Papers by Shu Wu

Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models (2024.findings-acl)

Challenge:	Existing methods learned semantic representations with dual encoders or dual variational auto-encoders failed to capture the aligned semantics between question and answer.
Approach:	They propose to use two variational auto-encoders to generate questions with aligned answers and generating answers with align questions.
Outcome:	The proposed method outperforms the state-of-the-art answer retrieval method on SQuAD.

Copied to clipboard

Junfei Wu, Qiang Liu, Ding Wang, Jinghao Zhang, Shu Wu, Liang Wang, Tieniu Tan

T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts (2025.acl-long)

Challenge:	Object hallucination has been an Achilles’ heel which hinders the broader applications of large vision-language models (LVLMs).
Approach:	They propose a logical closed loop-based framework for Object Hallucination Detection and Mitigation that uses logical consistency probing to raise questions with logical correlations to determine hallucinations.
Outcome:	The proposed method can be applied to all existing LVLMs and is effective and general.

Copied to clipboard

Ziwei Huang, Wanggui He, Quanyu Long, Yandi Wang, Haoyuan Li, Zhelun Yu, Fangxun Shu, Weilong Dai, Hao Jiang, Fei Wu, Leilei Gan

Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language Models (2026.acl-long)

Challenge:	Existing studies on text-to-image (T2I) models focus on text alignment, image quality, and object composition capabilities.
Approach:	They propose a T2I-FactualBench benchmark to evaluate the factuality of knowledge-intensive concept generation.
Outcome:	The proposed framework evaluates the factuality of knowledge-intensive concept generation tasks.

Copied to clipboard

Jiayi Zhang, Shu Yang, Junchao Wu, Derek F. Wong, Di Wang

LaMP-Val: Large Language Models Empower Personalized Valuation in Auction (2025.findings-emnlp)

Challenge:	Recent studies have focused on the internal representations of large language models and the mechanisms that lead to unintended cross-topic generalization.
Approach:	They propose a method that uses inhibition to localize political neurons and a technique that uses topic-specific blocking to mitigate the cross-topic generalization.
Outcome:	The proposed method reduces cross-topic generalization by 20% while preserving topic-specific performance.

Copied to clipboard

Jie Sun, Tianyu Zhang, Houcheng Jiang, Kexin Huang, Xiang Shu, Zhibo Zhu, Lintao Ma, Xingyu Lu, Jun Zhou, Junkang Wu, Chi Luo, An Zhang, Jiancan Wu, Xiang Wang

Rethinking Composed Image Retrieval Evaluation: A Fine-Grained Benchmark from Image Editing (2026.acl-long)

Challenge:	Currently, most research focuses on the bidding algorithms used within auction mechanisms.
Approach:	They propose a personalized valuation framework that integrates Large Language Models to incorporate personalized semantic preference into users valuation process.
Outcome:	The proposed framework incorporates Large Language Models to incorporate personalized semantic preference into users valuation process.

Copied to clipboard

Tingyu Song, Yanzhao Zhang, Mingxin Li, Zhuoning Guo, Dingkun Long, Pengjun Xie, Siyue Zhang, Yilun Zhao, Shu Wu

SINCon: Mitigate LLM-Generated Malicious Message Injection Attack for Rumor Detection (2025.acl-long)

Challenge:	Composed Image Retrieval (CIR) is a complex task in multimodal understanding . current CIR benchmarks lack a robust evaluation pipeline and limited query categories .
Approach:	They construct a fine-grained CIR benchmark that allows for precise control over modification types and content.
Outcome:	The proposed benchmark covers 5,000 high-quality queries structured across five main categories and fifteen subcategories.

Copied to clipboard

Mingqing Zhang, Qiang Liu, Xiang Tao, Shu Wu, Liang Wang

Robustness in NLP

Challenge:	Existing methods define important nodes as important and target them for attacks if the model treats nodes’ predictive influence more uniformly . Existing approaches target high predictive influence nodes but are vulnerable to malicious message injection attacks.
Approach:	They propose a defense mechanism that encourages the model to learn graph representations where nodes with varying importance have a more uniform influence on predictions.
Outcome:	Extensive experiments on the Twitter and Weibo datasets show that similarizing the predictive Influence of nodes with Contrastive Learning significantly enhances resistance against LLM-driven message injection attacks.

Explore the Reasoning Capability of LLMs in the Chess Testbed (2025.naacl-short)

Copied to clipboard

Shu Wang, Lei Ji, Renxi Wang, Wenxiao Zhao, Haokun Liu, Yifan Hou, Ying Nian Wu

Personalized Text Generation with Contrastive Activation Steering (2025.acl-long)

Challenge:	a recent study shows that large language models struggle with long-term, complex reasoning tasks.
Approach:	They propose to integrate annotated strategy and tactic into large language models to improve reasoning capability.
Outcome:	The proposed model performs better than GPT, Claude, and Gemini models . it integrates annotated strategy and tactic into the model .

Copied to clipboard

Jinghao Zhang, Yuting Liu, Wenjie Wang, Qiang Liu, Shu Wu, Liang Wang, Tat-Seng Chua

KELE: Residual Knowledge Erasure for Enhanced Multi-hop Reasoning in Knowledge Editing (2025.findings-emnlp)

Challenge:	Existing approaches to personalized text generation rely on retrieval-augmented generation and parameter-efficient fine-tuning.
Approach:	They propose a training-free framework that disentangles and represents personalized writing style as a vector in LLM’s activation-space.
Outcome:	The proposed framework achieves 8% relative improvement in personalized generation while reducing storage requirements by 1700 over PEFT method.

Copied to clipboard

Mengqi Zhang, Bowen Fang, Qiang Liu, Xiaotian Ye, Shu Wu, Pengjie Ren, Zhumin Chen, Liang Wang

A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models (2025.findings-emnlp)

Challenge:	Existing knowledge editing techniques show limitations when applied to multi-hop reasoning . residual single-hop knowledge causes edited models to revert to original answers .
Approach:	They propose a knowledge editing method that incorporates a Knowledge Erasure mechanism for Large language model Editing (KELE) they propose an erasure function for residual knowledge and an injection function for new knowledge .
Outcome:	The proposed method significantly improves multi-hop reasoning capability of edited models.

Copied to clipboard

Dong Shu, Xuansheng Wu, Haiyan Zhao, Daking Rai, Ziyu Yao, Ninghao Liu, Mengnan Du

Explainability & Interpretability in NLP

Challenge:	Sparse Autoencoders (SAEs) can disentangle complex features into more interpretable components.
Approach:	They propose to use Sparse Autoencoders to disentangle LLM features into more interpretable components.
Outcome:	The proposed method disentangles complex features into more interpretable components.

EX-FEVER: A Dataset for Multi-hop Explainable Fact Verification (2024.findings-acl)

Copied to clipboard

Huanhuan Ma, Weizhi Xu, Yifan Wei, Liuji Chen, Liang Wang, Qiang Liu, Shu Wu, Liang Wang

ThinkLinker: From Low-Rank Interaction to Knowledge-Aware Verification for Multimodal Entity Linking (2026.findings-acl)

Challenge:	Existing studies on fact verification lack a high-quality dataset for explainability . existing systems lack evidence retrieval and veracity prediction, limiting the ability to verify a claim .
Approach:	They propose a dataset for multi-hop explainable fact verification that summarises and modifies Wikipedia documents.
Outcome:	The proposed dataset aims to improve the accuracy of multi-hop explainable fact verification systems.

Copied to clipboard

Yingyao Ma, Yuanyuan Zhou, Congyu Zhang, Yi Yuan, Jiasong Wu, Lotfi Senhadji, Huazhong Shu

Detecting Latin in Historical Books with Large Language Models: A Multimodal Benchmark (2026.eacl-long)

Challenge:	Existing methods for multimodal entity linking rely on textual context for disambiguation . textual contextual information alone fails to resolve ambiguity, leading to unreliable disambiguations in weak contexts.
Approach:	They propose a two-stage multimodal entity linking framework called ThinkLinker . they propose fusion mechanism to model joint dependencies among features .
Outcome:	The proposed framework outperforms state-of-the-art models on public benchmark datasets.

Copied to clipboard

Yu Wu, Ke Shu, Jonas Fischer, Lidia Pivovarova, David Rosson, Eetu Mäkelä, Mikko Tolonen

RAVEN++: Pinpointing Fine-Grained Violations in Advertisement Videos with Active Reinforcement Reasoning (2025.emnlp-industry)

Challenge:	This paper presents a novel task of extracting low-resourced and noisy Latin fragments from mixed-language historical documents with varied layouts.
Approach:	They propose to extract low-resourced and noisy Latin fragments from mixed-language historical documents with varied layouts using a multimodal dataset.
Outcome:	The proposed model lacks a functional comprehension of Latin, but reliable detection is achievable with zero-shot models.

Copied to clipboard

Deyi Ji, Yuekui Yang, Liqun Liu, Peng Shu, Haiyang Wu, Shaogang Tang, Xudong Chen, Shaoping Ma, Tianrun Chen, Lanyun Zhu

Generate First, Then Sample: Enhancing Fake News Detection with LLM-Augmented Reinforced Sampling (2025.acl-long)

Challenge:	Recent advances in large language models have improved the detection of non-compliant content, but critical gaps persist in fine-grained understanding, explainability, and generalization.
Approach:	They propose a framework that combines active reinforcement learning, fine-grained violation understanding and progressive multi-stage training.
Outcome:	The proposed framework outperforms general-purpose LLMs and specialized models in fine-grained violation understanding, explainability, and generalization.

Copied to clipboard

Zhao Tong, Yimeng Gu, Huidong Liu, Qiang Liu, Shu Wu, Haichao Shi, Xiao-Yu Zhang

Reasoning

Challenge:	Existing models have a performance gap of 20% between classifying fake news and real news, making them less suitable for practical deployment.
Approach:	They propose to adopt an LLM to generate fake news in three different styles, which are later incorporated into the training set to augment the representation of fake news.
Outcome:	The proposed model achieves state-of-the-art performance on two benchmark datasets and improves detection accuracy by 24.02% and 11.06% respectively.

JARVIS or Ultron? A Survey on the Safety and Security Threats of Computer-Using Agents (2026.acl-long)

Copied to clipboard

Ada Chen, Yongjiang Wu, Junyuan Zhang, Jingyu Xiao, Shu Yang, Jen-tse Huang, Kun Wang, Wenxuan Wang, Shuai Wang

Challenge:	Recent advances in computer-using agents have created new safety and security risks . despite the impressive capabilities of CUAs, there are still significant security risks.
Approach:	They propose a systematization of knowledge on the safety and security threats of Computer-Using Agents.
Outcome:	The proposed framework provides a framework for assessing the safety and security risks of computer-using agents.

Chain-of-History Reasoning for Temporal Knowledge Graph Forecasting (2024.findings-acl)

Copied to clipboard

Yuwei Xia, Ding Wang, Qiang Liu, Liang Wang, Shu Wu, Xiao-Yu Zhang

MM-ShiftKV: Decode-Aware Prefill-Stage KV Selection for Multimodal Large Language Models (2026.findings-acl)

Challenge:	Existing graph-based models excel at capturing structural information within TKGs but lack semantic comprehension abilities.
Approach:	They propose a plug-and-play module to enhance the performance of graph-based TKG models by exploring high-order histories step-by-step.
Outcome:	Experiments on three datasets and backbones show that CoH is effective in capturing high-order historical information for LLMs.

Copied to clipboard

Jinsong Shu, Chenyang Wu, Zhongle Xie, Baokun Wang, Lidan Shou

Who Wrote This? The Key to Zero-Shot LLM-Generated Text Detection Is GECScore (2025.coling-main)

Challenge:	Recent work suggests a prefill-stage KV cache selection method to estimate KV importance from prefilling statistics.
Approach:	They propose a training-free, decode-aware and strictly prefill-only KV selection method that retains key-value caching for decoding .
Outcome:	The proposed method outperforms existing methods under tight cache budgets on multimodal benchmarks.

Copied to clipboard

Junchao Wu, Runzhe Zhan, Derek F. Wong, Shu Yang, Xuebo Liu, Lidia S. Chao, Min Zhang

Low-Resource NLP

Challenge:	Existing methods for detecting LLM-generated text require no training data.
Approach:	They propose a black-box zero-shot detection approach that calculates the Grammar Error Correction Score for a given text to differentiate between human-written and LLM-generated texts.
Outcome:	The proposed method outperforms current state-of-the-art zero-shot and supervised methods, achieving an average AUROC of 98.62% across XSum and Writing Prompts datasets.

Rethinking Text-based Protein Understanding: Retrieval or LLM? (2025.emnlp-main)

Copied to clipboard

Juntong Wu, Zijing Liu, He Cao, Li Hao, Bin Feng, Zishan Shu, Ke Yu, Li Yuan, Yu Li

From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge (2025.emnlp-main)

Challenge:	Recent studies have focused on integrating protein-related knowledge into large language models through continued pretraining and multi-modal alignment.
Approach:	They propose a retrieval-enhanced method which significantly outperforms fine-tuned LLMs for protein-to-text generation and shows accuracy and efficiency in training-free scenarios.
Outcome:	The proposed method significantly outperforms fine-tuned LLMs for protein-to-text generation and shows accuracy and efficiency in training-free scenarios.

Copied to clipboard

Dawei Li, Bohan Jiang, Liangjie Huang, Alimohammad Beigi, Chengshuai Zhao, Zhen Tan, Amrita Bhattacharjee, Yuxuan Jiang, Canyu Chen, Tianhao Wu, Kai Shu, Lu Cheng, Huan Liu

Challenge:	Recent advances in Large Language Models (LLMs) inspire the "LLM-as-a-judge" paradigm . traditional methods of assessment and evaluation fail in dynamic and open-ended scenarios .
Approach:	They propose a paradigm where LLMs are leveraged to perform scoring, ranking, or selection for machine learning evaluation scenarios.
Outcome:	The proposed model-based judgment and evaluation paradigms are based on large language models and are compared to the current model-driven evaluation paradigm.

Logical Form Generation via Multi-task Learning for Complex Question Answering over Knowledge Bases (2022.coling-1)

Copied to clipboard

Xixin Hu, Xuan Wu, Yiheng Shu, Yuzhong Qu

Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements (2025.findings-acl)

Challenge:	Existing generation-based KBQA methods that translate natural language questions to executable logical forms are proving promising but noise introduced can lead to incorrect results.
Approach:	They propose a Generation-based KBQA method that uses auxiliary information to enhance logical form generation by combining unseen KB items with novel combinations.
Outcome:	The proposed method achieves state-of-the-art results on ComplexWebQuestions and WebQuestIONSSP datasets.

Copied to clipboard

Shu Yang, Shenzhe Zhu, Zeyu Wu, Keyu Wang, Junchi Yao, Junchao Wu, Lijie Hu, Mengdi Li, Derek F. Wong, Di Wang

Robustness in NLP

Challenge:	Existing fraud detection benchmarks focus on single-turn classification tasks, failing to capture dynamic nature of real-world fraud attempts.
Approach:	They propose a bilingual benchmark to assess LLMs' ability to resist fraud and phishing attacks across five key fraud categories: Fraudulent Services, Impersonation, Phishing Scams, Fake Job Postings, and Online Relationships.
Outcome:	The proposed model improves in role-play settings and in e-commerce and recommendation systems.

Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks (2026.findings-acl)

Copied to clipboard

Yuxiang Zhang, Jiangming Shu, Ye Ma, Xueyuan Lin, Shangxi Wu, Jitao Sang

Reasoning

Challenge:	Existing approaches to managing working memory are based on external mechanisms that lack awareness of the agent’s reasoning state, leading to suboptimal decisions.
Approach:	They propose a framework that treats working memory management as learnable policy actions and enables joint optimization of information retention and task performance through end-to-end reinforcement learning.
Outcome:	The proposed framework matches models 16 larger while reducing average context length by 51%, with learned strategies that adapt to model capabilities and generalize across task complexities.

Rethinking Prompt-based Debiasing in Large Language Model (2025.findings-acl)

Copied to clipboard

Xinyi Yang, Runzhe Zhan, Shu Yang, Junchao Wu, Lidia S. Chao, Derek F. Wong

Knowledge Graph Enhanced Large Language Model Editing (2024.emnlp-main)

Challenge:	Existing prompt-based methods for debiasing are often superficial and lack a thorough understanding of complex bias concepts.
Approach:	They analyze a BBQ and stereoSet benchmarks to examine the assumption that large language models understand biases.
Outcome:	The proposed model misclassified 90% of unbiased content as biased despite high accuracy on BBQ dataset . the proposed model may have been flawed in previous attempts to debiase .

Copied to clipboard

Mengqi Zhang, Xiaotian Ye, Qiang Liu, Pengjie Ren, Shu Wu, Zhumin Chen

Counterfactual Debiasing for Fact Verification (2023.acl-long)

Challenge:	Existing methods for editing large language models struggle to track and incorporate changes in knowledge associated with edits, which limits the generalization ability of post-edit LLMs in processing edited knowledge.
Approach:	They propose a model editing method that leverages knowledge graphs to enhance LLM editing by capturing changes in associated knowledge by constructing an external graph.
Outcome:	The proposed method improves the generalization ability of LLMs in processing edited knowledge.

Copied to clipboard

Weizhi Xu, Qiang Liu, Shu Wu, Liang Wang

Reinforcement Learning–Guided Adaptive Tuning for Out-of-Distribution Harmful Text Detection (2026.acl-long)

Challenge:	Existing methods for debiasing factchecking models learn such biases instead of understanding the semantic relationship between the claim and evidence.
Approach:	They propose a counterfactual framework CLEVER which is augmentation-free and mitigates biases on the inference stage.
Outcome:	The proposed method is augmentation-free and mitigates biases on the inference stage.

Copied to clipboard

Mengyu Xiang, Tinghao Chen, Boxu Han, Qiudan Li, Shu Wu, Daniel Dajun Zeng

Learning Latent Relations for Temporal Knowledge Graph Reasoning (2023.acl-long)

Challenge:	Existing methods for testing harmful information on social media rely on fixed parameters that fail to handle substantial semantic discrepancies . RLAT can be used to adapt to semantic variations while preventing overfitting from continuous tuning.
Approach:	They propose a reinforcement learning-guided adaptive tuning method for harmful text detection that optimizes consistency loss and applies word-level attention constraints to reduce over-reliance on local words.
Outcome:	The proposed method outperforms state-of-the-art models in cross-platform and cross-temporal scenarios across multiple public datasets.

Copied to clipboard

Mengqi Zhang, Yuwei Xia, Qiang Liu, Shu Wu, Liang Wang

Structured Data in NLP

Challenge:	Existing methods for Temporal Knowledge Graph reasoning capture intra- and inter-time latent relations between entities that appear at different times.
Approach:	They propose a Latent relations Learning method for TKG reasoning that captures latent relations between entities at different times.
Outcome:	The proposed method exploits the intra- and inter-time latent relations of entities at different times.

MetaTKG: Learning Evolutionary Meta-Knowledge for Temporal Knowledge Graph Reasoning (2022.emnlp-main)

Copied to clipboard

Yuwei Xia, Mengqi Zhang, Qiang Liu, Shu Wu, Xiao-Yu Zhang

When Safety Alignment Fails to Generalize: Probing with Language Game Jailbreaks (2026.findings-acl)

Challenge:	Existing models rely on historical information to learn embeddings for entities, but ignore the evolution of facts.
Approach:	They propose a Temporal Meta-learning framework to learn evolutionary meta-knowledge from TKGs.
Outcome:	The proposed method improves on four widely-used datasets and three backbones on a wide range of scenarios on tKGs.

Copied to clipboard

Zewen Long, Yu Peng, Fangming Dong, Congyi Li, Xingmao Guan, Shu Wu, Kai Chen

M3TQA: Massively Multilingual Multitask Table Question Answering (2026.findings-acl)

Challenge:	Existing safety alignment methods rely on fixed or narrow transformation schemes to generalize . existing methods based on fixed and narrow transformations are often inadequate .
Approach:	They propose a framework for discovering and refining language game-based jailbreaks to probe alignment generalization.
Outcome:	The proposed framework allows controlled exploration of alignment behavior across closely related linguistic variants.

Copied to clipboard

Daixin Shu, Jian Yang, Zhenhe Wu, Xianjie Wu, Xianfu Cheng, Guan Xiangyuan, Yanghai Wang, Pengfei Wu, Tingyang Yang, Hualei Zhu, Wei Zhang, Ge Zhang, Jiaheng Liu, Zhoujun Li

Structured Data in NLP

Challenge:	Existing multilingual table benchmarks suffer from geolinguistic imbalance - overrepresenting certain languages and lacking sufficient scale for rigorous cross-lingual analysis.
Approach:	They propose a framework for massively multilingual table question answering that includes tables expanded to 97 languages from Chinese and English sources.
Outcome:	Experiments on state-of-the-art LLMs show that synthetically generated training data significantly boosts performance, especially for low-resource languages.

SHARP: Steering Hallucination in LVLMs via Representation Engineering (2025.emnlp-main)

Copied to clipboard

Junfei Wu, Yue Ding, Guofan Liu, Tianze Xia, Ziyue Huang, Dianbo Sui, Qiang Liu, Shu Wu, Liang Wang, Tieniu Tan

On the Generation of Medical Dialogs for COVID-19 (2021.acl-short)

Challenge:	Large Vision-Language Models (LVLMs) generate responses that are plausible but incorrect or unsupported—commonly referred to as hallucinations.
Approach:	They propose a representation-level intervention framework that modulates hallucination-related features during inference by probing their encoded features.
Outcome:	The proposed framework reduces hallucinations while maintaining the performance and generalization capabilities of Large Vision-Language Models (LVLMs).

Copied to clipboard

Meng Zhou, Zechen Li, Bowen Tan, Guangtao Zeng, Wenmian Yang, Xuehai He, Zeqian Ju, Subrato Chakravorty, Shu Chen, Xingyi Yang, Yichen Zhang, Qingyang Wu, Zhou Yu, Kun Xu, Eric Xing, Pengtao Xie

Dialogue Systems & Conversational Agents

Challenge:	under the pandemic of COVID-19, people experiencing COVI D19-related symptoms have a pressing need to consult doctors.
Approach:	They develop a medical dialog system that can provide COVID19-related consultations . they use two dialog datasets containing conversations between doctors and patients .
Outcome:	The proposed system can provide COVID19-related consultations, but is too small compared with general-domain dialog datasets.

Can Large Language Models Identify Implicit Suicidal Ideation? An Empirical Evaluation (2025.findings-emnlp)

Copied to clipboard

Tong Li, Shu Yang, Junchao Wu, Jiyao Wei, Lijie Hu, Mengdi Li, Derek F. Wong, Joshua R. Oltmanns, Di Wang

Stealthy Attack on Large Language Model based Recommendation (2024.acl-long)

Challenge:	Existing data on suicidal ideation in private conversations are limited . a new dataset of 1,200 test cases is presented to address this gap .
Approach:	They propose a dataset of 1,200 test cases simulating implicit suicidal ideation in private contexts.
Outcome:	The proposed dataset includes 1,200 test cases simulating implicit suicidal ideation in dialogue scenarios.

Copied to clipboard

Jinghao Zhang, Yuting Liu, Qiang Liu, Shu Wu, Guibing Guo, Liang Wang

Robustness in NLP

Challenge:	Recent advances in recommender systems have been overlooked due to their emphasis on textual content.
Approach:	They propose to introduce large language models into recommendation models to exploit the semantic understanding and strong transferability of LLMs.
Outcome:	The proposed approach significantly boosts an item’s exposure by altering its textual content during the testing phase, without requiring direct interference with the model’s training process.

Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders (2025.emnlp-main)

Copied to clipboard

Dong Shu, Xuansheng Wu, Haiyan Zhao, Mengnan Du, Ninghao Liu

REACT: Representation Extraction And Controllable Tuning to Overcome Overfitting in LLM Knowledge Editing (2025.emnlp-main)

Challenge:	Sparse Autoencoders (SAEs) have recently emerged as powerful tools for interpreting and steering the internal representations of large language models (LLMs).
Approach:	They propose a method that identifies the most influential latents by incorporating output-side gradient information.
Outcome:	The proposed method identifies the most influential latents by incorporating output-side gradient information.

Copied to clipboard

Haitian Zhong, Yuhuan Liu, Ziyang Xu, Guofan Liu, Qiang Liu, Shu Wu, Zhe Zhao, Liang Wang, Tieniu Tan

Look Both Ways and No Sink: Converting LLMs into Text Encoders without Training (2025.acl-long)

Challenge:	Large language model editing methods suffer from overfitting, where factual updates can propagate beyond their intended scope, overemphasizing the edited target even when it’s contextually inappropriate.
Approach:	They propose a framework for precise and controllable knowledge editing that utilizes two-phase representations and a linear transformation to compute a directional "belief shift" vector.
Outcome:	The proposed framework significantly reduces overfitting across nearly all evaluation metrics and on COUNTERFACT and MQuAKE.

Copied to clipboard

Ziyong Lin, Haoyi Wu, Shu Wang, Kewei Tu, Zilong Zheng, Zixia Jia

Thinking Beyond the Local: Multi-View Instructed Adaptive Reasoning in KG-Enhanced LLMs (2026.findings-eacl)

Challenge:	Existing methods for converting large language models into powerful text encoders require extensive training on large datasets.
Approach:	They propose a training-free approach that enables bidirectional attention and suppresses the attention sink phenomenon, resulting in superior performance.
Outcome:	The proposed approach enables bidirectional attention and suppresses the attention sink phenomenon, resulting in superior performance.

Copied to clipboard

Minghan Zhang, Shu Zhao, Zhen Yang, Hongsheng Wu, Yongxing Lin, Haodong Zou, Jie Chen, Zhen Duan

Knowledge Representation

Challenge:	Existing methods for large language models adopt query-driven iterative reasoning from a local perspective, limiting efficiency and accuracy for complex multi-hop tasks.
Approach:	They propose a multi-view instructed adaptive reasoning of LLM on Knowledge Graphs that allows LLMs to plan, evaluate, and adapt reasoning paths from a global perspective.
Outcome:	The proposed model overcomes the limitations of local exploration by enabling LLMs to plan, evaluate, and adapt reasoning paths from a global perspective.

Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAG (2025.acl-long)

Copied to clipboard

Xin Sun, Jianan Xie, Zhongqi Chen, Qiang Liu, Shu Wu, Yuehe Chen, Bowen Song, Zilei Wang, Weiqiang Wang, Liang Wang

Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks (2020.acl-main)

Challenge:	Large language models (LLMs) augmented with retrieval systems have significantly advanced natural language processing tasks by integrating external knowledge sources.
Approach:	They propose a method that conditions large language models to generate answers even in the absence of reliable knowledge.
Outcome:	The proposed approach balances accuracy with appropriate abstention, enhancing the reliability and trustworthiness of retrieval-augmented systems.

Copied to clipboard

Yufeng Zhang, Xueli Yu, Zeyu Cui, Shu Wu, Zhongzhen Wen, Liang Wang

Information Extraction & Text Mining

Challenge:	Existing graph-based methods for text classification cannot capture contextual word relationships within each document nor can they produce inductive learning of new words.
Approach:	They propose to use Graph Neural Networks to learn the local word representations and then aggregate the word nodes as the document embeddings.
Outcome:	The proposed method outperforms state-of-the-art methods on four benchmark datasets.

SepSeq: A Training-Free Framework for Long Numerical Sequence Processing in LLMs (2026.findings-acl)

Copied to clipboard

Jie Sun, Yu Liu, Lu Han, Qiwen Deng, Xiang Shu, Yang Xiao, Lintao Ma, Xingyu Lu, Jun Zhou, Pengfei Liu, Jiancan Wu, Xiang Wang

Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting (2025.findings-acl)

Challenge:	Existing large-scale large-context models suffer from performance degradation when processing long numerical sequences.
Approach:	They propose a framework to mitigate attention dispersion by strategically inserting separator tokens into the model to recalibrat attention to local segments while preserving global context.
Outcome:	The proposed framework improves accuracy and reduces inference token consumption by 16.4% on 9 widely-adopted LLMs.

Copied to clipboard

Hao Feng, Shu Wei, Xiang Fei, Wei Shi, Yingdong Han, Lei Liao, Jinghui Lu, Binghong Wu, Qi Liu, Chunhui Lin, Jingqun Tang, Hao Liu, Can Huang

Noise-Robust Semi-Supervised Learning for Distantly Supervised Relation Extraction (2023.findings-emnlp)

Challenge:	Current document image parsing solutions rely on specialized models or generate content autoregressively.
Approach:	They propose a multimodal document image parsing model that integrates specialized models with autogeneous content generation.
Outcome:	The proposed model achieves state-of-the-art performance across diverse page-level and element-level settings while ensuring superior efficiency.

Copied to clipboard

Xin Sun, Qiang Liu, Shu Wu, Zilei Wang, Liang Wang

Position Paper: Data-Centric AI in the Age of Large Language Models (2024.findings-emnlp)

Challenge:	Distantly supervised relation extraction (DSRE) methods are not capable of extracting relation labels for individual sentences.
Approach:	They propose a semi-supervised learning relation extraction framework for sentence-level DSRE . they discard only the labels of the noisy samples and utilize them as unlabeled samples .
Outcome:	The proposed framework achieves significant performance enhancements on two real-world datasets.

Copied to clipboard

Xinyi Xu, Zhaoxuan Wu, Rui Qiao, Arun Verma, Yao Shu, Jingtan Wang, Xinyuan Niu, Zhenfeng He, Jiangwei Chen, Zijian Zhou, Gregory Kang Ruey Lau, Hieu Dao, Lucas Agussurja, Rachael Hwee Ling Sim, Xiaoqiang Lin, Wenyang Hu, Zhongxiang Dai, Pang Wei Koh, Bryan Kian Hsiang Low

RLShield: Dynamic Jailbreak Detection for LLMs via Reinforced Adaptive Learning (2026.findings-acl)

Challenge:	a paper proposes a data-centric perspective of AI research, focusing on large language models.
Approach:	They propose a data-centric viewpoint of AI research, focusing on large language models . they propose four scenarios centered around data, including data curation, attribution, knowledge transfer .
Outcome:	The proposed research focuses on large language models with data centric benchmarks . the proposed benchmarks can be used to develop new data curation methods .

Copied to clipboard

Zhao Tong, Pengfei Yang, Yimeng Gu, Haichao Shi, Qiang Liu, Xingcheng Xu, Shu Wu, Xiao-Yu Zhang