Papers by Xiaolong Wang

Continual Learning Long Short Term Memory (2020.findings-emnlp)

Challenge:	Existing benchmarks for evaluating MLLMs have not addressed active perception . a novel benchmark is proposed to evaluate active perception in ML models .
Approach:	They propose a benchmark to evaluate active perception in Multimodal Large Language Models . they restrict the perceptual field of a model and require it to actively zoom or shift it .
Outcome:	The proposed benchmark focuses on a specialized form of Visual Question Answering (VQA) that eases and quantifies the evaluation yet challenging for existing MLLMs.

Copied to clipboard

Xin Guo, Yu Tian, Qinghan Xue, Panos Lampropoulos, Steven Eliuk, Kenneth Barner, Xiaolong Wang

Beyond "I Don’t Know": Evaluating LLM Self-Awareness in Discriminating Data and Model Uncertainty (2026.acl-long)

Challenge:	Existing approaches to prevent catastrophic forgetting in neural networks are based on the stability-plasticity dilemma, but only a limited size of old data is available.
Approach:	They propose a Continual Learning Long Short Term Memory cell in Recurrent Neural Network (RNN) that considers the state of each individual task's output gates and the correlation of the states between tasks.
Outcome:	The proposed method significantly improves on spoken language understanding tasks over state-of-the-art approaches.

Copied to clipboard

Jingyi Ren, Ante Wang, Yunghwei Lai, Xiaolong Wang, Linlu Gong, Weitao Li, Weizhi Ma, Yang Liu

Challenge:	Prior studies treat refusal as a generic "I don't know" lack of distinction limits downstream action decisions like requesting clarification or invoking external tools.
Approach:	They propose a benchmark to evaluate explicit uncertainty attribution in large language models.
Outcome:	The proposed method improves uncertainty attribution while preserving answer accuracy.

Perspective Transition of Large Language Models for Solving Subjective Tasks (2025.findings-acl)

Copied to clipboard

Xiaolong Wang, Yuanchi Zhang, Ziyue Wang, Yuzhuang Xu, Fuwen Luo, Yile Wang, Peng Li, Yang Liu

NeuInfer: Knowledge Inference on N-ary Facts (2020.acl-main)

Challenge:	Large language models (LLMs) have revolutionized the field of natural language processing . performance of LLMs on subjective tasks is limited, authors say .
Approach:	They propose a method that allows LLMs to select between direct, role, and third-person perspectives for best way to solve corresponding subjective problem.
Outcome:	The proposed method outperforms widely used single fixed perspective based methods on 12 subjective tasks.

Copied to clipboard

Saiping Guan, Xiaolong Jin, Jiafeng Guo, Yuanzhuo Wang, Xueqi Cheng

Knowledge Representation

Challenge:	Existing studies on knowledge inference on binary facts have focused on finding out connotative valid facts.
Approach:	They propose a neural network model, NeuInfer, for knowledge inference on n-ary facts.
Outcome:	The proposed model can cope with the task to infer an unknown element in a whole fact, while ignoring the binary facts.

DEEM: Dynamic Experienced Expert Modeling for Stance Detection (2024.lrec-main)

Copied to clipboard

Xiaolong Wang, Yile Wang, Sijie Cheng, Peng Li, Yang Liu

Sentiment Analysis

Challenge:	Existing work on stance detection tasks using large language models shows promising results, but it may not be able to provide detailed background knowledge.
Approach:	They propose a method which leverages the generated experienced experts and lets LLMs reason in a semi-parametric way.
Outcome:	The proposed method outperforms methods with self-consistency reasoning and reduces bias.

Social Welfare Function Leaderboard: On the Emergence of LLM Agents as the Welfare Dictator (2026.findings-acl)

Copied to clipboard

Zhengliang Shi, Ruotian Ma, Jen-tse Huang, Xinbei Ma, Xingyu Chen, Mengru Wang, Qu Yang, Yue Wang, Fanghua Ye, Ziyang Chen, Shanyi Wang, Cixing LI, Wenxuan Wang, Zhaopeng Tu, Xiaolong Li, Zhaochun Ren, Liefeng Bo

MulDimIF: A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models (2026.findings-acl)

Challenge:	Large language models (LLMs) are increasingly entrusted with high-stakes decisions that affect human welfare.
Approach:	They evaluate 20 state-of-the-art Large language models (LLMs) and 20 LLM dictators to create a social welfare function benchmark.
Outcome:	The proposed model creates dilemma between maximizing collective efficiency and ensuring distributive fairness.

Copied to clipboard

Junjie Ye, Caishuang Huang, Zhuohan Chen, Wenjie Fu, Chenyuan Yang, Leyi Yang, Yilong Wu, Peng Wang, Meng Zhou, Xiaolong Yang, Tao Gui, Qi Zhang, Zhongchao Shi, Jianping Fan, Xuanjing Huang

Too Good to be Bad: On the Failure of LLMs to Role-Play Villains (2026.findings-acl)

Challenge:	Existing research has focused on constraint categories, offering little guidance for improving instruction following abilities.
Approach:	They propose a multi-dimensional constraint framework that allows for instruction following . they construct 9,106 code-verifiable samples and evaluate 18 LLMs .
Outcome:	The proposed framework improves instruction following performance without compromising general performance.

Copied to clipboard

Zihao Yi, Qingxuan Jiang, Ruotian Ma, Xingyu Chen, Qu Yang, Mengru Wang, Fanghua Ye, Ying Shen, Zhaopeng Tu, Xiaolong Li, Liefeng Bo

Challenge:	Large Language Models (LLMs) are increasingly tasked with creative generation, but their ability to portray non-prosocial, antagonistic personas remains largely unexamined.
Approach:	They propose a moral alignment benchmark to test the safety of large language models . they find that models struggle with traits directly antithetical to safety principles .
Outcome:	The proposed model fails to accurately portray morally ambiguous or villainous characters . the model fails most with traits directly antithetical to safety principles .

KnowCoder-X: Boosting Multilingual Information Extraction via Code (2025.findings-acl)

Copied to clipboard

Yuxin Zuo, Wenxuan Jiang, Wenxuan Liu, Zixuan Li, Long Bai, Hanbin Wang, Yutao Zeng, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

Multilinguality

Challenge:	Empirical evidence indicates that Large Language Models exhibit spontaneous cross-lingual alignment in Information Extraction (IE) however, a significant imbalance across languages persists, highlighting an underlying deficiency.
Approach:	They propose a code LLM with advanced cross-lingual and multilingual capabilities for universal IE that standardizes the representation of multilingual schemas using Python classes and conducts IE alignment instruction tuning on translated instance prediction task.
Outcome:	The proposed model surpasses ChatGPT and SoTA by 30.17% without training in 29 unseen languages and significantly improves cross-lingual IE transferability.

Hallucination Detection in Structured Query Generation via LLM Self-Debating (2025.findings-emnlp)

Copied to clipboard

Miaoran Li, Jiangning Chen, Minghua Xu, Xiaolong Wang

MedWriter: Knowledge-Aware Medical Text Generation (2020.coling-main)

Challenge:	Hallucination remains a key challenge in applying large language models to structured query generation . we propose the Self-Debating framework to enhance detection performance .
Approach:	They propose a framework that prompts an LLM to generate contrastive explanations from opposing perspectives . they also propose 'self-debating' framework to enhance detection performance .
Outcome:	The proposed framework outperforms LLM-as-a-Judge baselines in hallucination detection . the framework generates contrastive explanations from opposing perspectives .

Copied to clipboard

Youcheng Pan, Qingcai Chen, Weihua Peng, Xiaolong Wang, Baotian Hu, Xin Liu, Junying Chen, Wenxiu Zhou

Structured Data in NLP

Challenge:	Recent studies focus on the information of unstructured text rather than structured information of the knowledge graph.
Approach:	They propose a knowledge-aware text generation model for medical domains that incorporates knowledge graphs into the model to improve the quality of generated text.
Outcome:	The proposed model improves the quality of generated text and has robust superiority over other methods.

EmoCharacter: Evaluating the Emotional Fidelity of Role-Playing Agents in Dialogues (2025.naacl-long)

Copied to clipboard

Qiming Feng, Qiujie Xie, Xiaolong Wang, Qingqiu Li, Yuejie Zhang, Rui Feng, Tao Zhang, Shang Gao

Dialogue Systems & Conversational Agents

Challenge:	EmoCharacter evaluates emotional fidelity of role-playing agents in dialogues . current evaluations focus on personality fidelity, tone imitation, and knowledge consistency .
Approach:	They propose a benchmark to assess emotional fidelity of role-playing agents in dialogues using large language models.
Outcome:	The proposed benchmark measures emotional fidelity of role-playing agents and the characters they portray.

Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models (2026.findings-acl)

Copied to clipboard

Bang Zhang, Ruotian Ma, Qingxuan Jiang, Peisong Wang, Jiaqi Chen, Zheng Xie, Xingyu Chen, Yue Wang, Fanghua Ye, Jian Li, Yifan Yang, Zhaopeng Tu, Xiaolong Li

Huatuo-26M, a Large-scale Chinese Medical QA Dataset (2025.findings-naacl)

Challenge:	Large language models (LLMs) have evolved from statistical sequence predictors to sophisticated autonomous agents capable of reasoning, planning, and sustaining multi-turn conversa-tions.
Approach:	They propose a system that instantiates a "Sentient Agent" that simulates human-like emotional changes and inner thoughts to provide a more realistic evaluation of the model in multi-turn conversations.
Outcome:	The proposed framework measures the agent's higher-order social cognition in multi-turn conversations.

Copied to clipboard

Xidong Wang, Jianquan Li, Shunian Chen, Yuxuan Zhu, Xiangbo Wu, Zhiyi Zhang, Xiaolong Xu, Junying Chen, Jie Fu, Xiang Wan, Anningzhe Gao, Benyou Wang

Question Answering

Challenge:	Large Language Models are a powerful tool for medical research, but the data is a bottleneck.
Approach:	They propose to use the largest ever medical Question Answering dataset with 26 Million QA pairs as a fine-tuning data for training large language models.
Outcome:	The proposed dataset demonstrates that it can be used to train large language models and improves zero-shot performance on other datasets.

CODIS: Benchmarking Context-dependent Visual Comprehension for Multimodal Large Language Models (2024.acl-long)

Copied to clipboard

Fuwen Luo, Chi Chen, Zihao Wan, Zhaolu Kang, Qidong Yan, Yingjie Li, Xiaolong Wang, Siyu Wang, Ziyue Wang, Xiaoyue Mi, Peng Li, Ning Ma, Maosong Sun, Yang Liu

Pluggable Neural Machine Translation Models via Memory-augmented Adapters (2024.lrec-main)

Challenge:	Multimodal large language models have demonstrated promising results in a variety of tasks that combine vision and language.
Approach:	They propose a benchmark to assess the ability of models to use contextual information in free-form text to enhance visual comprehension.
Outcome:	The proposed model fails to extract and utilize contextual information to improve understanding of images.

Copied to clipboard

Yuzhuang Xu, Shuo Wang, Peng Li, Xuebo Liu, Xiaolong Wang, Weidong Liu, Yang Liu

Machine Translation

Challenge:	Recent years, neural machine translation systems are often developed with large-scale parallel data extracted from the Web.
Approach:	They propose a memory-augmented adapter to steer pretrained neural machine translation models in a pluggable manner by combining model representations and retrieved results.
Outcome:	The proposed method outperforms several representative pluggable baselines on style- and domain-specific experiments.

UR2 : Unify RAG and Reasoning through Reinforcement Learning (2026.acl-long)

Copied to clipboard

Weitao Li, Boran Xiang, Xiaolong Wang, Jingyi Ren, Ante Wang, Zhinan Gou, Weizhi Ma, Yang Liu

Information Retrieval

Challenge:	Existing attempts to unify large language models are limited to open-domain QA with fixed retrieval settings.
Approach:	They propose a general reinforcement learning framework that dynamically coordinates retrieval and reasoning.
Outcome:	The proposed framework outperforms existing paradigms on open-domain QA, MMLU-Pro, medical, and mathematical reasoning tasks.

MUCAR: Benchmarking Multilingual Cross-Modal Ambiguity Resolution for Multimodal Large Language Models (2025.emnlp-main)

Copied to clipboard

Xiaolong Wang, Zhaolu Kang, Wangyuxuan Zhai, Xinyue Lou, Yunghwei Lai, Ziyue Wang, Yawen Wang, Kaiyu Huang, Yile Wang, Peng Li, Yang Liu

Document Embedding Enhanced Event Detection with Hierarchical and Supervised Attention (P18-2)

Challenge:	Existing multimodal benchmarks overlook linguistic and visual ambiguities, authors say . ambiguity resolution between modalities is lacking in multimodal large language models .
Approach:	They propose a benchmark to evaluate multimodal ambiguity resolution across multilingual and cross-modal scenarios.
Outcome:	a new benchmark evaluates multimodal ambiguity resolution across multilingual and cross-modal scenarios . the benchmark shows that MLLMs can resolve ambiguities in image-text alignment . however, existing benchmarks often overlook linguistic and visual ambiguties .

Copied to clipboard

Yue Zhao, Xiaolong Jin, Yuanzhuo Wang, Xueqi Cheng

Representation Learning

Challenge:	Existing methods for event detection use sentence-level contextual information.
Approach:	They propose a document embedding enhanced bi-RNN model to detect events in sentences . they use hierarchical and supervised attention based RNN to learn document embeds .
Outcome:	The proposed model compares with state-of-the-art models on a ACE-2005 dataset.

Sequential-NIAH: A Needle-In-A-Haystack Benchmark for Extracting Sequential Needles from Long Contexts (2025.emnlp-main)

Copied to clipboard

Yifei Yu, Qian-Wen Zhang, Lingfeng Qiao, Di Yin, Fang Li, Jie Wang, Chen Zeng Xi, Suncong Zheng, Xiaolong Liang, Xing Sun

Information Extraction & Text Mining

Challenge:	Recent models have extended Corresponding Author. context lengths to millions of tokens while maintaining reasoning and comprehension capabilities.
Approach:	They propose a benchmark to evaluate the ability of large language models to extract sequential information items from long contexts.
Outcome:	The proposed model achieves maximum accuracy of 63.50% on six well-known LLMs.

AnchorAlign: A Novel Anchor Alignment-enhanced Generative Method for Joint Named Entity Recognition and Relation Extraction (2026.findings-acl)

Copied to clipboard

Xiaolong Weng, Yuanyun Zhou, Boyu Qiu, Zehua Wang, Ying Xiong, Buzhou Tang

Information Extraction & Text Mining

Challenge:	Named Entity Recognition and Relation Extraction are interdependent tasks in information extraction.
Approach:	They propose a generative method enhanced by anchor alignment to bridge NER and RE tasks . they use anchor entities as semantic pivots to align the two tasks based on their semantic representations .
Outcome:	The proposed method outperforms state-of-the-art models on five benchmark datasets.

Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages (2024.acl-long)

Copied to clipboard

Yuanchi Zhang, Yile Wang, Zijun Liu, Shuo Wang, Xiaolong Wang, Peng Li, Maosong Sun, Yang Liu

Improving Text Embeddings with Large Language Models (2024.acl-long)

Challenge:	Contemporary large language models (LLMs) are pre-trained on multilingual corpora, but their performance lags behind in most languages compared to a few resource-rich languages.
Approach:	They propose a method that leverages the internal capabilities of large language models on resource-rich languages to enhance multilingual performance.
Outcome:	The proposed method improves multilingual performance while minimizing impact on original performance in resource-rich languages.

Copied to clipboard

Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei

Semantic Text Processing

Challenge:	Existing methods for obtaining text embeddings require complex training pipelines . authors leverage proprietary LLMs to generate diverse synthetic data for text embeds based on 93 languages .
Approach:	They propose a method for obtaining high-quality text embeddings using only synthetic data and less than 1k training steps.
Outcome:	The proposed method achieves strong performance on competitive text embedding benchmarks without using any labeled data.

When Helpers Become Hazards: A Benchmark for Analyzing Multimodal LLM-Powered Safety in Daily Life (2026.findings-acl)

Copied to clipboard

Xinyue Lou, Xu Jinan, Jingyi Yin, Xiaolong Wang, Zhaolu Kang, null Liaoyouwei, Yixuan Wang, Xiangyu Shi, Fengran Mo, SU Yao, Kaiyu Huang

LSDSCC: a Large Scale Domain-Specific Conversational Corpus for Response Generation with Diversity Oriented Evaluation Metrics (N18-1)

Challenge:	Safety impact of Multimodal Large Language Models (MLLMs) on human behavior is evaluated in this study.
Approach:	They propose a safety-warning-based evaluation framework that encourages models to provide clear and informative safety warnings, rather than generic refusals.
Outcome:	The proposed safety-warning-based evaluation framework encourages models to provide clear and informative safety warnings, rather than generic refusals.

Copied to clipboard

Zhen Xu, Nan Jiang, Bingquan Liu, Wenge Rong, Bowen Wu, Baoxun Wang, Zhuoran Wang, Xiaolong Wang

Dialogue Systems & Conversational Agents

Challenge:	Existing evaluation metrics for NRG models can't measure semantic relevance and diversity of generated results.
Approach:	They propose a large-scale domain-specific conversational corpus with preprocessing and cleansing procedures for model training and a testing set for measuring the diversity of generated results.
Outcome:	The proposed corpus can be taken as a new benchmark dataset for the NRG task.

Self-Improvement Programming for Temporal Knowledge Graph Question Answering (2024.lrec-main)

Copied to clipboard

Zhuo Chen, Zhao Zhang, Zixuan Li, Fei Wang, Yutao Zeng, Xiaolong Jin, Yongjun Xu

SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval (2023.acl-long)

Challenge:	Existing methods implicitly model time constraints by learning time-aware embeddings of questions and candidate answers, which is far from understanding the question comprehensively.
Approach:	They propose a temporal-based temporal programming method that leverages the in-context learning ability of Large Language Models to understand combinatory time constraints in questions.
Outcome:	The proposed method outperforms existing methods on multiTQ and CronQuestions datasets and is highly efficient on multi-level questions.

Copied to clipboard

Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei

Semantic Text Processing

Challenge:	SimLM uses a simple bottleneck architecture that learns to compress the passage information into a dense vector through self-supervised pre-training.
Approach:	They propose a simple yet effective pre-training method for dense passage retrieval that learns to compress the passage information into a dense vector through self-supervised pre-tuning.
Outcome:	The proposed method outperforms multi-vector approaches on large-scale passage retrieval datasets and shows significant improvements over baselines.

RCBSF: A Multi-Agent Framework for Automated Contract Revision via Stackelberg Game (2026.findings-acl)

Copied to clipboard

Shijia Xu, Yu Wang, Xiaolong Jia, Zhou Wu, Kai Liu, April Xiaowen Dong

Challenge:	despite the adoption of Large Language Models (LLMs), contract revision remains impeded because generic models treat strict legal constraints as mere suggestions.
Approach:	They propose a risk-constrained bilevel Stackelberg framework that models high-stakes revision as a strategic interaction rather than an open-ended conversation.
Outcome:	The proposed framework achieves state-of-the-art performance with an average RRR of 84.21% and enhanced token efficiency.

SR-RAG: Verifiable Multi-Hop Reasoning via On-the-fly Symbolic Graph Construction (2026.findings-acl)

Copied to clipboard

Zehua Wang, Zhaojin Zhang, Boyu Qiu, Xiaolong Weng, Ying Xiong, Buzhou Tang, Min Zhang

Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS (2026.findings-acl)

Challenge:	Existing paradigms for multi-hop reasoning suffer from high construction costs and limited adaptability to dynamic knowledge.
Approach:	They propose a symbolic reasoning framework for multi-hop question answering that integrates the advantages of both paradigms by dynamically generating sub-questions, performing information retrieval and symbolic encoding based on an on-the-fly graph and using a symbol verifier to validate intermediate reasoning steps.
Outcome:	The proposed framework significantly improves accuracy and robustness on multiple multi-hop benchmarks and a medical dataset.

Copied to clipboard

Shijia Xu, Zhou Wu, Xiaolong Jia, Yu Wang, Kai Liu, April Xiaowen Dong

Reasoning

Challenge:	Existing approaches to retrieval-augmented generation still face problems with low context utilization and frequent hallucinations.
Approach:	They propose a framework that reformulates retrieval and generation as constrained optimization and path planning.
Outcome:	The proposed framework significantly improves reasoning accuracy on complex queries while reducing hallucinations.

Your RAG is Unfair: Exposing Fairness Vulnerabilities in Retrieval-Augmented Generation via Backdoor Attacks (2025.emnlp-main)

Copied to clipboard

Gaurav Bagwe, Saket Sanjeev Chaturvedi, Xiaolong Ma, Xiaoyong Yuan, Kuang-Ching Wang, Lan Emily Zhang

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

Challenge:	Retrieval-augmented generation (RAG) enhances factual grounding but introduces new attack surfaces, particularly through backdoor attacks.
Approach:	They propose a framework that exposes fairness vulnerabilities in RAG through a two-phase backdoor attack.
Outcome:	Empirical results show that BiasRAG achieves high attack success rates while remaining undetectable under standard fairness evaluations.

Copied to clipboard

Xin Guo, Haotian Xia, Zhaowei Liu, Hanyang Cao, Zhi Yang, Zhiqiang Liu, Sizhe Wang, Jinyi Niu, Chuqi Wang, Yanhui Wang, Xiaolong Liang, Xiaoming Huang, Bing Zhu, Zhongyu Wei, Yun Chen, Weining Shen, Liwen Zhang