Papers by Xun Wang

UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generation (2024.acl-long)

Challenge:	Large language models (LLMs) can generate natural language texts for various domains and tasks, but their potential for clinical text mining is under-explored.
Approach:	They propose a pragmatic taxonomy for AD sign and symptom progression based on expert knowledge and train a system to detect AD-related signs and symptoms from EHRs.
Outcome:	The proposed taxonomy outperforms existing methods using only the gold dataset and silver datasets.

Copied to clipboard

Xun Liang, Shichao Song, Simin Niu, Zhiyu Li, Feiyu Xiong, Bo Tang, Yezhaohui Wang, Dawei He, Cheng Peng, Zhonghao Wang, Haiying Deng

LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering (2025.acl-long)

Challenge:	Large language models (LLMs) produce hallucinated text, compromising their practical utility in professional contexts.
Approach:	They have developed an unconstrained hallucination generation evaluation benchmark that contains hallucines generated by large language models with minimal restrictions.
Outcome:	The proposed benchmarks are based on a Chinese-language dataset that is lacking in the field.

Copied to clipboard

Jinhe Bi, Yujun Wang, Haokun Chen, Xun Xiao, Artur Hecker, Volker Tresp, Yunpu Ma

LlamaCare: An Instruction Fine-Tuned Large Language Model for Clinical NLP (2024.lrec-main)

Challenge:	Multimodal Large Language Models (MLLMs) enhance visual tasks by integrating visual representations into large language models.
Approach:	They propose a method to re-balance modalities by steering visual representations . they propose LLaVA Steering, a platform that enables rapid customization of MLLMs a component-based architecture .
Outcome:	The proposed model re-balances the modalities of visual representations in large language models . the model requires 500 times fewer trainable parameters than LoRA while maintaining comparable performance .

Copied to clipboard

Rumeng Li, Xun Wang, Hong Yu

AssistedDS: Benchmarking How External Domain Knowledge Assists LLMs in Automated Data Science (2025.findings-emnlp)

Challenge:	Large language models have shown remarkable abilities in generating natural texts . applying LLMs to clinical domain still poses significant challenges .
Approach:	They propose a method of instruction fine-tuning for adapting large language models to clinical domains . they generate instructions, inputs, and outputs covering a wide spectrum of clinical services .
Outcome:	The proposed method outperforms baseline LLMs on clinical tasks . it requires domain adaptation, task-specific learning, and reliability .

Copied to clipboard

An Luo, Xun Xian, Jin Du, Fangqiao Tian, Ganghua Wang, Ming Zhong, Shengchun Zhao, Xuan Bi, Zirui Liu, Jiawei Zhou, Jayanth Srinivasa, Ashish Kundu, Charles Fleming, Mingyi Hong, Jie Ding

Robustness in NLP

Challenge:	Large language models (LLMs) have advanced the automation of data science workflows, yet it remains unclear whether they can critically leverage external domain knowledge as human data scientists do in practice.
Approach:	They propose a benchmark to evaluate how large language models handle external domain knowledge in tabular prediction tasks.
Outcome:	The proposed model evaluates whether it can critically leverage external domain knowledge as human data scientists do in practice.

Assistant-Guided Mitigation of Teacher Preference Bias in LLM-as-a-Judge (2025.findings-emnlp)

Copied to clipboard

Zhuo Liu, Moxin Li, Xun Deng, Qifan Wang, Fuli Feng

Challenge:	LLM-as-a-Judge uses large language models to evaluate the quality of LLM generated responses, but training proxy judge models using evaluation data generated by powerful teacher models introduces a critical yet previously overlooked issue: teacher preference bias.
Approach:	They propose a new setting that incorporates an additional assistant model, which is not biased toward the teacher model’s responses, to complement the training data.
Outcome:	The proposed model reduces teacher preference bias while maintaining strong performance across six evaluation benchmarks.

Maximum Score Routing For Mixture-of-Experts (2025.findings-acl)

Copied to clipboard

Bowen Dong, Yilong Fan, Yutao Sun, Zhenyu Li, Tengyu Pan, Zhou Xun, Jianyong Wang

Green & Sustainable NLP

Challenge:	Traditional mixture-of-experts (MoE) networks impose an expert capacity constraint to ensure GPU-friendly computation.
Approach:	They propose a routing paradigm that dynamically allocates input tokens to top-k experts through differentiable sparse transformations, enabling scalable model capacity while preserving computational efficiency.
Outcome:	The proposed model achieves lower training losses and higher evaluation scores at equivalent FLOPs compared to constrained and unconstrained baselines.

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

Copied to clipboard

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

MimicLM: Zero-Shot Voice Imitation through Autoregressive Modeling of Pseudo-Parallel Speech Corpora (2026.findings-acl)

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

Copied to clipboard

Tao Feng, Yuxiang Wang, Yuancheng Wang, Xueyao Zhang, Dekun Chen, Chaoren Wang, Xun Guan, Zhizheng Wu

Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs (2024.findings-acl)

Challenge:	Existing approaches to voice imitation use complex model design and a quality ceiling when synthetic speech is used as training sources.
Approach:	They propose a model that uses synthetic speech as training sources while retaining real recordings as targets.
Outcome:	The proposed model outperforms existing methods in naturalness while maintaining competitive similarity scores across speaker identity, accent, and emotion dimensions.

Copied to clipboard

Xun Liang, Hanyu Wang, Shichao Song, Mengting Hu, Xunzhi Wang, Zhiyu Li, Feiyu Xiong, Bo Tang

Multimodality

Challenge:	Controlled Text Generation (CTG) aims to produce texts that exhibit specific desired attributes.
Approach:	They propose a pluggable CTG framework for Large Language Models to control text . they use attribute scorers to evaluate attributes of sentences and construct dynamic attribute graphs .
Outcome:	The proposed framework achieves a peak improvement of 19.29% over baseline methods in two tasks.

Eureka: Neural Insight Learning for Knowledge Graph Reasoning (2022.coling-1)

Copied to clipboard

Alex X. Zhang, Xun Liang, Bo Wu, Xiangping Zheng, Sensen Zhang, Yuhui Guo, Jun Wang, Xinyao Liu

Structured Data in NLP

Challenge:	Existing knowledge embedding methods have limited performance on knowledge graph reasoning tasks . eureka is empowered to learn seen relations with sufficient training triples .
Approach:	They propose a neural insight learning framework called Eureka to bridge the “seen” to “unsea” gap . Eureca is empowered to learn seen relations with sufficient training triples while providing flexibility to learn unseen relations given only one trigger .
Outcome:	The proposed framework outperforms state-of-the-art models on seen and unseen relations . it can learn seen and unseen relationships with sufficient training triples .

ODD: A Benchmark Dataset for the Natural Language Processing Based Opioid Related Aberrant Behavior Detection (2024.naacl-long)

Copied to clipboard

Sunjae Kwon, Xun Wang, Weisong Liu, Emily Druhl, Minhee Sung, Joel Reisman, Wenjun Li, Robert Kerns, William Becker, Hong Yu

NoteChat: A Dataset of Synthetic Patient-Physician Conversations Conditioned on Clinical Notes (2024.findings-acl)

Challenge:	Opioid related aberrant behaviors (ORABs) present novel risk factors for opioid overdose.
Approach:	They propose to use a biomedical natural language processing benchmark dataset to classify ORABs from patients’ EHR notes into nine categories: confirmed aberrant behavior, suggested aberrant behaviors, Opioids, indication, diagnosed opioid dependency, Benzodiazepines, medication changes, and Central Nervous System-related.
Outcome:	The proposed dataset outperforms two state-of-the-art models in most categories and the gains are especially higher among uncommon classes.

Copied to clipboard

Junda Wang, Zonghai Yao, Zhichao Yang, Huixue Zhou, Rumeng Li, Xun Wang, Yucheng Xu, Hong Yu

Dialogue Systems & Conversational Agents

Challenge:	NoteChat is a cooperative multi-agent framework for generating patient-physician dialogues . evaluator finds it outperforms state-of-the-art models for generating clinical notes . clinical documentation is largely done by physicians at both steps .
Approach:	They propose a cooperative multi-agent framework leveraging Large Language Models to generate patient-physician dialogues.
Outcome:	The proposed framework outperforms state-of-the-art models for generating clinical notes . it can engage patients directly and help clinical documentation, a leading cause of physician burnout .

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

Copied to clipboard

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

Smart Word Suggestions for Writing Assistance (2023.findings-acl)

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

Chenshuo Wang, Shaoguang Mao, Tao Ge, Wenshan Wu, Xun Wang, Yan Xia, Jonathan Tien, Dongyan Zhao

Challenge:	Using word suggestions, writing assistance is a widely used application of natural language processing (NLP) . a task is performed to identify words or phrases that require improvement and provide substitution suggestions for each improvable target.
Approach:	They propose a task and benchmark to help writers improve word usage . they use human-labeled data and a distantly supervised dataset for testing .
Outcome:	The proposed task and benchmark aims to improve word usage in writing aids.

World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering (2024.emnlp-main)

Copied to clipboard

Jiacong Wang, Bohong Wu, Haiyong Jiang, Zhou Xun, Xin Xiao, Haoyuan Guo, Jun Xiao

Multimodality

Challenge:	Recent advances in Vision-Language Models and the scarcity of high-quality multi-modal alignment data have inspired numerous researches on synthetic VLM data generation.
Approach:	They propose a multi-modal data construction pipeline that organizes the final output into a Python code format.
Outcome:	The proposed pipeline improves visual question answering and visual grounding benchmarks across different VLMs.

Watch Every Step! LLM Agent Learning via Iterative Step-level Process Refinement (2024.emnlp-main)

Copied to clipboard

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

ALYMPICS: LLM Agents Meet Game Theory (2025.coling-main)

Challenge:	Recent approaches to enhance agent performance focus on outcome rewards, which may lead to errors or suboptimal actions due to the absence of process supervision signals.
Approach:	They propose a step-level framework that provides detailed step-by-step guidance to enhance agent training by using Monte Carlo methods.
Outcome:	The proposed framework outperforms strong baselines on three tasks and shows that it is effective in augmenting efficiency and its applicability to diverse models.

Copied to clipboard

Shaoguang Mao, Yuzhe Cai, Yan Xia, Wenshan Wu, Xun Wang, Fengyi Wang, Qiang Guan, Tao Ge, Furu Wei

Linguistics & Cognitive NLP

Challenge:	Alympics provides a framework for simulating human-like strategic interactions with Large Language Model (LLM) agents.
Approach:	They propose a framework utilizing Large Language Models (LLM) agents for empirical game theory research.
Outcome:	The proposed framework can be used to study human-like strategic interactions with large language model (LLM) agents in a game on the multi-round auction of scarce survival resources.

CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference (2025.acl-long)

Copied to clipboard

Jinglong Luo, Guanzhong Chen, Yehong Zhang, Shiyu Liu, Hui Wang, Yue Yu, Xun Zhou, Yuan Qi, Zenglin Xu

EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety (2025.emnlp-main)

Challenge:	Existing privacy-preserving Transformer Inference frameworks suffer from high computational overhead and performance losses.
Approach:	They propose a framework that integrates random permutations and SMPC to address the "impossible trinity" CENTAUR resists diverse data reconstruction attacks and boosts inference speed by 5.030.4 times .
Outcome:	CENTAUR achieves an unprecedented balance between privacy, efficiency, and performance.

Copied to clipboard

Jiahao Qiu, Yinghui He, Xinzhe Juan, Yimin Wang, Yuhan Liu, Zixin Yao, Yue Wu, Xun Jiang, Ling Yang, Mengdi Wang

Developing a Reliable, Fast, General-Purpose Hallucination Detection and Mitigation Service (2025.naacl-industry)

Challenge:	EmoAgent evaluates and mitigates mental health hazards in human-AI interactions, especially for vulnerable human users with psychological disorders.
Approach:	EmoAgent is a multi-agent AI framework designed to evaluate and mitigate mental health hazards in human-AI interactions.
Outcome:	EmoAgent evaluates and mitigates mental health hazards in human-AI interactions.

Copied to clipboard

Song Wang, Xun Wang, Jie Mei, Yujia Xie, Si-Qing Chen, Wayne Xiong

Reasoning

Challenge:	Hallucination is a problem in large language models that produce incorrect output . authors propose a reliable and high-speed production system to detect and rectify hallucinations .
Approach:	They propose a high-speed production system that detects hallucinations in LLMs . they propose NER, natural language inference, span-based detection and a rewriting mechanism .
Outcome:	The proposed system detects a wide range of hallucinations in LLM responses.

Efficient Federated Learning on Knowledge Graphs via Privacy-preserving Relation Embedding Aggregation (2022.findings-emnlp)

Copied to clipboard

Kai Zhang, Yu Wang, Hongyi Wang, Lifu Huang, Carl Yang, Xun Chen, Lichao Sun

SCALE: Synergized Collaboration of Asymmetric Language Translation Engines (2024.findings-acl)

Challenge:	Existing frameworks that share entity embeddings of knowledge graphs (KGs) would incur a severe privacy leakage.
Approach:	They propose a new attack method that aims to recover the original embedding information based on the known entity embeddables of FedE.
Outcome:	The proposed framework can be used to infer whether a specific relation exists in a private client.

Copied to clipboard

Xin Cheng, Xun Wang, Tao Ge, Si-Qing Chen, Furu Wei, Dongyan Zhao, Rui Yan

Multilinguality

Challenge:	In this paper, we introduce SCALE, a collaborative framework that connects a compact Specialized Translation Model (STM) and a general-purpose Large Language Model (LLM) as one unified translation engine.
Approach:	They propose a collaborative framework that connects a Specialized Translation Model (STM) and a general-purpose Large Language Model (LLM) as one unified translation engine.
Outcome:	The proposed framework outperforms both LLMs and supervised models in high-resource or challenging low-resourced settings.

K-Level Reasoning: Establishing Higher Order Beliefs in Large Language Models for Strategic Reasoning (2025.naacl-long)

Copied to clipboard

Yadong Zhang, Shaoguang Mao, Tao Ge, Xun Wang, Yan Xia, Man Lan, Furu Wei

PibE-MPP: A Play-it-by-Ear Masking Performance Plug-in for LLMs (2026.findings-acl)

Challenge:	Strategic reasoning requires Large Language Model (LLM) agents to adapt their strategies dynamically in multi-agent environments.
Approach:	They propose a framework that enables Large Language Models to achieve varying levels of strategic depth by recursive mechanisms that allow agents to form higher order beliefs about others' beliefs.
Outcome:	The proposed framework enables LLMs to achieve varying levels of strategic depth, allowing agents to form higher order beliefs—beliefs about others’ beliefs.

Copied to clipboard

Mengwei Wang, Simin Niu, Xun Liang, Yuefeng Ma, Sensen Zhang, Jiawei Yang, Shichao Song, Hanyu Wang, Huayi Lai

Counterfactual Active Learning for Out-of-Distribution Generalization (2023.acl-long)

Challenge:	Random masking is a widely adopted classic baseline in large language models (LLMs).
Approach:	They propose a play-it-by-ear masking performance plug-in which enables LLMs to adaptively select masking target combinations for each task.
Outcome:	The proposed performance plug-in retains the advantages and mitigates the drawbacks of random masking in large language models.

Copied to clipboard

Xun Deng, Wenjie Wang, Fuli Feng, Hanwang Zhang, Xiangnan He, Yong Liao

TrojFSP: Trojan Insertion in Few-shot Prompt Tuning (2024.naacl-long)

Challenge:	Existing studies on active learning methods focus on the out-of-distribution generalization of out- of-distortion samples.
Approach:	They propose a counterfactual active learning approach that empowers active learning with counterfact thinking to bridge the seen samples with unseen cases.
Outcome:	The proposed approach outperforms existing active learning methods on public datasets with comparable IID performance.

Copied to clipboard

Mengxin Zheng, Jiaqi Xue, Xun Chen, Yanshan Wang, Qian Lou, Lei Jiang

Harnessing and Evaluating the Intrinsic Extrapolation Ability of Large Language Models for Vehicle Trajectory Prediction (2025.naacl-long)

Challenge:	Prompt tuning on a few data samples presents security issues, e.g., Trojan attacks.
Approach:	They propose a method to transfer established data poisoning attacks directly to few-shot prompt tuning, a technique to address the poisoned imbalance issue.
Outcome:	The proposed method achieves an ASR of over 99% while maintaining negligible decreases in CDA.

Copied to clipboard

Jiawei Liu, Yanjiao Liu, Xun Gong, Tingting Wang, Hong Chen, Yunfeng Hu

SecCoder: Towards Generalizable and Robust Secure Code Generation (2024.emnlp-main)

Challenge:	Emergent abilities of large language models (LLMs) have advanced their application in autonomous vehicle research.
Approach:	They propose a framework that leverages LLMs’ built-in extrapolation capabilities for vehicle trajectory prediction, enabling them to understand traffic agents' behavior and interactions over time.
Outcome:	The proposed framework enables off-the-shelf, frozen LLMs to achieve competitive trajectory prediction performance with qualitative analyses revealing their enhanced understanding of complex, multi-agent traffic scenarios.

Copied to clipboard

Boyu Zhang, Tianyu Du, Junkai Tong, Xuhong Zhang, Kingsum Chow, Sheng Cheng, Xun Wang, Jianwei Yin

Programming Languages in NLP

Challenge:	Existing secure code generation methods have limited generalizability to unseen test cases and poor robustness against the attacked model, leading to safety failures in code generation.
Approach:	They propose a generalizable and robust secure code generation method SecCoder by using in-context learning and the safe demonstration.
Outcome:	The proposed method achieves a significant security improvement of 7.20% on unseen test cases and better robustness against the attacked model.

SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model (2025.acl-long)

Copied to clipboard

Xun Liang, Simin Niu, Zhiyu Li, Sensen Zhang, Hanyu Wang, Feiyu Xiong, Zhaoxin Fan, Bo Tang, Jihao Zhao, Jiawei Yang, Shichao Song, Mengwei Wang

Robustness in NLP

Challenge:	Existing approaches to integrating external knowledge into large language models (LLMs) however, the incorporation of external knowledge increases the vulnerability of LLMs .
Approach:	They propose a benchmark to evaluate the RAG security using a dataset . they classify attack tasks into silver noise, inter-context conflict, soft ad, and white Denial-of-Service .
Outcome:	The proposed benchmark evaluates the security of RAG against 14 representative RAG components.

Psyche-R1: Towards Reliable Psychological LLMs through Unified Empathy, Expertise, and Reasoning (2026.acl-long)

Copied to clipboard

Chongyuan Dai, Jinpeng Hu, Hongchang Shi, Zhuo Li, Dan Guo, Xun Yang, Meng Wang

Dialogue Systems & Conversational Agents

Challenge:	Recent reasoning-augmented LLMs have demonstrated impressive capabilities across a wide range of domains owing to their exceptional text understanding capabilities.
Approach:	They propose a Chinese psychological LLM that integrates empathy, psychological expertise, and reasoning.
Outcome:	The proposed model produces over 75k high-quality psychological questions paired with detailed rationales, generated through and iterative prompt-rationale optimization procedure, along with 73k empathetic dialogues.

ContextCheck: Sentence-Level Faithfulness Verification with Context-Aware Disambiguation (2026.findings-acl)

Copied to clipboard

Yueqin Yin, Yaxi Li, Xin Liu, Xun Wang, Kaiqiang Song, Simin Ma, Shujian Liu, Sathish Reddy Indurthi, Haoyun Deng, Pengcheng He, Mingyuan Zhou, Song Wang

Challenge:	Large language models often hallucinate, producing content that is factually incorrect or not grounded in the sources.
Approach:	They propose a framework for sentence-level faithfulness verification with context-aware disambiguation.
Outcome:	The proposed framework improves Macro F1 by over 10 points compared to baselines on three context-dependent datasets.

Navigating the OverKill in Large Language Models (2024.acl-long)

Copied to clipboard

Chenyu Shi, Xiao Wang, Qiming Ge, Songyang Gao, Xianjun Yang, Tao Gui, Qi Zhang, Xuanjing Huang, Xun Zhao, Dahua Lin