Papers by Li An

Detecting Subtle Differences between Human and Model Languages Using Spectrum of Relative Likelihood (2024.emnlp-main)

Challenge:	Existing studies on depression detection rely on textual and visual content to determine whether a human being is depressed or non-depressed.
Approach:	They propose a multimodal topic-enriched Auxiliary Learning approach that captures topic information from texts and images for depression detection.
Outcome:	The proposed approach improves the performance of the primary task by using topic information from text and images.

Copied to clipboard

Yang Xu, Yu Wang, Hao An, Zhichen Liu, Yongyuan Li

Psycholinguistics

Challenge:	Existing methods for detecting modelgenerated texts from human texts are limited by the fact that absolute likelihood values of texts are bound to certain linguistic and cognitive constraints.
Approach:	They propose to use relative likelihood values instead of absolute ones to extract useful features from the spectrum-view of likelihood for the human-model text detection task.
Outcome:	The proposed method can reveal subtle differences between human and model languages, which find theoretical roots in psycholinguistics studies.

Enhancing Neural Models with Vulnerability via Adversarial Attack (2020.coling-main)

Copied to clipboard

Rong Zhang, Qifei Zhou, Bo An, Weiping Li, Tong Mo, Bo Wu

AMO-Bench: Large Language Models Still Struggle in High School Math Competitions (2026.findings-acl)

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

Junlin Liu, Shengnan An, Shuang Zhou, Dan Ma, Yehao Lin, Xinxuan Lv, Xuanlin Wang, Xiaoyu Li, Ziwen Wang, Xuezhi Cao, Xunliang Cai

ReTRE: Benchmarking LLM Transfer Robustness with Structure-Preserving Variants (2026.acl-long)

Challenge:	Existing benchmarks for mathematical reasoning are becoming less effective due to performance saturation.
Approach:	They propose to use a mathematical reasoning benchmark with Olympiad difficulty to evaluate top-tier LLMs.
Outcome:	The proposed benchmarks are cross-validated by experts to meet IMO difficulty standards and entirely original problems to prevent performance leakages from data memorization.

Copied to clipboard

ZhongDong Li, Weijie Shi, Yue Cui, Haolun MA, Yuanjun Liu, Jiawei Li, An Liu, Jia Zhu, Jiajie Xu

WirelessMathBench: A Mathematical Modeling Benchmark for LLMs in Wireless Communications (2025.findings-acl)

Challenge:	Learning transfer theory emphasizes that applying acquired knowledge to novel manifestations is a key signal of deep understanding
Approach:	They propose a benchmark that probes transfer robustness along two rewrite levels: Near Transfer and Far Transfer.
Outcome:	The proposed benchmark demonstrates that large language models are robust when faced with novel manifestations of the same problem.

Copied to clipboard

Xin Li, Mengbing Liu, Li Wei, Jiancheng An, Merouane Abdelkader Debbah, Chau Yuen

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

Challenge:	Large Language Models (LLMs) have demonstrated impressive results across a broad array of tasks, yet their capacity for complex, domain-specific mathematical reasoning remains underexplored.
Approach:	They propose a benchmark to evaluate Large Language Models on mathematical modeling challenges to wireless communications engineering.
Outcome:	The proposed benchmark evaluates LLMs on mathematical modeling challenges to wireless communications engineering.

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.

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

Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders (2026.acl-long)

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

Yupeng Hou, Jiacheng Li, Xiangjun Fu, Zhankui He, An Yan, Xiusi Chen, Julian McAuley

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

Challenge:	Recent advances in large language models have enabled their use as semantic encoders for recommendation, but their roles and behaviors in this setting are still not well understood.
Approach:	They propose a benchmark to evaluate large language models as semantic encoders in recommendation scenarios.
Outcome:	The proposed benchmark shows that ranking of 11 leading LLMs is low compared to MTEB, highlighting the unique challenges of semantic encoding in recommendation.

Copied to clipboard

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

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

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

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.

RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following (2025.findings-acl)

Copied to clipboard

Junru Lu, Jiazheng Li, Guodong Shen, Lin Gui, Siyu An, Yulan He, Di Yin, Xing Sun

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

Challenge:	Existing role-playing datasets mostly contribute to controlling role style and knowledge boundaries, but overlook role-following in instruction-follower scenarios.
Approach:	They propose a fine-grained role-playing and instruction-following composite benchmark, named RoleMRC, which includes multi-turn dialogues between ideal roles and humans, including free chats or discussions upon given passages .
Outcome:	The proposed model improves instruction-following without compromising general role-playing and reasoning capabilities.

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

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

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

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

Tell Me What You Don’t Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing (2025.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

Wenhao Liu, Siyu An, Junru Lu, Muling Wu, Tianlong Li, Xiaohua Wang, Changze Lv, Xiaoqing Zheng, Di Yin, Xing Sun, Xuanjing Huang

Representation Learning

Challenge:	Role-playing Agents (RPAs) struggle to recognize and respond to hard queries that conflict with their role-play knowledge.
Approach:	They propose a lightweight representation editing approach that conveniently shifts conflicting requests to the rejection region, thereby enhancing the model’s refusal accuracy.
Outcome:	The proposed model improves RPAs’ refusal ability of conflicting requests while maintaining their general role-playing capabilities.

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

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

Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence (2024.emnlp-main)

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

Junru Lu, Jiazheng Li, Siyu An, Meng Zhao, Yulan He, Di Yin, Xing Sun

Challenge:	Existing studies attributed verbosity to biased labels, but new research shows that DPO can be effective in mitigating verboses.
Approach:	They propose to use a method to reduce the amount of verbosity in LLMs by using a downsampling approach.
Outcome:	The proposed approach overcomes the problem of verbosity by reducing the length reliance of the proposed algorithm.

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

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

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

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

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

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

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

HMoE: Heterogeneous Mixture of Experts for Language Modeling (2025.emnlp-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

An Wang, Xingwu Sun, Ruobing Xie, Shuaipeng Li, Jiaqi Zhu, Zhen Yang, Pinxue Zhao, Weidong Han, Zhanhui Kang, Di Wang, Naoaki Okazaki, Cheng-zhong Xu

Sparsifying Mamba (2025.findings-emnlp)

Challenge:	Mixture of Experts (MoE) models use homogeneous experts with diverse capacities, resulting in a lack of expert specialization and parameter utilization.
Approach:	They propose a framework where experts differ in size and possess diverse capacities . they propose HMoE to encourage frequent activation of smaller experts .
Outcome:	The proposed framework outperforms homogeneous homogenous MoE models on evaluation benchmarks and achieves lower loss rate with fewer activated parameters.

Copied to clipboard

An Wang, Ruobing Xie, Shuaipeng Li, Xingwu Sun, Zhanhui Kang

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

Challenge:	Existing attempts to integrate sparsification with Mamba fail to leverage Mamba's internal structure for fine-grained sparsifying.
Approach:	They propose to use Mamba to integrate sparsification into Mamba and propose a flexible and effective mechanism for parameter scalability.
Outcome:	The proposed framework can independently achieve parameter scalability and has stronger performance.

Copied to clipboard

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

CGoDial: A Large-Scale Benchmark for Chinese Goal-oriented Dialog Evaluation (2022.emnlp-main)

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

Yinpei Dai, Wanwei He, Bowen Li, Yuchuan Wu, Zheng Cao, Zhongqi An, Jian Sun, Yongbin Li

Dialogue Systems & Conversational Agents

Challenge:	a new benchmark for goal-oriented dialog evaluation is needed to address the problem of knowledge sources, noisy user expressions, and the shortage of annotated data.
Approach:	They propose a Chinese benchmark for goal-oriented dialog evaluation that uses dialog sessions and 574,949 dialog turns to bridge the gap between academic benchmarks and spoken dialog scenarios.
Outcome:	The proposed benchmark contains 96,763 dialog sessions and 574,949 dialog turns totally.

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

Copied to clipboard

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

UltraIF: Advancing Instruction Following from the Wild (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

Kaikai An, Li Sheng, Ganqu Cui, Shuzheng Si, Ning Ding, Yu Cheng, Baobao Chang

Interventional Rationalization (2023.emnlp-main)

Challenge:	a lack of transparency has resulted in a gap between research community and leading companies . large language models have demonstrated remarkable capabilities in following complex instructions .
Approach:	They propose a method to build large language models that can follow complex instructions with open-source data.
Outcome:	The proposed approach can synergize complex instructions and filter responses with evaluation questions.

Copied to clipboard

Linan Yue, Qi Liu, Li Wang, Yanqing An, Yichao Du, Zhenya Huang

SciDTB: Discourse Dependency TreeBank for Scientific Abstracts (P18-2)

Challenge:	Existing methods for rationalization use spurious correlations in data to compose rationales and make predictions.
Approach:	They propose a method to discover the causal rationales by using a structural causal model.
Outcome:	The proposed method is based on the causal theory and validates on three real-world datasets.

Copied to clipboard

An Yang, Sujian Li

Syntactic Text Processing

Challenge:	Discourse relations are annotated on scientific articles.
Approach:	They propose a domain-specific discourse treebank annotated on scientific articles . they use dependency trees to represent discourse structure, which is flexible and simplified .
Outcome:	The proposed treebank is a benchmark for evaluating discourse dependency parsers.

Do Large Language Models Discriminate in Hiring Decisions on the Basis of Race, Ethnicity, and Gender? (2024.acl-short)

Copied to clipboard

Haozhe An, Christabel Acquaye, Colin Wang, Zongxia Li, Rachel Rudinger

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

Challenge:	We study whether large language models exhibit race- and gender-based name discrimination in hiring decisions .
Approach:	They propose templatic prompts to LLMs to write an email to a named job applicant informing them of a hiring decision.
Outcome:	The proposed model generates an acceptance or rejection email based on the applicant's first name .

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

PerMemSafe: Benchmarking Implicit Personalized Safety of Long Horizon Self-Evolving Agents (2026.findings-acl)

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.

Copied to clipboard

Hengyu An, Minxi Li, Naen Xu, Chunyi Zhou, Xiaogang Xu, Tianyu Du, Jinbao Li, Shouling Ji

Dialogue Systems & Conversational Agents

Challenge:	Existing self-evolving agents have a low safety rate in long-horizon interactions . however, this reliance on context-independent safety evaluations is insufficient .
Approach:	They propose a framework that explicitly models personalized risk inference and memory evolution.
Outcome:	The proposed framework improves implicit personalized safety by 23.8% over prior frameworks while maintaining helpfulness in long-horizon interactions.

Soul-Mix: Enhancing Multimodal Machine Translation with Manifold Mixup (2024.acl-long)

Copied to clipboard

Xuxin Cheng, Ziyu Yao, Yifei Xin, Hao An, Hongxiang Li, Yaowei Li, Yuexian Zou

GATEAU: Selecting Influential Samples for Long Context Alignment (2025.emnlp-main)

Challenge:	Multimodal machine translation (MMT) aims to improve the performance of machine translation with the help of visual information.
Approach:	They propose a multimodal machine translation mixup method that integrates visual information into conventional text-only neural machine translation systems.
Outcome:	The proposed method outperforms existing models on a multi-directional dataset with fewer parameters and achieves new state-of-the-art performance.

Copied to clipboard

Shuzheng Si, Haozhe Zhao, Gang Chen, Yunshui Li, Kangyang Luo, Chuancheng Lv, Kaikai An, Fanchao Qi, Baobao Chang, Maosong Sun

Challenge:	Existing studies have attempted to scale up the available data volume by synthesizing long instruction-following samples, but a lack of a well-defined strategy for ensuring data quality may introduce low-quality samples and restrict the model’s performance.
Approach:	They propose a framework to identify influential samples enriched with long-range dependency relations that can be used to align large language models to handle instructions with extremely long contexts.
Outcome:	The proposed framework identifies samples with long-range dependency relations and shows that the model trained on these samples exhibits better instruction-following and long-context understanding capabilities.

SODAPOP: Open-Ended Discovery of Social Biases in Social Commonsense Reasoning Models (2023.eacl-main)

Copied to clipboard

Haozhe An, Zongxia Li, Jieyu Zhao, Rachel Rudinger

Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension (P19-1)

Challenge:	Existing diagnostic tests for detecting social biases in NLP models only detect stereotypic associations pre-specified by the designer.
Approach:	They propose an approach for automatic social bias discovery in social commonsense question-answering by substituting names associated with different demographic groups and generating many distractor answers from a masked language model.
Outcome:	The proposed approach uncovers model’s stereotypic associations between demographic groups and an open set of words.

Copied to clipboard

An Yang, Quan Wang, Jing Liu, Kai Liu, Yajuan Lyu, Hua Wu, Qiaoqiao She, Sujian Li

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

Challenge:	Recent results show pre-trained language models (LMs) can improve machine reading comprehension (MRC) Experimental results indicate that KT-NET offers significant and consistent improvements over BERT .
Approach:	They propose a method that leverages external knowledge bases to improve machine reading comprehension (MRC) KT-NET employs an attention mechanism to select desired knowledge from KBs and fuses selected knowledge with BERT to enable context- and knowledge-aware predictions.
Outcome:	The proposed model outperforms baseline models on ReCoRD and SQuAD1.1 benchmarks and ranks 1st on the ReCoDR and SQUAD1.1 leaderboards.

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 .

LEGENT: Open Platform for Embodied Agents (2024.acl-demos)

Copied to clipboard

Zhili Cheng, Zhitong Wang, Jinyi Hu, Shengding Hu, An Liu, Yuge Tu, Pengkai Li, Lei Shi, Zhiyuan Liu, Maosong Sun