Papers by Wentao Chen

Timeline-based Sentence Decomposition with In Context Learning for Temporal Fact Extraction (2024.acl-long)

Challenge:	Existing research focuses on benchmarking LLMs in single-turn dialogues, neglecting the nuanced nature of human feedback within real-world usage scenarios.
Approach:	They propose a fine-grained, multi-task benchmark designed to evaluate LLMs’ responsiveness to human feedback under real-world usage scenarios in Chinese.
Outcome:	The proposed benchmarks show that human feedback can significantly impact LLMs’ responsiveness in real-world usage scenarios.

Copied to clipboard

Jianhao Chen, Haoyuan Ouyang, Junyang Ren, Wentao Ding, Wei Hu, Yuzhong Qu

Low-Resource NLP

Challenge:	Recent research on temporal fact extraction fails to establish time-to-fact correspondences in complex sentences.
Approach:	They propose a timeline-based sentence decomposition strategy using large language models with in-context learning to extract temporal facts from natural language text.
Outcome:	The proposed method achieves state-of-the-art on a complex temporal fact extraction dataset.

Syllogistic Reasoning for Legal Judgment Analysis (2023.emnlp-main)

Copied to clipboard

Wentao Deng, Jiahuan Pei, Keyi Kong, Zhe Chen, Furu Wei, Yujun Li, Zhaochun Ren, Zhumin Chen, Pengjie Ren

MathMixup: Boosting LLM Mathematical Reasoning with Difficulty-Controllable Data Synthesis and Curriculum Learning (2026.findings-acl)

Challenge:	Legal judgment assistants are developing fast due to impressive progress of large language models.
Approach:	They construct and manually correct a syllogistic reasoning dataset for legal judgment analysis using large language models as benchmarks.
Outcome:	The proposed dataset contains 11,239 criminal cases covering 4 criminal elements, 80 charges and 124 articles.

Copied to clipboard

Xuchen Li, Jing Chen, Xuzhao Li, Hao Liang, Xiaohuan Zhou, Taifeng Wang, Wentao Zhang

Intent-calibrated Self-training for Answer Selection in Open-domain Dialogues (2023.tacl-1)

Challenge:	Existing data synthesis methods suffer from limited diversity and lack precise control over problem difficulty, making them insufficient for efficient training paradigms such as curriculum learning.
Approach:	They propose a data synthesis paradigm that generates high-quality, difficulty-controllable mathematical reasoning problems through hybrid and decomposed strategies.
Outcome:	The proposed paradigm outperforms existing methods and improves mathematical reasoning abilities.

Copied to clipboard

Wentao Deng, Jiahuan Pei, Zhaochun Ren, Zhumin Chen, Pengjie Ren

Natural Language Interfaces

Challenge:	Existing answer selection models require large amounts of labeled data to produce accurate answers.
Approach:	They propose intent-calibrated self-training to calibrate answer labels using labeled data . they propose intentcalibration to improve quality of pseudo answer labels .
Outcome:	The proposed intent-calibrated answer selection paradigm outperforms baselines with 1%, 5%, and 10% labeled data on two benchmark datasets.

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing (2026.acl-industry)

Copied to clipboard

Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Zirui Tang, Boyu Niu, Yuanhong Zheng, Dongsheng Ma, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Fangdong Wang, Jingzhou Chen, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, RuiLiang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Dechen Lin, null Shenguanlin, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He

Green & Sustainable NLP

Challenge:	Document images are characterized by higher resolutions, denser content, and more complex structural layouts.
Approach:	They propose a 1.2B-parameter document parsing vision-language model that decouples layout analysis from local content recognition.
Outcome:	The proposed model surpasses general-purpose and domain-specific models on multiple benchmarks while maintaining significantly lower computational overhead.

Improving Multi-label Malevolence Detection in Dialogues through Multi-faceted Label Correlation Enhancement (2022.acl-long)

Copied to clipboard

Yangjun Zhang, Pengjie Ren, Wentao Deng, Zhumin Chen, Maarten Rijke

Dialogue Systems & Conversational Agents

Challenge:	Current methods for detecting dialogue malevolence neglect label correlation.
Approach:	They propose to crowdsource a multi-label dataset for detecting malevolent dialogue responses and a model with label correlation enhanced CRF to measure the correlation between malevolence and negative emotions.
Outcome:	The proposed model outperforms the best performing baseline method on precision, recall, F1, and Jaccard score by 16.1%, 11.9%, 12.0%, and 6.1% on malevolence.

Automatic rule generation for time expression normalization (2021.findings-emnlp)

Copied to clipboard

Wentao Ding, Jianhao Chen, Jinmao Li, Yuzhong Qu

Challenge:	Existing SOTA methods for normalization rely on expert-designed rules or grammars . current methods are domain sensitive and not sufficient on emerging corpora .
Approach:	They propose a method that generates normalization rules from annotated data without expert intervention.
Outcome:	The proposed method surpasses existing rule-based methods on the Tweets benchmark and on the TempEval-3 benchmark.

Leveraging Unpaired Feedback for Long-Term LLM-based Recommendation Tuning (2025.findings-emnlp)

Copied to clipboard

Jizhi Zhang, Chongming Gao, Wentao Shi, Xin Chen, Jingang Wang, Xunliang Cai, Fuli Feng

Challenge:	a recent study highlights unpaired feedback as a key challenge for long-term LLM-based recommenders . unpaired user feedback is crucial for improving LLMs in dynamic user environments, authors say .
Approach:	They propose a framework that incorporates unpaired feedback into LLMs to improve long-term recommendation performance.
Outcome:	The proposed framework improves long-term recommendation performance by incorporating unpaired feedback without requiring paired supervision.

Semantic Framework based Query Generation for Temporal Question Answering over Knowledge Graphs (2022.emnlp-main)

Copied to clipboard

Wentao Ding, Hao Chen, Huayu Li, Yuzhong Qu

Hallucinations as Orthogonal Noise: Inference-Time Manifold Alignment via Dynamic Contextual Orthogonalization (2026.findings-acl)

Challenge:	Existing methods for temporal question answering ignore intrinsic connections between events that can make them temporally related.
Approach:	They propose a temporal question answering method that generates query graphs by exploring relevant facts of mentioned entities.
Outcome:	The proposed method outperforms existing methods on two benchmarks over different knowledge graphs.

Copied to clipboard

Mingkuan Zhao, Wentao Hu, Tianchen Huang, Yuheng Min, Suquan Chen, Yide Gao, Yanbo Zhai, Shuangyong Song, Xuelong Li

One Pair Suffices: Unlocking Universal Zero-Shot Translation via Cross-Architecture Alignment (2026.acl-long)

Challenge:	Hallucinations in Large Language Models persist in critical domains where generated content diverges from contextual facts or logical constraints.
Approach:	They propose to generate hallucinations as orthogonal noise relative to the semantic manifold of the residual stream.
Outcome:	The proposed method achieves superior contextual faithfulness compared to state-of-the-art methods.

Copied to clipboard

Hao Zong, Cong Hu Yuan, Chao Bei, Wentao Chen, Huan Liu, Kaiyu Huang, Degen Huang

Do LLMs Behave as Claimed? Investigating How LLMs Follow Their Own Claims using Counterfactual Questions (2025.emnlp-main)

Challenge:	Current paradigms for empowering Large Language Models with multilingual capabilities rely heavily on massive instruction tuning.
Approach:	They propose a hybrid cross-alignment approach that fuses a frozen NLLB encoder with a Qwen decoder via a closed-loop dual-adapter architecture.
Outcome:	The proposed model outperforms towerPlus-9B and Aya-101 on language-agnostic projection protocols.

Copied to clipboard

Haochen Shi, Shaobo Li, Guoqing Chao, Xiaoliang Shi, Wentao Chen, Zhenzhou Ji

Responsible & Trustworthy NLP

Challenge:	Existing evaluation frameworks rely on curated datasets that, once public, may be accessed by newer LLMs.
Approach:	They propose a framework that generates counterfactual questions and answers from existing evaluation datasets and uses them to evaluate LLMs.
Outcome:	The proposed evaluation framework reduces the risk of data leakage by allowing the LLMs to respond to counterfactual questions and verify their claims.

Dataset for the First Evaluation on Chinese Machine Reading Comprehension (L18-1)

Copied to clipboard

Yiming Cui, Ting Liu, Zhipeng Chen, Wentao Ma, Shijin Wang, Guoping Hu

A Sentence Cloze Dataset for Chinese Machine Reading Comprehension (2020.coling-main)

Challenge:	Existing reading comprehension datasets are mostly in English .
Approach:	They propose a Chinese reading comprehension dataset to add diversity to existing reading comprehension data . proposed dataset contains cloze-style reading comprehension and user query reading comprehension .
Outcome:	The proposed dataset is based on a Chinese reading comprehension dataset . it includes two types of cloze-style and user query reading comprehension . the proposed dataset hosted the 1st Evaluation on Chinese Machine Reading Comprehension (CMRC-2017)

Copied to clipboard

Yiming Cui, Ting Liu, Ziqing Yang, Zhipeng Chen, Wentao Ma, Wanxiang Che, Shijin Wang, Guoping Hu

InfiMM: Advancing Multimodal Understanding with an Open-Sourced Visual Language Model (2024.findings-acl)

Challenge:	Using cloze-style reading comprehension, Chinese machine reading comprehension datasets are becoming more and more popular . a new task is proposed to fill the right candidate sentence into the passage with several blanks .
Approach:	They propose a Chinese task to fill the right candidate sentence into a passage with blanks . they build a dataset to evaluate the difficulty of the task and make fake candidates .
Outcome:	The proposed task fills the right candidate sentence into the passage with blanks . the proposed dataset contains over 100K blanks within over 10K passages based on Chinese narrative stories .

Copied to clipboard

Haogeng Liu, Quanzeng You, Yiqi Wang, Xiaotian Han, Bohan Zhai, Yongfei Liu, Wentao Chen, Yiren Jian, Yunzhe Tao, Jianbo Yuan, Ran He, Hongxia Yang

Can LLMs be Good Graph Judge for Knowledge Graph Construction? (2025.emnlp-main)

Challenge:	InfiMM is a multimodal large language model that adapts to complex vision-language tasks.
Approach:	They present a Multimodal Large Language Model that adapts to intricate vision-language tasks using large-scale training data and comprehensive training strategies.
Outcome:	Empirical evaluations across a variety of benchmarks underscore InfiMM’s remarkable capability in multimodal understanding.

Copied to clipboard

Haoyu Huang, Chong Chen, Zeang Sheng, Yang Li, Wentao Zhang

Structured Data in NLP

Challenge:	Existing methods for converting unstructured text into structured Knowledge Graphs (KGs) have limitations such as large amount of noise, inaccurate knowledge, and hallucination .
Approach:	They propose a GraphJudge framework to reduce noise in real-world documents . they propose Graphjudge to fine-tune a LLM as a graph judge to enhance quality .
Outcome:	The proposed framework eliminates noise in real-world documents and improves the quality of generated KGs.

Dynamic Model-Bank Test-Time Adaptation for Automatic Speech Recognition (2025.emnlp-main)

Copied to clipboard

Yanshuo Wang, Yanghao Zhou, Yukang Lin, Haoxing Chen, Jin Zhang, Wentao Zhu, Jie Hong, Xuesong Li

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

Challenge:	Existing ASR TTA methods struggle with instability under continual and long-term distribution shifts.
Approach:	They propose a continuous adaptive model-bank framework that adapts to domain shifts in ASR test-time scenarios.
Outcome:	Experiments on diverse, continuously shifting ASR benchmarks show that DMSUTA outperforms existing continual TTA baselines.

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

Data Contamination Calibration for Black-box LLMs (2024.findings-acl)

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

Wentao Ye, Jiaqi Hu, Liyao Li, Haobo Wang, Gang Chen, Junbo Zhao

Challenge:	Despite the rapid advancements of Large Language Models, the unchecked ultra-large-scale training sets introduce a series of potential risks like data contamination.
Approach:	They propose a method to detect contaminated training data and diminish the contamination effect by using a to-be-released dataset.
Outcome:	The proposed method outperforms existing methods by at least 4.5% on more 4 dataset formats, with more than 10 base LLMs.

A Span-Extraction Dataset for Chinese Machine Reading Comprehension (D19-1)

Copied to clipboard

Yiming Cui, Ting Liu, Wanxiang Che, Li Xiao, Zhipeng Chen, Wentao Ma, Shijin Wang, Guoping Hu

Machine Reading Comprehension

Challenge:	Existing reading comprehension datasets are mostly in English . MRC is a new field of research that aims to comprehend the context of articles and answer the questions based on them.
Approach:	They propose a Span-Extraction dataset for Chinese machine reading comprehension to add language diversities to existing reading comprehension datasets.
Outcome:	The proposed dataset is composed of 20,000 real questions annotated on Wikipedia paragraphs by human experts.

MLLM-Bench: Evaluating Multimodal LLMs with Per-sample Criteria (2025.naacl-long)

Copied to clipboard

Wentao Ge, Shunian Chen, Hardy Chen, Nuo Chen, Junying Chen, Zhihong Chen, Wenya Xie, Shuo Yan, ChenghaoZhu ChenghaoZhu, Ziyue Lin, Dingjie Song, Xidong Wang, Anningzhe Gao, Zhang Zhiyi, Jianquan Li, Xiang Wan, Benyou Wang

LongInsightBench: A Comprehensive Benchmark for Evaluating Omni-Modal Models on Human-Centric Long-Video Understanding. (2026.findings-acl)

Challenge:	Existing evaluation methodologies for multimodal large language models are limited in evaluating objective queries without considering real-world user experiences.
Approach:	They propose to evaluate multimodal large language models with per-sample criteria using potent MLLM as the judge.
Outcome:	The proposed evaluation paradigm shows that it can be used to evaluate multimodal large language models with per-sample criteria.

Copied to clipboard

ZhaoYang Han, Qihan Lin, Hao Liang, Bowen Chen, Zhou Liu, Wentao Zhang

Multimodal Chemical Structure-Text Coreference in Intellectual Property via Rule-guided Reinforcement Learning (2026.findings-acl)

Challenge:	LongInsightBench is the first benchmark designed to assess models’ ability to understand long videos, with a focus on human language, viewpoints, actions, and other contextual elements.
Approach:	They propose a benchmark to assess models’ ability to understand long videos with a focus on human language, viewpoints, actions, and other contextual elements.
Outcome:	The proposed model excels in three key areas: a) long-duration, human-centric videos; b) diversifying and challenging task scenarios; c) quality assurance pipeline; and d) reliability.

Copied to clipboard

Hanmeng Zhong, Wentao Wu, Linqing Chen, Peng Zhou

Information Extraction & Text Mining

Challenge:	Existing tools for identifying chemical structures and textual referents are inadequate for this multimodal task.
Approach:	They propose a RULE-guided multimodal Reinforcement learning framework for chemical structure-text coreference . RULER is a rule-driven reinforcement learning framework that uses rule-based reward functions to obtain the correct domain knowledge.
Outcome:	The proposed framework improves on the baseline framework and shows superior efficacy.

AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation (2026.findings-acl)

Copied to clipboard

Wentao Shi, Yu Wang, Yuyang Zhao, Yuxin Chen, Fuli Feng, Xueyuan Hao, Xi Su, Qi GU, Hui Su, Xunliang Cai, Xiangnan He

Challenge:	Existing approaches to verify agent behaviors in complex environments rely on rule-based verifiers or LLM-as-a-Judge models.
Approach:	They propose a benchmark to evaluate Agent-as-a-Judge across three domains . the benchmark covers search, data systems, and graphical user interfaces - with 155 tasks and 516 trajectories .
Outcome:	The proposed benchmark outperforms existing benchmarks in search, data systems, and GUI domains while revealing open challenges in agent-based verification.

Training Verifier to Assessing Complex Real-World Tool-Use Trajectories (2026.findings-acl)

Copied to clipboard

Linzhuang Sun, Mingyang Chen, Hao Liang, Tianpeng Li, Zhou Yijie, Chenzheng Zhu, Tianyu Guo, Huanyao Zhang, Jingxuan Wei, Bihui Yu, Fan Yang, Wentao Zhang

Challenge:	Existing methods for training effective AI agents often resort to synthetic data generation.
Approach:	They propose a plug-and-play framework for data quality control in tool-use scenarios . they construct a tool-verify dataset and release a benchmark to assess its performance .
Outcome:	The proposed framework surpasses Qwen2.5-72B-Instruct on Tool-V-Bench and the previous APIGen-MT dataset.

CFBench: A Comprehensive Constraints-Following Benchmark for LLMs (2025.acl-long)

Copied to clipboard

Tao Zhang, ChengLIn Zhu, Yanjun Shen, Wenjing Luo, Yan Zhang, Hao Liang, Tao Zhang, Fan Yang, Mingan Lin, Yujing Qiao, Weipeng Chen, Bin Cui, Wentao Zhang, Zenan Zhou

CoMave: Contrastive Pre-training with Multi-scale Masking for Attribute Value Extraction (2023.findings-acl)

Challenge:	Existing evaluations of Large Language Models (LLMs) focus on fragmented constraints or narrow scenarios, but they overlook the comprehensiveness and authenticity of constraints from the user’s perspective.
Approach:	They propose a Chinese Comprehensive Constraints Following Benchmark for LLMs that compiles constraints from real-world instructions and constructs a systematic framework for constraint types.
Outcome:	The proposed framework integrates multi-dimensional assessment criteria with requirement prioritization, covering various perspectives of constraints, instructions, and requirement fulfillment.

Copied to clipboard

Xinnan Guo, Wentao Deng, Yongrui Chen, Yang Li, Mengdi Zhou, Guilin Qi, Tianxing Wu, Dong Yang, Liubin Wang, Yong Pan

CRAB: A Benchmark for Evaluating Curation of Retrieval-Augmented LLMs in Biomedicine (2025.emnlp-industry)

Challenge:	Existing methods to extract product features from unstructured text still suffer from problems . e-commerce platforms are focusing on multi-scale values, which can be confusing .
Approach:	They propose a pre-training technique to automatically obtain attribute value pairs from product descriptions to aid e-commerce.
Outcome:	The proposed method improves on the existing token-level masking strategy and achieves state-of-the-art on four benchmarks.

Copied to clipboard

Hanmeng Zhong, Linqing Chen, Wentao Wu, Weilei Wang

Information Retrieval

Challenge:	Recent development in Retrieval-Augmented Large Language Models (LLMs) have shown great promise in biomedical applications.
Approach:	They propose a multilingual benchmark to evaluate retrieval-augmented large language models' curation ability.
Outcome:	The proposed benchmark is available in English, French, German and Chinese.

UniDataBench: Evaluating Data Analytics Agents Across Structured and Unstructured Data (2026.acl-long)

Copied to clipboard

Han Weng, Zhou Liu, Yuanfeng Song, Xiaoming Yin, Xing Chen, Wentao Zhang

The Dominance of Text Space: Unveiling the Asymmetric Nature of Cross-Modal Alignment in Large Language Models (2026.acl-long)

Challenge:	Existing benchmarks do not assess agents’ capabilities across data types . Existing tools only evaluate agents' ability to extract reasonable insights across data formats.
Approach:	They propose a multi-source benchmark to evaluate the performance of data analytics agents in handling diverse data sources.
Outcome:	The proposed agent performs end-to-end analysis over diverse data sources by automatically discovering cross-source linkages, decomposing goals, and generating robust, self-correcting code to extract actionable insights.

Copied to clipboard

Linqing Chen, Hanmeng Zhong, Wentao Wu, Peng Zhou

Resonant Context Anchoring: Decoupling Attention Routing and Signal Gain at Inference Time (2026.findings-acl)

Challenge:	Existing methods for cross-modal alignment assume a symmetric interaction between visual and textual modalities, implying that both spaces adapt to each other.
Approach:	They propose a method that regularizes the projector to maintain the geometric structure of the text embedding space via spectral filtering.
Outcome:	The proposed method preserves the LLM’s inherent linguistic capabilities and reduces object hallucination significantly better than standard fine-tuning methods.

Copied to clipboard

Mingkuan Zhao, Yide Gao, Wentao Hu, Suquan Chen, Tianchen Huang, Zhenhua An, Zetao Chang, Xiayu Sun, Yuheng Min

SciFlow-Bench: Evaluating Structure-Aware Scientific Diagram Generation via Inverse Parsing (2026.acl-long)

Challenge:	Existing mitigation strategies rely on suppressing specific neuron activations or employing computationally expensive contrastive decoding mechanisms, which often result in increased perplexity or significantly elevated inference latency.
Approach:	They propose a lightweight inference-time intervention method grounded in the perspective of residual stream signal dynamics to resolve the signal attenuation of external evidence during its propagation through deep networks.
Outcome:	The proposed method improves contextual faithfulness across multiple factual consistency and strong knowledge-conflict tasks while maintaining the model’s general language understanding capabilities.

Copied to clipboard

Tong Zhang, Honglin Lin, Zhou Liu, Chong Chen, Wentao Zhang

HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation (2025.findings-acl)

Challenge:	Existing benchmarks for scientific diagram generation rely on image-centric metrics or evaluation of intermediate symbolic representations rather than final rendered images.
Approach:	They propose a structure-first benchmark for evaluating scientific diagram generation from pixel-level outputs.
Outcome:	The proposed benchmark evaluates scientific diagram generation directly from pixel-level outputs.

Copied to clipboard

Hao Liu, Zhengren Wang, Xi Chen, Zhiyu Li, Feiyu Xiong, Qinhan Yu, Wentao Zhang

Information Retrieval

Challenge:	Traditional retrieval systems focus on lexical or semantic similarity rather than logical relevance.
Approach:	They propose a new RAG framework that augments retrieval with logical reasoning . hopRAG uses a retrieve-reason-prune mechanism to explore multi-hop neighbors .
Outcome:	The proposed framework outperforms conventional retrieval systems and state-of-the-art benchmarks on multi-hop QA tasks.

LongTableBench: Benchmarking Long-Context Table Reasoning across Real-World Formats and Domains (2025.findings-emnlp)

Copied to clipboard

Liyao Li, Jiaming Tian, Hao Chen, Wentao Ye, Chao Ye, Haobo Wang, Ningtao Wang, Xing Fu, Gang Chen, Junbo Zhao