math reasoning tasks.

A Reinforcement Learning Framework for Robust and Secure LLM Watermarking (2026.eacl-long)

Copied to clipboard

Li An, Yujian Liu, Yepeng Liu, Yuheng Bu, Yang Zhang, Shiyu Chang

ReactXT: Understanding Molecular “Reaction-ship” via Reaction-Contextualized Molecule-Text Pretraining (2024.findings-acl)

Challenge:	Existing watermarking algorithms rely on heuristic green/red token lists . however, these lists are inconsistent and can be compromised .
Approach:	They propose a framework for robust and secure LLM watermarking using reinforcement learning.
Outcome:	The proposed method achieves state-of-the-art trade-off across all criteria with notable improvements in resistance to spoofing attacks without degrading other criteria.

Copied to clipboard

Zhiyuan Liu, Yaorui Shi, An Zhang, Sihang Li, Enzhi Zhang, Xiang Wang, Kenji Kawaguchi, Tat-Seng Chua

Prompted Aspect Key Point Analysis for Quantitative Review Summarization (2024.acl-long)

Challenge:	Molecular-text modeling is an emerging research field that aims to facilitate molecule-relevant tasks with a textual interface and textual knowledge.
Approach:	They propose a new method for reaction-text modeling that uses three types of input contexts to incrementally pretrain LMs.
Outcome:	The proposed method improves experimental procedure prediction and molecule captioning and offers competitive results in retrosynthesis.

Copied to clipboard

An Tang, Xiuzhen Zhang, Minh Dinh, Erik Cambria

Summarization

Challenge:	Recent abstractive approaches generate KPs based on sentences, resulting in overlapping and hallucinated opinions.
Approach:	They propose to use supervised learning to extract short sentences as key points before matching them to review comments for quantification of KP prevalence.
Outcome:	The proposed framework achieves state-of-the-art performance on Yelp and SPACE.

MT-Video-Bench: A Holistic Video Understanding Benchmark for Evaluating Multimodal LLMs in Multi-Turn Dialogues (2026.findings-acl)

Copied to clipboard

Yaning Pan, Qianqian Xie, Guohui Zhang, Zekun Moore Wang, Yongqian Wen, Yuanxing Zhang, Haoxuan Hu, Zhiyu Pan, Yibing Huang, Zhidong Gan, Yonghong Lin, An Ping, Shihao Li, Yanghai Wang, Tianhao Peng, Jiaheng Liu

Natural Language Interfaces

Challenge:	Existing evaluation benchmarks for Multimodal Large Language Models (MLLMs) focus on single-turn question answering, overlooking the complexity of multi-turn dialogues in real-world scenarios.
Approach:	They propose a video understanding benchmark for MLLMs in multi-turn dialogues that assesses six core competencies that focus on perceptivity and interactivity.
Outcome:	The MT-Video-Bench evaluates 1,000 multi-turn dialogues from diverse domains and reveals significant performance discrepancies and limitations in handling multi-turned video dialogues.

RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing (2025.findings-emnlp)

Copied to clipboard

Hao Xiang, Tianyi Tang, Yang Su, Bowen Yu, An Yang, Fei Huang, Yichang Zhang, Yaojie Lu, Hongyu Lin, Xianpei Han, Jingren Zhou, Junyang Lin, Le Sun

Dialogue Systems & Conversational Agents

Challenge:	Existing benchmarks focus on character-centric approach and fail to reflect real-world applications.
Approach:	RMTBench is a user-centric bilingual role-playing benchmark featuring 80 diverse characters and over 8,000 dialogue rounds.
Outcome:	RMTBench features 80 diverse characters and over 8,000 dialogue rounds.

Learning Bias-reduced Word Embeddings Using Dictionary Definitions (2022.findings-acl)

Copied to clipboard

Haozhe An, Xiaojiang Liu, Donald Zhang

Learn from Failure: Fine-tuning LLMs with Trial-and-Error Data for Intuitionistic Propositional Logic Proving (2024.acl-long)

Challenge:	Existing word embeddings have undesirable gender, racial, and religious biases . DD-GloVe is a train-time debiasing algorithm that uses dictionary definitions based on word definitions.
Approach:	They propose a dictionary-guided loss function that encourages word embeddings to be similar to their relatively neutral dictionary definition representations.
Outcome:	The proposed algorithm can learn word embeddings by leveraging dictionary definitions.

Copied to clipboard

Chenyang An, Zhibo Chen, Qihao Ye, Emily First, Letian Peng, Jiayun Zhang, Zihan Wang, Sorin Lerner, Jingbo Shang

Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond (2025.acl-industry)

Challenge:	Recent advances in Automated Theorem Proving have shown the effectiveness of leveraging a (large) language model that generates tactics (i.e. proof steps) to search through proof states.
Approach:	They propose to use a large language model that generates tactics to search through proof states.
Outcome:	The proposed model solves more unseen theorems with lower trial searches than the current model, which only learns from failed attempts.

Copied to clipboard

Liang Wen, Yunke Cai, Fenrui Xiao, Xin He, Qi An, Zhenyu Duan, Yimin Du, Junchen Liu, Tanglifu Tanglifu, Xiaowei Lv, Haosheng Zou, Yongchao Deng, Shousheng Jia, Xiangzheng Zhang

Musical Score Understanding Benchmark: Evaluating Large Language Models’ Comprehension of Complete Musical Scores (2026.acl-long)

Challenge:	Experimental results show that opensource curriculum training is more effective when distinct datasets are available for different training stages.
Approach:	They propose an opensource suite for training long reasoning models using publicdata and models.
Outcome:	The proposed model outperforms DeepSeek-R1-DistillQwen-32B models in math reasoning.

Copied to clipboard

Congren Dai, Yue Yang, Krinos Li, Huichi Zhou, Shijie Liang, Zhang Bo, Enyang Liu, Ge Jin, Hongran An, Haosen Zhang, Peiyuan Jing, KinHei Lee, Zhenxuan Zhang, Xiaobing Li, Maosong Sun

ReLM: Leveraging Language Models for Enhanced Chemical Reaction Prediction (2023.findings-emnlp)

Challenge:	Existing benchmarks for musical score understanding are narrow in scope, focusing on isolated fragments, short excerpts, or multiple-choice formulations, rather than supporting holistic reasoning over entire scores.
Approach:	They propose a benchmark for score-level musical understanding across textual and visual modalities.
Outcome:	The musical score understanding benchmark contains 1,800 question-answer pairs from works by Bach, Beethoven, Chopin, Debussy, and others.

Copied to clipboard

Yaorui Shi, An Zhang, Enzhi Zhang, Zhiyuan Liu, Xiang Wang

MPO: Multilingual Safety Alignment via Reward Gap Optimization (2025.acl-long)

Challenge:	Existing methods for predicting chemical reactions are limited by insufficient training data and inability to utilize textual information.
Approach:	They propose a framework that leverages chemical knowledge encoded in language models to assist GNNs, thereby enhancing the accuracy of real-world chemical reaction predictions.
Outcome:	The proposed framework improves state-of-the-art GNN-based methods across chemical reaction datasets especially in out-of distribution settings.

Copied to clipboard

Weixiang Zhao, Yulin Hu, Yang Deng, Tongtong Wu, Wenxuan Zhang, Jiahe Guo, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu

Multilinguality

Challenge:	Existing preference learning methods for safety alignment are monolingual and struggle with noisy multilingual data.
Approach:	They propose a multilingual reward gaP optimization approach that leverages the well-aligned safety capabilities of the dominant language to improve safety alignment across multiple languages.
Outcome:	Extensive experiments on three LLMs, LLaMA-3.1, Gemma-2 and Qwen2.5, validate MPO’s efficacy in multilingual safety alignment without degrading general multilingual utility.

EFUF: Efficient Fine-Grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models (2024.emnlp-main)

Copied to clipboard

Shangyu Xing, Fei Zhao, Zhen Wu, Tuo An, Weihao Chen, Chunhui Li, Jianbing Zhang, Xinyu Dai

PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning (2026.findings-acl)

Challenge:	Existing methods to eliminate hallucinations require expensive human annotation . hallucination in multimodal large language models poses unique challenges for current research .
Approach:	They propose a fine-grained unlearning framework that performs gradient ascent to eliminate hallucinations without paired data.
Outcome:	The proposed method reduces hallucinations while preserving quality with modest computational overhead.

Copied to clipboard

Ruixiang Feng, Yuntao Wen, Silin Zhou, Ke Shi, Yifan Wang, Ran Le, Zhenwei An, Zongchao Chen, Chen Yang, Guangyue Peng, Yiming Jia, Dongsheng Wang, Tao Zhang, Lisi Chen, Yang Song, Shen Gao, Shuo Shang

Neural News Recommendation with Long- and Short-term User Representations (P19-1)

Challenge:	Existing LRMs often suffer from "overthinking" and excessively long reasoning traces . a dual-level framework for length compression of LRM is proposed .
Approach:	They propose a framework for prefix-protected and difficulty-aware compression under hierarchical supervision.
Outcome:	The proposed framework reduces token usage while improving accuracy on math benchmarks.

Copied to clipboard

Mingxiao An, Fangzhao Wu, Chuhan Wu, Kun Zhang, Zheng Liu, Xing Xie

ThinkAnswer Loss: Balancing Semantic Similarity and Exact Matching for LLM Reasoning Enhancement (2025.findings-emnlp)

Challenge:	Existing news recommendation methods learn a single representation for each user, which may be insufficient.
Approach:	They propose a neural news recommendation approach which can learn both long- and short-term user representations by using a news encoder and a user encoder.
Outcome:	The proposed approach can learn both long- and short-term user representations on a real-world dataset.

Copied to clipboard

Shan Yang, Kun Wu, Zeju Li, Linlin Zhang, Xiangyu Pei, Leike An, Yu Liu

LipoAgent: Coordinating Fine-Tuned LLM Agents for Safer Lipid Design (2026.findings-acl)

Challenge:	Existing methods for knowledge distillation use Chain-of-Thought (CoT) and answer pairs, but they lack appropriate supervision signals.
Approach:	They propose a framework that decouples CoT and answer supervision . the framework applies semantic similarity constraints while maintaining strict literal matching for the answer .
Outcome:	The proposed framework decouples CoT and answer supervision while maintaining strict literal matching for the answer.

Copied to clipboard

Leshu Li, An Lu, Haiyu Wang, Zhibin Feng, Conghui Duan, Qing Bao, Zongmin Zhao, Sai Qian Zhang

Green & Sustainable NLP

Challenge:	Lipid nanoparticles (LNPs) are among the most clinically mature platforms for nucleic acid delivery, yet designing lipids that are effective and biologically safe remains a major bottleneck.
Approach:	They propose a safety-aware multi-agent LLM framework for lipid discovery that enforces toxicity as a prerequisite for efficiency prediction.
Outcome:	The proposed framework achieves an average improvement in mRNA transfection efficiency prediction across multiple foundation models.

Repulsive Attention: Rethinking Multi-head Attention as Bayesian Inference (2020.emnlp-main)

Copied to clipboard

Bang An, Jie Lyu, Zhenyi Wang, Chunyuan Li, Changwei Hu, Fei Tan, Ruiyi Zhang, Yifan Hu, Changyou Chen

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

Challenge:	Existing studies show that multi-head attention is an effective module in deep neural networks, but there are no explicit mechanisms guaranteeing this property.
Approach:	They propose a non-parametric approach that explicitly improves the repulsiveness in multi-head attention and consequently strengthens model’s expressiveness.
Outcome:	The proposed approach improves the repulsiveness in multi-head attention and strengthens model’s expressiveness.

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

Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion (2025.acl-long)

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

Jianqing Zhu, Huang Huang, Zhihang Lin, Juhao Liang, Zhengyang Tang, Khalid Almubarak, Mosen Alharthi, Bang An, Juncai He, Xiangbo Wu, Fei Yu, Junying Chen, Ma Zhuoheng, Yuhao Du, He Zhang, Saied Alshahrani, Emad A. Alghamdi, Lian Zhang, Ruoyu Sun, Haizhou Li, Benyou Wang, Jinchao Xu

Refining Corpora from a Model Calibration Perspective for Chinese Spelling Correction (2024.findings-acl)

Challenge:	In the evolving landscape of large language models, the predominant focus has been on English and Chinese.
Approach:	They propose to utilize Arabic-specific vocabulary in the tokenizer to accelerate decoding.
Outcome:	The proposed model achieves decent performance comparable to the best Arabic LLMs across various Arabic benchmarks.

Copied to clipboard

Dingyao Yu, Yang An, Wei Ye, Xiongfeng Xiao, Shaoguang Mao, Tao Ge, Shikun Zhang

Multimodality

Challenge:	Chinese Spelling Correction (CSC) lacks large-scale high-quality corpora due to labor-intensive labeling of spelling errors in real-life writing or typing scenarios.
Approach:	They propose to use OCR/ASR-based generation to refine Chinese Spelling Correction models on random replacement-based corpora and filter them based on prediction confidence.
Outcome:	The proposed model outperforms existing models on three widely-used benchmarks while significantly alleviating over-correction.

Long Chain-of-Thought Fine-tuning via Understanding-to-Reasoning Transition (2025.emnlp-main)

Copied to clipboard

Chenxin An, Zhihui Xie, Xiaonan Li, Ming Zhong, Shansan Gong, Lei Li, Jun Zhang, Jingjing Xu, Lingpeng Kong

Hard Sample Aware Prompt-Tuning (2023.acl-long)

Challenge:	Existing research on long-context scaling in language models has focused on managing lengthy input prompts instead of producing long outputs.
Approach:	They propose a sequence-level curriculum learning framework that shifts a model’s focus from interpreting long chain-of-thoughts to generating them.
Outcome:	Experiments on rigorous reasoning benchmarks, including AIME24 and GPQA Diamond, show that the proposed approach surpasses standard fine-tuning by over 10% while maintaining robust performance on understanding tasks.

Copied to clipboard

Yuanjian Xu, Qi An, Jiahuan Zhang, Peng Li, Zaiqing Nie

Harder Task Needs More Experts: Dynamic Routing in MoE Models (2024.acl-long)

Challenge:	Prompt-tuning based few-shot learning has garnered increasing attention in recent years due to its efficiency and promising capability.
Approach:	They propose a framework to distinguish informative hard samples from misleading ones in model training.
Outcome:	The proposed framework achieves new SOTA results on a series of NLP tasks pushing the SST-5 accuracy to 49.5% (1.1% point absolute improvement), QNLI accuracy to 74.6% (1.9% absolute improvement)

Copied to clipboard

Quzhe Huang, Zhenwei An, Nan Zhuang, Mingxu Tao, Chen Zhang, Yang Jin, Kun Xu, Kun Xu, Liwei Chen, Songfang Huang, Yansong Feng

SWE-Swiss: A Multi-Task Fine-Tuning and RL Recipe for High-Performance Issue Resolution (2026.findings-acl)

Challenge:	Unlike existing MoE approaches that rely on fixed TopK Routing, our dynamic expert selection framework dynamically allocates experts based on the confidence level in expert selection for each input.
Approach:	They propose a dynamic expert selection framework that dynamically allocates experts based on the confidence level in expert selection for each input.
Outcome:	The proposed method achieves an average improvement of 0.7% with less than 90% activated parameters and outperforms dense models in QA and machine translation tasks.

Copied to clipboard

Zhenyu He, Qingping Yang, Wei Shen, Xiaojian Zhong, Kechi Zhang, Chenxin An, Wenlei Shi, Tianle Cai, Di He, Jiaze Chen, Jingjing Xu

MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning (2026.findings-acl)

Challenge:	SWE-Swiss-32B demonstrates strong generalization to other common LLM benchmarks.
Approach:	They propose a two-phase training recipe that decomposes issue resolution into three core skills: Localization, Repair, and Unit Test Generation.
Outcome:	The proposed model achieves a 60.2% score on the SWE-bench Verified benchmark and is in the top-tier performance bracket of much larger models.

Copied to clipboard

Xukai Wang, Xuanbo Liu, Mingrui Chen, Haitian Zhong, Xuanlin Yang, Bohan Zeng, Jinbo Hu, Hao Liang, Junbo Niu, Xuchen Li, Ruitao Wu, Ruichuan An, Yang Shi, Liu Liu, Qiang Liu, Zhouchen Lin, Xu-Yao Zhang, Wentao Zhang, Bin Dong

Aspect-based Key Point Analysis for Quantitative Summarization of Reviews (2024.findings-eacl)

Challenge:	Existing benchmarks designed to evaluate the reasoning capabilities of large models are limited in scope and lack flexibility to adapt difficulty according to evolving reasoning capacities of models.
Approach:	They propose a benchmark that incorporates multidisciplinary questions to evaluate the reasoning capabilities of large models and can adjust and update question difficulty based on the reasoning abilities of advanced models.
Outcome:	The proposed benchmark incorporates multidisciplinary questions to evaluate the reasoning capabilities of large models and can adjust and update question difficulty based on the reasoning abilities of advanced models.

Copied to clipboard

An Tang, Xiuzhen Zhang, Minh Dinh

Information Extraction & Text Mining

Challenge:	Existing studies on review summarization use only major opinions, but ignore minority opinions and fail to quantify opinion prevalence.
Approach:	They propose a framework for quantitative review summarization using aspect-based key point analysis (ABKPA) they use aspect-basic sentiment analysis to automatically annotate silver labels for matching aspect-sentiment pairs .
Outcome:	The proposed framework outperforms state-of-the-art baselines on Yelp reviews on five business categories.

ACIArena: Toward Unified Evaluation for Agent Cascading Injection (2026.acl-long)

Copied to clipboard

Hengyu An, Minxi Li, Jinghuai Zhang, Naen Xu, Chunyi Zhou, Changjiang Li, Xiaogang Xu, Tianyu Du, Shouling Ji

FIPO: Free-form Instruction-oriented Prompt Optimization with Preference Dataset and Modular Fine-tuning Schema (2025.coling-main)

Challenge:	Existing studies consider only limited attack strategies and simplified MAS settings, limiting their generalizability and comprehensive evaluation.
Approach:	They propose a framework to evaluate the robustness of Multi-Agent Systems (MAS) they propose unified evaluation suites spanning attack surfaces and attack objectives .
Outcome:	ACIArena provides a benchmark of 1,356 test cases for evaluating MAS robustness . it covers six widely used MAS implementations and provides measurable results .

Copied to clipboard

Junru Lu, Siyu An, Min Zhang, Yulan He, Di Yin, Xing Sun

Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation (2021.findings-acl)

Challenge:	naive prompts can enhance the task performance of large language models, but they are resource-intensive.
Approach:	They propose an automatic prompt optimization method that refines naive prompts according to task outputs from in-box testing models.
Outcome:	The proposed method is based on a large-scale dataset and performed fairly across multiple models.

Copied to clipboard

Peng Wang, Junyang Lin, An Yang, Chang Zhou, Yichang Zhang, Jingren Zhou, Hongxia Yang

Structured Data in NLP

Challenge:	Existing methods for table-to-text generation suffer from poor faithfulness and low coverage.
Approach:	They propose a method that combines Autoregressive and Non-Autoregressive generation to generate a table-to-text from a key-value table using a skeleton and an edit-based non-autoregressively generation model.
Outcome:	The proposed method outperforms the existing methods on WikiPerson and WikiBio datasets on coverage and faithfulness.

Learning Algebraic Recombination for Compositional Generalization (2021.findings-acl)

Copied to clipboard

Chenyao Liu, Shengnan An, Zeqi Lin, Qian Liu, Bei Chen, Jian-Guang Lou, Lijie Wen, Nanning Zheng, Dongmei Zhang

Tanbih: Get To Know What You Are Reading (D19-3)

Challenge:	Neural sequence models exhibit limited compositional generalization ability in semantic parsing tasks.
Approach:	They propose an end-to-end neural model to learn algebraic recombination for compositional generalization.
Outcome:	The proposed model is based on two realistic and comprehensive compositional generalization benchmarks.

Copied to clipboard

Yifan Zhang, Giovanni Da San Martino, Alberto Barrón-Cedeño, Salvatore Romeo, Jisun An, Haewoon Kwak, Todor Staykovski, Israa Jaradat, Georgi Karadzhov, Ramy Baly, Kareem Darwish, James Glass, Preslav Nakov

Challenge:	Nowadays, more and more readers consume news online.
Approach:	They propose a news platform that displays news grouped into events and generates media profiles that show the general factuality of reporting, the degree of propagandistic content, hyper-partisanship, leading political ideology, general frame of reporting and stance with respect to various claims and topics of a media outlet.
Outcome:	The proposed news platform displays news grouped into events and generates media profiles that show the factuality of reporting, the degree of propagandistic content, hyper-partisanship, leading political ideology, general frame of reporting and stance with respect to various claims and topics of a news outlet.

CIF-PT: Bridging Speech and Text Representations for Spoken Language Understanding via Continuous Integrate-and-Fire Pre-Training (2023.findings-acl)

Copied to clipboard

Linhao Dong, Zhecheng An, Peihao Wu, Jun Zhang, Lu Lu, Ma Zejun

IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents (2025.emnlp-main)

Challenge:	Speech-to-text training and language model distillation are used to bridge the representations between speech and text.
Approach:	They propose a pre-training paradigm that integrates speech and text into a single frame-to-token alignment.
Outcome:	The proposed paradigm outperforms the state-of-the-art model on intent classification and slot filling tasks.

Copied to clipboard

Hengyu An, Jinghuai Zhang, Tianyu Du, Chunyi Zhou, Qingming Li, Tao Lin, Shouling Ji

RolePlot: A Systematic Framework for Evaluating and Enhancing the Plot-Progression Capabilities of Role-Playing Agents (2025.acl-long)

Challenge:	Existing methods for detecting Indirect Prompt Injection (IPI) attacks rely on assumptions about the model's inherent security, which lacks structural constraints on agent behaviors.
Approach:	They propose a novel task execution paradigm that models the agents’ task execution process as a traversal over a planned Tool Dependency Graph (TDG).
Outcome:	The proposed model reduces unintended tool invocations triggered by injected instructions, enhancing robustness against IPI attacks.

Copied to clipboard

Pinyi Zhang, Siyu An, Lingfeng Qiao, Yifei Yu, Jingyang Chen, Jie Wang, Di Yin, Xing Sun, Kai Zhang

Dialogue Systems & Conversational Agents

Challenge:	Existing research has focused on role-playing agents’ ability to portray specified characters, but their ability to advance the plot requires substantial improvements to deliver more engaging interaction.
Approach:	They propose a role-playing framework to evaluate and enhance the plot-progression capabilities of role-players.
Outcome:	The proposed framework improves RPAs’ ability to time plot developments and yields a significant increase in conversation turns and sustained higher arousal levels.

Debiased Orthogonal Boundary-Driven Efficient Noise Mitigation (2026.acl-long)

Copied to clipboard

Hao Li, Jiayang Gu, Jingkuan Song, An Zhang, Lianli Gao

AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender (2025.emnlp-main)

Challenge:	Existing noise mitigation methods face limitations due to their task-specific design, model dependency, and significant computational overhead.
Approach:	They propose a model-agnostic noise label mitigation paradigm that uses an estimator model and a scoring function to assess the noise level of input pairs.
Outcome:	The proposed method is superior to existing methods in training tasks and tasks.

Copied to clipboard

Weixiang Zhao, Jiahe Guo, Yulin Hu, Yang Deng, An Zhang, Xingyu Sui, Xinyang Han, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu

Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval (2025.emnlp-main)

Challenge:	Activation steering offers training-free defense but relies on fixed steering coefficients, resulting in suboptimal protection and increased false rejections of benign inputs.
Approach:	They propose an adaptive activation steering method that dynamically adjusts model behavior based on input characteristics.
Outcome:	The proposed method outperforms baseline methods across multiple jailbreak attacks with minimal impact on utility.

Copied to clipboard

Tianlu Zheng, Yifan Zhang, Xiang An, Ziyong Feng, Kaicheng Yang, Qichuan Ding

AceGPT, Localizing Large Language Models in Arabic (2024.naacl-long)

Challenge:	a large-scale visionlanguage pre-training framework is limited by the scarcity of large-sized annotated vision-language data . noise-resistant data construction pipeline is needed to filter and caption web-sourced images . noisy text tokens can be a problem for fine-grained representation learning .
Approach:	They develop a noise-resistant data construction pipeline that leverages in-context learning capabilities of MLLMs to automatically filter and caption web-sourced images.
Outcome:	The proposed framework improves cross-modal alignment by masking noisy textual tokens based on the gradient-attention similarity score.

Copied to clipboard

Huang Huang, Fei Yu, Jianqing Zhu, Xuening Sun, Hao Cheng, Song Dingjie, Zhihong Chen, Mosen Alharthi, Bang An, Juncai He, Ziche Liu, Junying Chen, Jianquan Li, Benyou Wang, Lian Zhang, Ruoyu Sun, Xiang Wan, Haizhou Li, Jinchao Xu

MusTQ: A Temporal Knowledge Graph Question Answering Dataset for Multi-Step Temporal Reasoning (2024.findings-acl)

Challenge:	Significant concerns emerge when addressing cultural sensitivity and local values.
Approach:	They propose a localized Large Language Model (LLM) specifically for Arabic, a language imbued with unique cultural characteristics inadequately addressed by current mainstream models.
Outcome:	The proposed model sets the state-of-the-art standard for open Arabic LLMs across various benchmarks.

Copied to clipboard

Tingyi Zhang, Jiaan Wang, Zhixu Li, Jianfeng Qu, An Liu, Zhigang Chen, Hongping Zhi

Multimodality

Challenge:	Existing studies focus on fact-centered reasoning with limited attention to temporal reasoning.
Approach:	They propose a new TKGQA dataset, MusTQ, which contains 666K multi-step temporal reasoning questions and a TKG.
Outcome:	The proposed model achieves state-of-the-art multi-step temporal reasoning ability with entity-time attention mechanism and optimized temporal knowledge graph representation.

How Do In-Context Examples Affect Compositional Generalization? (2023.acl-long)

Copied to clipboard

Shengnan An, Zeqi Lin, Qiang Fu, Bei Chen, Nanning Zheng, Jian-Guang Lou, Dongmei Zhang

Low-Resource NLP

Challenge:	In-context learning paradigms that focus on large corpus are limiting compositional generalization performance.
Approach:	They propose a test suite to investigate in-context compositional generalization . they propose to use examples that are structurally similar to the test case .
Outcome:	The proposed test suite investigates in-context compositional generalization performance . it finds that the performance can be affected by the selection of in-const examples .

Profiler: Black-box AI-generated Text Origin Detection via Context-aware Inference Pattern Analysis (2025.emnlp-main)

Copied to clipboard

Hanxi Guo, Siyuan Cheng, Xiaolong Jin, Zhuo Zhang, Guangyu Shen, Kaiyuan Zhang, Shengwei An, Guanhong Tao, Xiangyu Zhang

Challenge:	Existing methods to identify the origin of AI-generated texts fail to identify origin due to the high similarity of different LLMs.
Approach:	They propose a black-box AI-generated text origin detection method which accurately predicts the origin of an input text by extracting distinct context inference patterns.
Outcome:	The proposed method outperforms 10 state-of-the-art baselines and achieves a 25% increase in AUC score on average across natural language and code datasets.

Transferring General Multimodal Pretrained Models to Text Recognition (2023.findings-acl)

Copied to clipboard

Junyang Lin, Xuancheng Ren, Yichang Zhang, Gao Liu, Peng Wang, An Yang, Chang Zhou

Multimodality

Challenge:	Existing methods for text recognition rely on large-scale pretraining on human-annotated or synthetic data.
Approach:	They propose a method to transfer multimodal pretrained models to text recognition using image captioning.
Outcome:	The proposed method outperforms the baselines and achieves state-of-the-art performance in the Chinese text recognition benchmark.

PANDA: Preference Adaptation for Enhancing Domain-Specific Abilities of LLMs (2024.findings-acl)

Copied to clipboard

An Liu, Zonghan Yang, Zhenhe Zhang, Qingyuan Hu, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Yang Liu

Challenge:	Large language models have demonstrated considerable capabilities across various tasks . however, they often fall short of the performance achieved by domain-specific state-of-the-art models .
Approach:	They propose a tuning-free method to augment domain-specific abilities of Large language models . they leverage insights from the response preference of expert models to augment LLMs .
Outcome:	The proposed method outperforms the expert model on 4 ScienceWorld tasks.

SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios (2026.acl-long)

Copied to clipboard

Junkai Chen, Huihui Huang, Yunbo Lyu, Junwen An, Jieke Shi, Chengran Yang, Ting Zhang, Haoye Tian, Yikun Li, Zhenhao Li, Xin Zhou, Xing Hu, David Lo

Challenge:	Existing benchmarks fail to capture scenarios in which vulnerabilities are introduced by humans . we evaluate 5 popular code agents supported by 5 LLMs on SecureVibeBench .
Approach:	They propose a benchmarking tool that compares 105 C/C++ secure coding tasks . they use real-world open-source vulnerabilities and a comprehensive evaluation tool .
Outcome:	The proposed benchmarks show that code agents struggle to produce correct and secure code . the best performing agent produces merely 23.8% correct and secured solutions .

Neuron-Level Sequential Editing for Large Language Models (2025.acl-long)

Copied to clipboard

Houcheng Jiang, Junfeng Fang, Tianyu Zhang, Baolong Bi, An Zhang, Ruipeng Wang, Tao Liang, Xiang Wang