Papers by Yixin Wang

BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks (2026.acl-long)

Challenge:	Language Models (LMs) have demonstrated impressive molecule understanding ability on 1D text-related tasks, but lack 2D graph perception, a critical ability of human professionals in comprehending molecules’ topological structures.
Approach:	They propose to combine a cross-modal projector and a uni-modal adapter to enable an LM to understand both text- and graph-based molecular contents via a Q-Former.
Outcome:	The proposed model outperforms the baselines on tasks such as molecule captioning, IUPAC name prediction, and molecule-text retrieval.

Copied to clipboard

Rui Miao, Yixin Liu, Yili Wang, Xu Shen, Yue Tan, Yiwei Dai, Shirui Pan, Xin Wang

Robustness in NLP

Challenge:	Existing supervised defense methods rely on labeled malicious agents to train a supervised model of malicious behavior.
Approach:	They propose an unsupervised defense method that learns without requiring any attack-specific labels or prior knowledge of malicious behaviors.
Outcome:	The proposed method detects diverse attack types across MAS with various communication patterns while maintaining superior generalizability compared to baselines.

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

Copied to clipboard

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

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

Improving Event Detection via Open-domain Trigger Knowledge (2020.acl-main)

Copied to clipboard

Meihan Tong, Bin Xu, Shuai Wang, Yixin Cao, Lei Hou, Juanzi Li, Jun Xie

LLMs Are Prone to Fallacies in Causal Inference (2024.emnlp-main)

Challenge:	Existing methods for event detecting are prone to overfitting densely labeled trigger words due to the small scale of training data.
Approach:	They propose a novel Enrichment Knowledge Distillation model to leverage external open-domain trigger knowledge to reduce in-built biases to frequent trigger words in annotations.
Outcome:	The proposed model outperforms nine strong baselines and is especially effective for unseen/sparsely labeled trigger words.

Copied to clipboard

Nitish Joshi, Abulhair Saparov, Yixin Wang, He He

Challenge:	Recent work shows that causal facts can be extracted from LLMs through prompting . but it is unclear if this success is limited to explicitly-mentioned causal facts in pretraining data .
Approach:	They fine tune LLMs on synthetic data and test whether they can infer causal relations . they find that LLM can correctly deduce absence of causal relations from temporal and spatial relations if order is randomized .
Outcome:	The proposed model outperforms existing methods on causal inference tasks.

Where Fact Ends and Fairness Begins: Redefining AI Bias Evaluation through Cognitive Biases (2025.findings-emnlp)

Copied to clipboard

Jen-tse Huang, Yuhang Yan, Linqi Liu, Yixin Wan, Wenxuan Wang, Kai-Wei Chang, Michael R. Lyu

MMedAgent: Learning to Use Medical Tools with Multi-modal Agent (2024.findings-emnlp)

Challenge:	Existing benchmarks conflate factual correctness and normative fairness . a model may generate responses that are factually accurate but socially unfair .
Approach:	They propose a benchmark to examine the boundary between fact and fair . they draw on representativeness bias, attribution bias and ingroup–outgroup bias to explain why models often misalign fact and faireness.
Outcome:	The proposed model is based on ten frontier models and is available on github . it is compared with a standard model that generates people of color in Nazi-era uniforms .

Copied to clipboard

Binxu Li, Tiankai Yan, Yuanting Pan, Jie Luo, Ruiyang Ji, Jiayuan Ding, Zhe Xu, Shilong Liu, Haoyu Dong, Zihao Lin, Yixin Wang

R2F: A General Retrieval, Reading and Fusion Framework for Document-level Natural Language Inference (2022.emnlp-main)

Challenge:	Multi-modal Large Language Models (MLLMs) exhibit limited generality and often fall short when compared to specialized models.
Approach:	They propose a multi-modal medical agent that picks the most suitable medical tools based on user inputs.
Outcome:	The proposed agent performs better than open-source models and the closed-source model, GPT-4o.

Copied to clipboard

Hao Wang, Yixin Cao, Yangguang Li, Zhen Huang, Kun Wang, Jing Shao

Early Exit with Disentangled Representation and Equiangular Tight Frame (2023.findings-acl)

Challenge:	Document-level natural language inference (DOCNLI) is a new task in natural language processing.
Approach:	They propose a document-level natural language inference framework that fuses sentence-level tasks into a set of sentence-based tasks.
Outcome:	The proposed framework improves interpretability and performance with evidence.

Copied to clipboard

Yixin Ji, Jikai Wang, Juntao Li, Qiang Chen, Wenliang Chen, Min Zhang

Representation Learning

Challenge:	Existing early exit paradigm relies on training parametrical internal classifiers to complete specific tasks.
Approach:	They propose a method to decouple two distinct types of representation and introduce a non-parametric tight frame classifier for improvement.
Outcome:	Experiments on monolingual and multilingual tasks show that the proposed method improves over existing methods.

Diagnosing Memorization in Chain-of-Thought Reasoning, One Token at a Time (2025.emnlp-main)

Copied to clipboard

Huihan Li, You Chen, Siyuan Wang, Yixin He, Ninareh Mehrabi, Rahul Gupta, Xiang Ren

TheoremQA: A Theorem-driven Question Answering Dataset (2023.emnlp-main)

Challenge:	Large Language Models (LLMs) perform well on reasoning benchmarks but often fail when inputs alter slightly, raising concerns about overreliance on memorization.
Approach:	They propose a framework for Source-aware Token-level Identification of Memorization which attributes each token in a reasoning chain to one of multiple memorization sources based on their statistical co-occurrence with the token in the pretraining corpus.
Outcome:	The proposed framework attributes each token in a reasoning chain to one of multiple memorization sources based on their statistical co-occurrence with the token in the pretraining corpus.

Copied to clipboard

Wenhu Chen, Ming Yin, Max Ku, Pan Lu, Yixin Wan, Xueguang Ma, Jianyu Xu, Xinyi Wang, Tony Xia

Rethinking the Role of Entropy in Optimizing Tool-Use Behaviors for Large Language Model Agents (2026.acl-long)

Challenge:	Recent LLMs like GPT-4 and PaLM-2 have made tremendous progress in solving fundamental math problems like GSM8K by achieving over 90% accuracy.
Approach:	They propose to use theorem-driven question-answering dataset to evaluate AI models' ability to apply theoretic concepts to solving challenging science problems.
Outcome:	TheoremQA is curated by domain experts and contains 800 high-quality questions covering 350 theoremics from Math, Physics, EE&CS, and Finance.

Copied to clipboard

Zeping Li, Hongru Wang, Yiwen Zhao, Guanhua Chen, Yixia Li, Keyang Chen, Yixin Cao, Guangnan Ye, Hongfeng Chai, Zhenfei Yin

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

Challenge:	Large language models excel in mathematical reasoning and multi-hop question answering tasks, but in long trajectories, agents often invoke tools excessively or inappropriately, increasing computation cost and derailing the reasoning process.
Approach:	They propose to use entropy reduction as a supervisory signal to reduce tool calls . they propose to design two reward strategies to address the needs of optimizing tool-use behavior.
Outcome:	The proposed reward strategies reduce tool calls by 72.07% and improve performance by 22.27%.

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

SCALER: Synthetic Scalable Adaptive Learning Environment for Reasoning (2026.findings-acl)

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

Caijun Xu, Changyi Xiao, Zhongyuan Peng, Xinrun Wang, Yixin Cao

DUAL RM: Beyond Rule-based Preference Reward Modeling via Meta-Reward (2026.acl-long)

Challenge:	Reinforcement learning (RL) is a principled way to enhance the reasoning capabilities of large language models, yet its effectiveness hinges on training signals that remain informative as models evolve.
Approach:	They propose a framework that sustains effective learning signals through adaptive environment design that transforms real-world programming problems into verifiable reasoning environments with controllable difficulty and unbounded instance generation.
Outcome:	The proposed framework outperforms baselines across diverse reasoning benchmarks and exhibits more stable, long-horizon training dynamics.

Copied to clipboard

Xiaobo Liang, Wanfu Wang, Qipeng Huang, Yuyang Ding, Zecheng Tang, Yixin Ji, Qianben Chen, Zhe Zhao, Kehai Chen, Juntao Li, Min Zhang

Challenge:	Existing preference-based reward modeling methods face a recursive dependency where each verifier requires a meta-verifier, leading to continuous and costly dependence on human annotation.
Approach:	They propose a dual RM that couples discriminative and generative reward models under a non-parametric meta-reward.
Outcome:	The proposed model achieves strong performance across major preference benchmarks and even when trained exclusively on language modality, it exhibits robust cross-modal transfer on Omni-RewardBench.

DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models (2023.emnlp-main)

Copied to clipboard

Chengcheng Han, Xiaowei Du, Che Zhang, Yixin Lian, Xiang Li, Ming Gao, Baoyuan Wang

Dialogue Systems & Conversational Agents

Challenge:	Chain-of-Thought prompting has improved the reasoning capabilities of Large Language Models (LLMs) but it is ineffective or detrimental to the performance on reasoning tasks in Smaller Language Model (SLMs) with less than 10 billion parameters.
Approach:	They propose a Dialogue-guided Chain-of-Thought method to improve the reasoning capabilities of Large Language Models (LLMs) by generating intermediate reasoning steps in a dialogue format to guide the model to the final answer.
Outcome:	The proposed method can achieve significant performance gains over state-of-the-art competitors on four arithmetic reasoning datasets.

Beyond Single Frames: Can LMMs Comprehend Implicit Narratives in Comic Strip? (2025.findings-emnlp)

Copied to clipboard

Xiaochen Wang, Heming Xia, Jialin Song, Longyu Guan, Qingxiu Dong, Rui Li, Yixin Yang, Yifan Pu, Weiyao Luo, Yiru Wang, Xiangdi Meng, Wenjie Li, Zhifang Sui

AbGen: Evaluating Large Language Models in Ablation Study Design and Evaluation for Scientific Research (2025.acl-long)

Challenge:	Large Multimodal Models have demonstrated strong performance on vision-language benchmarks, yet current evaluations focus on single-image reasoning.
Approach:	STRIPCIPHER is a benchmark designed to evaluate model ability on understanding implicit narratives in silent comics.
Outcome:	STRIPCIPHER is a high-quality, human-annotated dataset featuring fine-grained annotations and comprehensive coverage of varying difficulty levels.

Copied to clipboard

Yilun Zhao, Weiyuan Chen, Zhijian Xu, Manasi Patwardhan, Chengye Wang, Yixin Liu, Lovekesh Vig, Arman Cohan

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

Challenge:	a benchmark designed to evaluate the capabilities of LLMs in designing ablation studies for scientific research is available online.
Approach:	They propose to use a benchmark to evaluate LLMs' ability to design ablation studies . they investigate whether current automated evaluation methods are not reliable .
Outcome:	The benchmark compared leading LLMs with human experts on generating detailed ablation study designs . the results show that current evaluation methods are not reliable for the task .

Copied to clipboard

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

Searching for Best Practices in Retrieval-Augmented Generation (2024.emnlp-main)

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

Xiaohua Wang, Zhenghua Wang, Xuan Gao, Feiran Zhang, Yixin Wu, Zhibo Xu, Tianyuan Shi, Zhengyuan Wang, Shizheng Li, Qi Qian, Ruicheng Yin, Changze Lv, Xiaoqing Zheng, Xuanjing Huang

Adaptive Feature-based Low-Rank Compression of Large Language Models via Bayesian Optimization (2024.findings-emnlp)

Challenge:	Retrieval-augmented generation (RAG) techniques have proven to be effective in integrating up-to-date information, mitigating hallucinations, and enhancing response quality, especially in specialized domains.
Approach:	They propose several strategies for deploying RAG that balance performance and efficiency.
Outcome:	The proposed approaches can significantly enhance question-answering capabilities and accelerate the generation of multimodal content using a “retrieval as generation” strategy.

Copied to clipboard

Yixin Ji, Yang Xiang, Juntao Li, Qingrong Xia, Zi Ye, Xinyu Duan, Zhefeng Wang, Kehai Chen, Min Zhang

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

Challenge:	Large language models require a balance between efficiency and performance.
Approach:	They propose a low-rank compression technique that reduces non-essential parameters by decomposing weight matrices into products of two low-ranked matrici.
Outcome:	The proposed method outperforms existing pruning and low-rank compression techniques in maintaining model performance at the same compression ratio.

Copied to clipboard

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

LiveChat: A Large-Scale Personalized Dialogue Dataset Automatically Constructed from Live Streaming (2023.acl-long)

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

Copied to clipboard

Jingsheng Gao, Yixin Lian, Ziyi Zhou, Yuzhuo Fu, Baoyuan Wang

Dialogue Systems & Conversational Agents

Challenge:	a recent study shows that open-domain dialogue systems are not able to perform well in fast-growing scenarios such as live streaming due to the domain gap between online-post constructed data and those required in downstream conversational tasks.
Approach:	They propose to train a conversational agent based on large social media datasets with multiple domains to improve response in live streaming scenarios.
Outcome:	The proposed model improves response modeling and addressee recognition in live open-domain scenarios.

MMEKG: Multi-modal Event Knowledge Graph towards Universal Representation across Modalities (2022.acl-demo)

Copied to clipboard

Yubo Ma, Zehao Wang, Mukai Li, Yixin Cao, Meiqi Chen, Xinze Li, Wenqi Sun, Kunquan Deng, Kun Wang, Aixin Sun, Jing Shao

ReIFE: Re-evaluating Instruction-Following Evaluation (2025.naacl-long)

Challenge:	Recent Knowledge Graphs (KGs) store billions of world facts in a directed graph, but expression ability of such entity-centric KGs is limited.
Approach:	They propose a large-scale multi-modal event knowledge graph named MMEKG that unifies different modalities of knowledge via events.
Outcome:	The proposed system unifies different modalities of knowledge via events, which complement and disambiguate each other.

Copied to clipboard

Yixin Liu, Kejian Shi, Alexander Fabbri, Yilun Zhao, PeiFeng Wang, Chien-Sheng Wu, Shafiq Joty, Arman Cohan

Robustness in NLP

Challenge:	Existing evaluations of large language models (LLMs) for instruction following are incomplete.
Approach:	They propose to use 25 base LLMs and 15 recently proposed evaluation protocols to evaluate instruction following on 4 human-annotated datasets.
Outcome:	The proposed evaluations identify the best-performing base LLMs and evaluation protocols with a high degree of robustness.

LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement (2024.findings-emnlp)

Copied to clipboard

Jiahao Ying, Mingbao Lin, Yixin Cao, Wei Tang, Bo Wang, Qianru Sun, Xuanjing Huang, Shuicheng Yan

Challenge:	Using advanced Large Language Models, instructors can improve training of smaller models by analyzing their own model's errors.
Approach:	They propose a framework that leverages advanced Large Language Models to enhance training of smaller target models.
Outcome:	The proposed framework outperforms ChatGPT on multiple benchmarks and shows that it improves on both in-domain and out-of-domain benchmarks.

ERGO: Event Relational Graph Transformer for Document-level Event Causality Identification (2022.coling-1)

Copied to clipboard

Meiqi Chen, Yixin Cao, Kunquan Deng, Mukai Li, Kun Wang, Jing Shao, Yan Zhang

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

Challenge:	Existing methods to identify event-event causal relations in a document are noisy and require heuristic rules or external tools.
Approach:	They propose a document-level event-event causality identification framework that uses heuristic rules to design edges between events.
Outcome:	The proposed framework outperforms existing state-of-the-art methods on two benchmark datasets.

Copied to clipboard

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

GEMv2: Multilingual NLG Benchmarking in a Single Line of Code (2022.emnlp-demos)

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

Sebastian Gehrmann, Abhik Bhattacharjee, Abinaya Mahendiran, Alex Wang, Alexandros Papangelis, Aman Madaan, Angelina Mcmillan-major, Anna Shvets, Ashish Upadhyay, Bernd Bohnet, Bingsheng Yao, Bryan Wilie, Chandra Bhagavatula, Chaobin You, Craig Thomson, Cristina Garbacea, Dakuo Wang, Daniel Deutsch, Deyi Xiong, Di Jin, Dimitra Gkatzia, Dragomir Radev, Elizabeth Clark, Esin Durmus, Faisal Ladhak, Filip Ginter, Genta Indra Winata, Hendrik Strobelt, Hiroaki Hayashi, Jekaterina Novikova, Jenna Kanerva, Jenny Chim, Jiawei Zhou, Jordan Clive, Joshua Maynez, João Sedoc, Juraj Juraska, Kaustubh Dhole, Khyathi Raghavi Chandu, Laura Perez Beltrachini, Leonardo F . R. Ribeiro, Lewis Tunstall, Li Zhang, Mahim Pushkarna, Mathias Creutz, Michael White, Mihir Sanjay Kale, Moussa Kamal Eddine, Nico Daheim, Nishant Subramani, Ondrej Dusek, Paul Pu Liang, Pawan Sasanka Ammanamanchi, Qi Zhu, Ratish Puduppully, Reno Kriz, Rifat Shahriyar, Ronald Cardenas, Saad Mahamood, Salomey Osei, Samuel Cahyawijaya, Sanja Štajner, Sebastien Montella, Shailza Jolly, Simon Mille, Tahmid Hasan, Tianhao Shen, Tosin Adewumi, Vikas Raunak, Vipul Raheja, Vitaly Nikolaev, Vivian Tsai, Yacine Jernite, Ying Xu, Yisi Sang, Yixin Liu, Yufang Hou

Text Generation

Challenge:	Evaluations in machine learning rarely use the latest metrics, datasets, or human evaluation in favor of remaining compatible with prior work.
Approach:	They propose to use the Generation, Evaluation, and Metrics Benchmark to integrate new evaluation methods into existing evaluations.
Outcome:	The proposed evaluation infrastructure bridges the gap between the advantages of leaderboards and in-depth and evolving evaluations by allowing model developers to benefit from each other's work.

The Factuality Tax of Diversity-Intervened Text-to-Image Generation: Benchmark and Fact-Augmented Intervention (2024.emnlp-main)

Copied to clipboard

Yixin Wan, Di Wu, Haoran Wang, Kai-Wei Chang

Revealing the Importance of Semantic Retrieval for Machine Reading at Scale (D19-1)

Challenge:	Prompt-based “diversity interventions” are commonly adopted to improve the diversity of Text-to-Image models depicting individuals with diverse racial or gender traits.
Approach:	They propose a benchmark to quantify the trade-off between using diversity interventions and preserving demographic factuality in T2I models.
Outcome:	The proposed model significantly improves the demographic factuality under diversity interventions while preserving diversity.

Copied to clipboard

Yixin Nie, Songhe Wang, Mohit Bansal

Recognizing Everything from All Modalities at Once: Grounded Multimodal Universal Information Extraction (2024.findings-acl)

Challenge:	Recent advances in representation learning have separated progress in both IR and MC . few studies have examined the relationship between retrieval and comprehension at different levels of granularity for development of MRS systems.
Approach:	They propose a simple yet effective pipeline system with consideration on hierarchical semantic retrieval at both paragraph and sentence level and their potential effects on the downstream task.
Outcome:	The proposed system achieves state-of-the-art on the leaderboard test sets of both FEVER and HOTPOTQA.

Copied to clipboard

Meishan Zhang, Hao Fei, Bin Wang, Shengqiong Wu, Yixin Cao, Fei Li, Min Zhang

DocEE: A Large-Scale and Fine-grained Benchmark for Document-level Event Extraction (2022.naacl-main)

Challenge:	Existing studies on IE tasks have focused on recognizing and analyzing cross-modal information . a multimodal large language model (MLLM) is developed to analyze IE across modalities .
Approach:	They propose a multimodal large language model (MLLM) capable of grounding information from all modalities.
Outcome:	The proposed framework provides a framework to analyze IE tasks over various modalities and their fine-grained groundings.

Copied to clipboard

MeiHan Tong, Bin Xu, Shuai Wang, Meihuan Han, Yixin Cao, Jiangqi Zhu, Siyu Chen, Lei Hou, Juanzi Li

Navigating the Nuances: A Fine-grained Evaluation of Vision-Language Navigation (2024.findings-emnlp)

Challenge:	Existing datasets focus on sentence-level event extraction, but document-level EE is limited due to the lack of large-scale and practical training and evaluation datasets.
Approach:	They propose a document-level event extraction dataset with 27,000+ events and 180,000+ arguments.
Outcome:	The proposed dataset includes 27,000+ events, 180,000+ arguments and large-scale manual annotations, fine-grained argument types and application-oriented settings.

Copied to clipboard

Zehao Wang, Minye Wu, Yixin Cao, Yubo Ma, Meiqi Chen, Tinne Tuytelaars

Isotropic Representation Can Improve Zero-Shot Cross-Lingual Transfer on Multilingual Language Models (2023.findings-emnlp)

Challenge:	a new evaluation framework for vision-language navigation is proposed . current evaluation standards hinge on endpoint success rates and path alignment metrics .
Approach:	They propose a semi-automatic method for CFG construction with Large-Language Models . they induct data spanning five principal instruction categories and analyze them .
Outcome:	The proposed framework diagnoses current models for the Vision-Language Navigation task at a finer-grained level.

Copied to clipboard

Yixin Ji, Jikai Wang, Juntao Li, Hai Ye, Min Zhang

End-to-End Learnable Psychiatric Scale Guided Risky Post Screening for Depression Detection on Social Media (2025.emnlp-main)

Challenge:	Existing mPLMs can align representations well for myriads of cross-lingual transfer tasks.
Approach:	They propose enhanced isotropy and constrained code-switching for zero-shot cross-lingual transfer to alleviate the problem of misalignment caused by anisotropic representations.
Outcome:	The proposed method improves on three zero-shot cross-lingual transfer tasks and over existing methods.

Copied to clipboard

Bichen Wang, Yuzhe Zi, Yixin Sun, Hao Yang, Yanyan Zhao, Bing Qin

Challenge:	Existing methods to detect depression from social media posting history are limited by frozen screening models and lack of learning.
Approach:	They propose to use a frozen screening model to train a risky post detection model with psychiatric scales to enable a learnable end-to-end learning process.
Outcome:	The proposed model outperforms several strong baseline methods and qualitative analysis confirms that it better captures users’ mental states than others.

Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction (2022.acl-long)

Copied to clipboard

Yubo Ma, Zehao Wang, Yixin Cao, Mukai Li, Meiqi Chen, Kun Wang, Jing Shao

A + B: A General Generator-Reader Framework for Optimizing LLMs to Unleash Synergy Potential (2024.findings-acl)

Challenge:	Using a prompt-based model, we find that event argument extraction is efficient and generalized well to few-shot settings.
Approach:	They propose a model PAIE for event argument extraction using prompt tuning for extractive objectives.
Outcome:	The proposed model can extract arguments with the same role instead of heuristic threshold tuning.

Copied to clipboard

Wei Tang, Yixin Cao, Jiahao Ying, Bo Wang, Yuyue Zhao, Yong Liao, Peng Zhou

Hierarchical Verbalizer for Few-Shot Hierarchical Text Classification (2023.acl-long)

Challenge:	Retrieval-Augmented Generation (RAG) is an effective solution to supplement necessary knowledge to large language models.
Approach:	They propose a "generate-then-read" pipeline to replace retrieval stage with generation from the LLM itself.
Outcome:	The proposed framework outperforms single models in the base and chat versions and addresses safety and helpfulness post-adaptation challenges.

Copied to clipboard

Ke Ji, Yixin Lian, Jingsheng Gao, Baoyuan Wang

Uncertainty Calibration for Tool-Using Language Agents (2024.findings-emnlp)

Challenge:	Existing work on the hierarchical text classification problem is limited due to the complexity of label hierarchy and intensive labeling cost.
Approach:	They propose a path-based few-shot setting and a strict path-basic evaluation metric to further explore few- shot HTC tasks.
Outcome:	The proposed framework outperforms those who inject hierarchy through graph encoders on three popular HTC datasets under the few-shot setting.

Copied to clipboard

Hao Liu, Zi-Yi Dou, Yixin Wang, Nanyun Peng, Yisong Yue

Thinking Traps in Long Chain-of-Thought: A Measurable Study and Trap-Aware Adaptive Restart (2026.findings-acl)

Challenge:	Language agents are increasingly used to perform tasks and interact with a variety of external tools to achieve specific, goal-oriented objectives.
Approach:	They propose a tool calibration tool called ProbeCal which recalibrates the internal probabilities of tool-using language agents to better reflect the actual effectiveness of tool.
Outcome:	The proposed model significantly improves off-the-shelf language models in tool-using applications.

Copied to clipboard

null Chenkang, Fan Yu, Junjie Nian, Sihan Zhao, Zhuoka Feng, Zijun Yao, Wang Heng, Yu Minshen, Yixin Cao

Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models (2025.findings-emnlp)

Challenge:	Experiments show that extended generation does not guarantee correctness . a recurring pattern in Long-CoT failures is a problem for large reasoning models .
Approach:	They propose a test-time control framework that truncates the trajectory before the trap segment and adaptively restarts decoding.
Outcome:	Experiments show that TAAR improves reasoning performance without fine-tuning model parameters.

Copied to clipboard

Haibo Wang, Zhiyang Xu, Yu Cheng, Shizhe Diao, Yufan Zhou, Yixin Cao, Qifan Wang, Weifeng Ge, Lifu Huang

Robust Prompt Optimization for Large Language Models Against Distribution Shifts (2023.emnlp-main)

Challenge:	Video Large Language Models (VLMs) have been praised for their performance in coarse-grained video understanding but still face ineffective temporal grounding and inadequate timestamp representations.
Approach:	They propose a novel Video-LLM that senses and reasoned over specific video moments with fine-grained temporal precision.
Outcome:	The proposed model surpasses existing models in fine-grained video understanding tasks and exhibits strong potential as a general video understanding assistant.

Copied to clipboard

Moxin Li, Wenjie Wang, Fuli Feng, Yixin Cao, Jizhi Zhang, Tat-Seng Chua

VIB-Probe: Detecting and Mitigating Hallucinations in Vision-Language Models via Variational Information Bottleneck (2026.acl-long)

Challenge:	Existing research has explored automatic prompt optimization methods to eliminate manual effort in identifying effective prompts for a given task.
Approach:	They propose a framework for prompt optimization that can be generalized to an unlabeled target group.
Outcome:	The proposed framework improves on target group and source group while generalizing to unlabeled target group.

Copied to clipboard

Feiran Zhang, Yixin Wu, Zhenghua Wang, Xiaohua Wang, Changze Lv, Xuanjing Huang, Xiaoqing Zheng

Learning from Miscellaneous Other-Class Words for Few-shot Named Entity Recognition (2021.acl-long)

Challenge:	Existing hallucination detection methods rely on external verification tools . however, entanglement of visual-linguistic syntax and noise makes it difficult to detect hallucis .
Approach:	They propose a hallucination detection framework that leverages the Variational Information Bottleneck theory to detect hallucinic heads and to infer hallucication mitigation strategies.
Outcome:	The proposed framework outperforms baselines in hallucinations and noise detection environments.

Copied to clipboard

Meihan Tong, Shuai Wang, Bin Xu, Yixin Cao, Minghui Liu, Lei Hou, Juanzi Li

Low-Resource NLP

Challenge:	Existing methods to classify named entity mentions with fewshots fail to differentiate rich semantics in other-class words, which will aggravate overfitting under few shot scenario.
Approach:	They propose a model that can automatically induce different unde- fined classes from the other class to improve few-shot Named Entity Recognition (NER) .
Outcome:	The proposed model outperforms five state-of-the-art models in 1- shot and 5-shots settings on four NER bench marks.

MoPrune: Scene-Guided Motion-Aware Token Pruning for Efficient Video Large Language Models (2026.findings-acl)

Copied to clipboard

Wenhao Hong, Ziyang Wang, Yixin Zhang, Zilei Wang

UNICORN: A Unified Causal Video-Oriented Language-Modeling Framework for Temporal Video-Language Tasks (2024.emnlp-main)

Challenge:	Prior approaches to token pruning ignore video dynamics and the fact that different scenes exhibit different redundancy patterns.
Approach:	They propose a token pruning framework that is train-free and scene-guided to accelerate VideoLLMs by removing redundant visual information from video frames.
Outcome:	MoPrune is a training-free, scene-guided and motion-centric token pruning framework for accelerating VideoLLMs.

Copied to clipboard

Yuanhao Xiong, Yixin Nie, Haotian Liu, Boxin Wang, Jun Chen, Rong Jin, Cho-Jui Hsieh, Lorenzo Torresani, Jie Lei

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

Challenge:	Recent advances in large multimodal models have encouraged the development of large multi-modal models . however, it is unclear how to extend these models to the more complex video domain .
Approach:	They propose a visual instruction tuning framework to address temporal video-language tasks . they collect a dataset and fine-tune the framework on instruction-following data .
Outcome:	The proposed model can perform better on established temporal video-language tasks without training objectives and intensive pre-training.

Copied to clipboard

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

Psychological Counseling Cannot Be Achieved Overnight: Automated Psychological Counseling Through Multi-Session Conversations (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

Bichen Wang, Junzhe Wang, Yixin Sun, Xing Fu, Yanyan Zhao, Bing Qin

Dialogue Systems & Conversational Agents

Challenge:	Existing studies on single-session counseling are limited to a single-session setting.
Approach:	They propose to use a large language model to deliver automated psychological counseling to a dataset constructed using real client profiles from publicly available psychological case reports.
Outcome:	The proposed model performs better than baseline models across multiple sessions.

Permutative Preference Alignment from Listwise Ranking of Human Judgments (2025.emnlp-main)

Copied to clipboard

Yang Zhao, Yixin Wang, Mingzhang Yin

Challenge:	Existing methods to align Large Language Models with human preferences are based on the Bradley-Terry model, but when multiple responses are available, the B-T model fails to guarantee an accurate list ranking of the responses.
Approach:	They propose an offline listwise approach that incorporates the Normalized Discounted Cumulative Gain (NDCG) as an alternative training objective for LLM alignment.
Outcome:	The proposed approach outperforms existing pairwise and listwise methods on evaluation sets and general benchmarks such as AlpacaEval.

Text-guided 3D Human Generation from 2D Collections (2023.findings-emnlp)

Copied to clipboard

Tsu-Jui Fu, Wenhan Xiong, Yixin Nie, Jingyu Liu, Barlas Oguz, William Wang

Mitigating Position Bias in Transformers via Layer-Specific Positional Embedding Scaling (2026.findings-acl)

Challenge:	3D human modeling is used for engaging interaction in gaming, film, and animation. however, the customization of characters is crucial for creativity and scalability.
Approach:	They propose a 3D human generation using fashion descriptions to enhance 3D geometry transformation and fine-grained consistency.
Outcome:	The proposed model can generate a 3D human, guided by a fashion description, with high efficiency.

Copied to clipboard

Zhenghua Wang, Yiran Ding, Changze Lv, Yixin Wu, Tianlong Li, Zhibo Xu, Muling Wu, Tianyuan Shi, Shizheng Li, Qi Qian, Xuanjing Huang, Xiaoqing Zheng

A Comprehensive Evaluation of Large Language Models on Legal Judgment Prediction (2023.findings-emnlp)

Challenge:	Existing methods to address the "lost-in-the-middle" problem suffer from high latency or suboptimal hand-crafted scaling strategies.
Approach:	They propose a layer-specific positional embedding scaling method that assigns distinct scaling factors to each layer.
Outcome:	Experiments show that the proposed method mitigates positional attention bias and delivers consistent improvements across multiple long-context benchmarks.

Copied to clipboard

Ruihao Shui, Yixin Cao, Xiang Wang, Tat-Seng Chua

CRMArena: Understanding the Capacity of LLM Agents to Perform Professional CRM Tasks in Realistic Environments (2025.naacl-long)

Challenge:	Large language models (LLMs) have demonstrated great potential for domain-specific applications, such as the law domain.
Approach:	They propose a framework to investigate LLMs' competence in the law domain by using similar cases and multi-choice options.
Outcome:	The proposed solutions can be extended to other domains to facilitate evaluations in other domain.

Copied to clipboard

Kung-Hsiang Huang, Akshara Prabhakar, Sidharth Dhawan, Yixin Mao, Huan Wang, Silvio Savarese, Caiming Xiong, Philippe Laban, Chien-Sheng Wu

Challenge:	Existing benchmarks for evaluating CRM agents on work-related tasks are limited due to data privacy concerns.
Approach:	They propose a benchmark to evaluate AI agents on real-world CRM tasks . they use 16 commonly used industrial objects with high interconnectivity to simulate real data distributions.
Outcome:	The new benchmark evaluates AI agents on real-world customer service tasks . it includes 16 commonly used industrial objects with high interconnectivity . the results highlight the need for enhanced agent capabilities in function-calling and rule-following .

Mitigating Hallucinations in VLMs: Enhancing Visual Attention via Head-Wise Perturbation (2026.findings-acl)

Copied to clipboard

Zhenghua Wang, Yixin Wu, Feiran Zhang, Qi Qian, Changze Lv, Xuanjing Huang, Xiaoqing Zheng

Causal Inference for Human-Language Model Collaboration (2024.naacl-long)

Challenge:	Vision–Language Models (VLMs) have demonstrated strong capabilities in tasks that require joint understanding of text and images.
Approach:	They propose a strategy that incorporates head-wise attention perturbation via continuous multiplicative noise coupled with a visual-guided loss focused on vision-sensitive text tokens to promote a more balanced attention distribution.
Outcome:	The proposed approach outperforms baseline models on three benchmarks and consistently outperformed the baseline model.

Copied to clipboard

Bohan Zhang, Yixin Wang, Paramveer Dhillon

Balancing Forget Quality and Model Utility: A Reverse KL-Divergence Knowledge Distillation Approach for Better Unlearning in LLMs (2025.naacl-long)

Challenge:	In this paper, we examine the collaborative dynamics between humans and language models where the interaction involves LMs proposing text segments and humans editing or responding to these segments.
Approach:	They propose a causal estimand to estimate the incremental stylistic effect (ISE) of various interaction strategies in dynamic human-LM collaborations.
Outcome:	The proposed estimand reduces confounding and significantly improves counterfactual estimation over a set of competitive baselines.

Copied to clipboard

Bichen Wang, Yuzhe Zi, Yixin Sun, Yanyan Zhao, Bing Qin

QRMeM: Unleash the Length Limitation through Question then Reflection Memory Mechanism (2024.findings-emnlp)

Challenge:	Existing methods for unlearning large language models struggle with forget quality and model utility, leading to over-unlearning or partial unlearning.
Approach:	They propose a method that uses reverse KL-divergence based knowledge distillation for unlearning to achieve significant forget quality while maintaining model utility.
Outcome:	The proposed method outperforms existing methods in forget quality and model utility with larger unlearning datasets.

Copied to clipboard

Bo Wang, Heyan Huang, Yixin Cao, Jiahao Ying, Wei Tang, Chong Feng

Question Answering

Challenge:	Existing methods for processing large textual content face insufficient adaptation to task-specific needs and missing multi-segmentation relationships.
Approach:	They propose a question then reflection memory mechanism which integrates a dual-structured memory pool and a structured graph guidance to facilitate a reflective trial-and-error approach for navigating and identifying relevant segments.
Outcome:	The proposed model achieves superior performance on multiple-choice questions and multi-doc QA.

CPRM: A LLM-based Continual Pre-training Framework for Relevance Modeling in Commercial Search (2025.naacl-industry)

Copied to clipboard

Kaixin Wu, Yixin Ji, Zeyuan Chen, Qiang Wang, Cunxiang Wang, Hong Liu, Baijun Ji, Xu Jia, Zhongyi Liu, Jinjie Gu, Yuan Zhou, Linjian Mo

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

Challenge:	Relevance modeling between queries and items is a key component of commercial search engines.
Approach:	They propose a framework for continual pre-training of LLMs to enhance domain knowledge . they employ queries and multi-field item to jointly pre-train for enhancing domain knowledge.
Outcome:	The proposed model achieves convincing performance compared to strong baselines.

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.

Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems (2025.emnlp-main)

Copied to clipboard

Xu Shen, Yixin Liu, Yiwei Dai, Yili Wang, Rui Miao, Yue Tan, Shirui Pan, Xin Wang

Green & Sustainable NLP

Challenge:	Empirical studies for communication topology design often overlook why and when sparse and dense topologies help or hinder collaboration.
Approach:	They propose a topology design approach that balances error suppression and beneficial information propagation by fusing connectivity patterns from dense and sparse graphs.
Outcome:	The proposed topology design achieves superior performance across tasks with sparse and dense graphs.

Few-shot Event Detection: An Empirical Study and a Unified View (2023.acl-long)

Copied to clipboard

Yubo Ma, Zehao Wang, Yixin Cao, Aixin Sun