Papers by Shu Wang

DynamicFocalPO: Adaptive Focusing Strategy for Preference Optimization (2026.findings-acl)

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

Shu Zhou, Junan Chen, Rui Ling, Xin Wang, Tao Fan, Hao Wang

The Retrieval Bottleneck: Scaling Laws for Reinforcement Learning in RAG (2026.acl-long)

Challenge:	Recent preference optimization algorithms such as Direct Preference Optimization (DPO) have become prevalent for aligning large language models with human preferences.
Approach:	They propose a preference optimization algorithm that introduces a modulating factor that down-weighs misranked preference pairs and employs focusing strategy that adapts over the course of training.
Outcome:	Experiments show that DynamicFocalPO surpasses both DPO and FocalPO on benchmarks including Alpaca Eval 2.0 and Arena-Hard using Mistral-Base-7B and Llama-3-Instruct-8B.

Copied to clipboard

Shu Zhou, Jinman Leng, Yufei Song, Xin Wang, Tao Fan, Hao Wang

Enhancing Extractive Question Answering in Multiparty Dialogues with Logical Inference Memory Network (2025.coling-main)

Challenge:	Retrieval-augmented generation (RAG) has become the dominant paradigm for building knowledge-intensive language systems.
Approach:	They propose a sigmoidal scaling law that shows that retrieval quality determines the asymptotic performance ceiling.
Outcome:	The proposed model achieves strong performance on knowledge-intensive benchmarks while retaining the predictable scaling long available for pre-training but previously absent in RAG-RL.

Copied to clipboard

Shu Zhou, Rui Zhao, Zhengda Zhou, Haohan Yi, Xuhui Zheng, Hao Wang

Natural Language Interfaces

Challenge:	Existing models for multiparty dialogue question answering (QA) do not consider logical inference relations in multiparty dialogs, leading to suboptimal performance.
Approach:	They propose a memory network with logical inference for extractive QA in multiparty dialogues.
Outcome:	The proposed model achieves state-of-the-art on Molweni and FriendsQA benchmarks.

Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs (2026.acl-long)

Copied to clipboard

Wenrui Zhou, Mohamed Hendy, Shu Yang, Qingsong Yang, Zikun Guo, Yuyu Luo, Lijie Hu, Di Wang

Adaptive Attentional Network for Few-Shot Knowledge Graph Completion (2020.emnlp-main)

Challenge:	Current sycophancy research has largely overlooked its specific manifestations in the video-language domain.
Approach:	They propose a video-LLM sycophancy benchmarking and evaluation to evaluate scophancies in video-LLMs.
Outcome:	The proposed benchmark evaluates sycophantic behavior in state-of-the-art Video-LLMs across diverse question formats, prompt biases, and visual reasoning tasks.

Copied to clipboard

Jiawei Sheng, Shu Guo, Zhenyu Chen, Juwei Yue, Lihong Wang, Tingwen Liu, Hongbo Xu

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

Challenge:	Recent attempts to learn static representations of entities and references ignore their dynamic properties.
Approach:	They propose to learn static representations of entities and references ignoring their dynamic properties . a neighbor encoder learns entities' roles while a query-aware aggregator learns references' contributions .
Outcome:	The proposed approach achieves state-of-the-art results with different few-shot sizes.

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

Are Intermediate Layers and Labels Really Necessary? A General Language Model Distillation Method (2023.findings-acl)

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

Shicheng Tan, Weng Lam Tam, Yuanchun Wang, Wenwen Gong, Shu Zhao, Peng Zhang, Jie Tang

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

Challenge:	Existing knowledge distillation methods rely on intermediate layer features and golden labels, which require aligned model architecture and labeled data respectively.
Approach:	They propose a general language model distillation method that performs two-stage word prediction distillation and vocabulary compression, which is simple and shows extremely strong performance.
Outcome:	The proposed method outperforms 25 state-of-the-art methods on the SuperGLUE benchmark, achieving an average score that surpasses the best method by 3%.

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

Multi-Modal Knowledge Graph Transformer Framework for Multi-Modal Entity Alignment (2023.findings-emnlp)

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

Qian Li, Cheng Ji, Shu Guo, Zhaoji Liang, Lihong Wang, Jianxin Li

Controllable Text Generation with Focused Variation (2020.findings-emnlp)

Challenge:	Multi-modal entity alignment (MMEA) is a critical task that aims to identify equivalent entity pairs across multi-modal knowledge graphs (MMKGs).
Approach:	They propose a novel MMEA transformer that hierarchically introduces neighbor features, multi-modal attributes, and entity types to enhance alignment task.
Outcome:	The proposed transformer hierarchically introduces neighbor features, multi-modal attributes, and entity types to enhance the alignment task.

Copied to clipboard

Lei Shu, Alexandros Papangelis, Yi-Chia Wang, Gokhan Tur, Hu Xu, Zhaleh Feizollahi, Bing Liu, Piero Molino

Text Generation

Challenge:	Focused-Variation Network (FVN) is a new model to control language generation.
Approach:	They propose a model that learns discrete latent spaces for each attribute inside codebooks and uses them to generate fluent text.
Outcome:	The proposed model can generate fluent and mostly coherent text on two text generation datasets with annotated content and style, and show state-of-the-art performance as assessed by automatic and human evaluations.

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

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

Understanding How Value Neurons Shape the Generation of Specified Values in LLMs (2025.findings-emnlp)

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

Yi Su, Jiayi Zhang, Shu Yang, Xinhai Wang, Lijie Hu, Di Wang

Explainability & Interpretability in NLP

Challenge:	Current approaches to interpret value representations are limited by superficial judgments over mechanistic analysis.
Approach:	They propose a mechanistic interpretability framework that uses the Schwartz Values Survey to interpret value . they use a dataset that operationalizes four dimensions of universal value through behavioral contexts .
Outcome:	The proposed method bridges psychological value frameworks with neuron analysis in large language models.

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

Copied to clipboard

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

MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering (2025.findings-acl)

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

Jingqun Tang, Qi Liu, Yongjie Ye, Jinghui Lu, Shu Wei, An-Lan Wang, Chunhui Lin, Hao Feng, Zhen Zhao, Yanjie Wang, Yuliang Liu, Hao Liu, Xiang Bai, Can Huang

Multilinguality

Challenge:	Text-Centric Visual Question Answering (TEC-VQA) is a text-centric visual task understanding tool.
Approach:	They introduce a benchmark that features human expert annotations across 9 languages . they prioritize the text in question-answer pairs while disregarding visual text in images .
Outcome:	The proposed benchmarks prioritize the text in question-answer pairs while disregarding visual text in images.

Explainable Claim Verification via Knowledge-Grounded Reasoning with Large Language Models (2023.findings-emnlp)

Copied to clipboard

Haoran Wang, Kai Shu

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

Challenge:	Existing claims verification models rely on annotated data, which is expensive to create at a large scale.
Approach:	They propose a model that can verify complex claims without annotated data . they leverage the in-context learning ability of Large Language Models to translate a claim into a First-Order-Logic clause .
Outcome:	The proposed model outperforms baseline models on three datasets . it performs well on the datasets, and the results are published online.

Copied to clipboard

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

Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images (2026.acl-long)

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

Qishun Yang, Shu Yang, Lijie Hu, Di Wang

Visual Data in NLP

Challenge:	Existing methods require explicit safety labels or contrastive data, yet visual inputs enable harmful outputs.
Approach:	They propose a visual self-fulfilling alignment mechanism that fine-tunes vision-language models on neutral VQA tasks without any safety labels.
Outcome:	The proposed approach reduces attack success rate, improves response quality, and mitigates over-refusal while preserving general capabilities.

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

Taxonomy-Guided Zero-Shot Recommendations with LLMs (2025.coling-main)

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

Yueqing Liang, Liangwei Yang, Chen Wang, Xiongxiao Xu, Philip S. Yu, Kai Shu

AutoMonitor-Bench: Evaluating the Reliability of LLM-Based Misbehavior Monitor (2026.findings-acl)

Challenge:	Existing approaches to deploy large language models (LLMs) into RecSys have limited prompt length, unstructured item information, and un-constrained generation of recommendations.
Approach:	They propose a taxonomy-guided recommendation framework that empowers LLMs with category information in a systematic approach.
Outcome:	The proposed framework significantly improves recommendation quality compared to zero-shot approaches.

Copied to clipboard

Shu Yang, Jingyu Hu, Tong Li, Hanqi Yan, Wenxuan Wang, Di Wang

Challenge:	AutoMonitor-Bench evaluates the reliability of LLM-based misbehavior monitors across diverse tasks and failure modes.
Approach:	They introduce AutoMonitor-Bench, a benchmark designed to evaluate misbehavior monitors across diverse tasks and failure modes.
Outcome:	The new benchmark evaluates the reliability of LLM-based misbehavior monitors across tasks and failure modes.

RPC-Bench: A Fine-grained Benchmark for Research Paper Comprehension (2026.acl-long)

Copied to clipboard

Yelin Chen, Fanjin Zhang, Suping Sun, Yunhe Pang, Yuanchun Wang, Jian Song, XiaoYan Li, Lei Hou, Shu Zhao, Jie Tang, Juanzi Li

Challenge:	Existing benchmarks for understanding research papers offer limited fine-grained evaluation at scale.
Approach:	They propose a large-scale question-answering benchmark built from review–rebuttal exchanges of high-quality computer science papers.
Outcome:	The proposed model is based on human-verified QA pairs and contains 15K questions.

Dual-Gated Fusion with Prefix-Tuning for Multi-Modal Relation Extraction (2023.findings-acl)

Copied to clipboard

Qian Li, Shu Guo, Cheng Ji, Xutan Peng, Shiyao Cui, Jianxin Li, Lihong Wang

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

Challenge:	Existing methods for multi-modal relation extraction lack useful visual information.
Approach:	They propose a novel multi-modal relation extraction framework to capture deeper correlations of text, entity pair, and image/objects.
Outcome:	The proposed framework captures the deeper correlations of text, entity pair, and image/objects, and extracts useful information.

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

CuMA: Aligning LLMs with Sparse Cultural Values via Demographic-Aware Mixture of Adapters (2026.acl-long)

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

Ao Sun, Xiaoyu Wang, Zhe Tan, Yu Li, Zhu Jiachen, Yuheng Jia, Shu Su

Real-time Ad Retrieval via LLM-generative Commercial Intention for Sponsored Search Advertising (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) have a global audience, so alignment must extend to cultural resonance.
Approach:	They propose a framework that frames alignment as a conditional capacity separation problem.
Outcome:	The proposed framework outperforms both dense baselines and semantic-only MoEs on three large language models.

Copied to clipboard

Tongtong Liu, Zhaohui Wang, Meiyue Qin, Zenghui Lu, Xudong Chen, Yuekui Yang, Peng Shu

Memorize Step by Step: Efficient Long-Context Prefilling with Incremental Memory and Decremental Chunk (2024.emnlp-main)

Challenge:	Existing methods for retrieving documents and ads use one-to-few mappings and time-consuming content extraction.
Approach:	They propose a framework that leverages LLM-generated commercial intents as an intermediate semantic representation to directly retrieve ads for queries in real-time.
Outcome:	The proposed framework has been implemented in a real-world online system, handling daily search volumes in billions.

Copied to clipboard

Zhiyuan Zeng, Qipeng Guo, Xiaoran Liu, Zhangyue Yin, Wentao Shu, Mianqiu Huang, Bo Wang, Yunhua Zhou, Linlin Li, Qun Liu, Xipeng Qiu

Green & Sustainable NLP

Challenge:	Existing methods to optimize LLM for long sequences for long documents are slow and consume memory.
Approach:	They propose a method that starts with a small memory size and gradually increases it . they propose Decremental Chunk based on Incremental Memory (IMDC) which reduces chunk size while increasing memory size .
Outcome:	The proposed method is faster (1.45x) and reduces GPU memory consumption by 23.3% compared to fixed-size memory.

MedDialog: Large-scale Medical Dialogue Datasets (2020.emnlp-main)

Copied to clipboard

Guangtao Zeng, Wenmian Yang, Zeqian Ju, Yue Yang, Sicheng Wang, Ruisi Zhang, Meng Zhou, Jiaqi Zeng, Xiangyu Dong, Ruoyu Zhang, Hongchao Fang, Penghui Zhu, Shu Chen, Pengtao Xie

Dialogue Systems & Conversational Agents

Challenge:	telemedicine is a medical practice that provides patient care remotely using video conferencing tools.
Approach:	They build large-scale medical dialogue datasets to facilitate research . they pretrain several models on the Chinese MedDialog dataset and compare their performance .
Outcome:	The proposed datasets show that models trained on MedDialog can generate doctor-like medical dialogues.

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

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.

CasEE: A Joint Learning Framework with Cascade Decoding for Overlapping Event Extraction (2021.findings-acl)

Copied to clipboard

Jiawei Sheng, Shu Guo, Bowen Yu, Qian Li, Yiming Hei, Lihong Wang, Tingwen Liu, Hongbo Xu

Information Extraction & Text Mining

Challenge:	Existing methods assume that events appear in sentences without overlaps . overlapping event extraction is a challenging task in natural language understanding .
Approach:	They propose a joint learning framework with cascade decoding for overlapping event extraction . they sequentially perform type detection, trigger extraction and argument extraction based on the specific former prediction .
Outcome:	The proposed framework improves on a public event extraction benchmark . it sequentially performs type detection, trigger extraction and argument extraction .

RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning (2022.emnlp-main)

Copied to clipboard

Mingkai Deng, Jianyu Wang, Cheng-Ping Hsieh, Yihan Wang, Han Guo, Tianmin Shu, Meng Song, Eric Xing, Zhiting Hu

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

Challenge:	Existing methods for finding the optimal prompt for a task are difficult to optimize.
Approach:	They propose an efficient discrete prompt optimization approach with reinforcement learning that generates the optimal discrete stimulus after training with reward.
Outcome:	The proposed approach is based on a parameter-efficient policy network that generates the optimal discrete prompt after training with reward.

Copied to clipboard

Weizhi Xu, Qiang Liu, Shu Wu, Liang Wang

Learning Latent Relations for Temporal Knowledge Graph Reasoning (2023.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

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.

LATTE: Learning to Think with Vision Specialists (2025.emnlp-main)

Copied to clipboard

Zixian Ma, Jianguo Zhang, Zhiwei Liu, Jieyu Zhang, Juntao Tan, Manli Shu, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Caiming Xiong, Ranjay Krishna, Silvio Savarese

Piecing It All Together: Verifying Multi-Hop Multimodal Claims (2025.coling-main)

Challenge:	Open-source vision-language models excel on simple question-answering tasks, but struggle with complex questions that require both perception and reasoning.
Approach:	They propose a family of vision-language models that have LeArned to Think wiTh vision spEcialists by offloading perception to state-of-the-art vision models.
Outcome:	The proposed model achieves 4-5% gains over baselines across 6 benchmarks covering both perception and reasoning abilities.

Copied to clipboard

Haoran Wang, Aman Rangapur, Xiongxiao Xu, Yueqing Liang, Haroon Gharwi, Carl Yang, Kai Shu

Reasoning

Challenge:	Existing claim verification datasets often do not require systems to perform complex reasoning or effectively interpret multimodal evidence.
Approach:	They propose a task that requires models to reason over multiple pieces of evidence . they construct a large-scale dataset comprising 15k multi-hop claims paired with multimodal evidence - generated and refined using large language models with additional input from human feedback.
Outcome:	The proposed method is based on human performance benchmarks and human reasoning hops.

Understanding the Repeat Curse in Large Language Models from a Feature Perspective (2025.findings-acl)

Copied to clipboard

Junchi Yao, Shu Yang, Jianhua Xu, Lijie Hu, Mengdi Li, Di Wang

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

Challenge:	Large language models suffer from repetitive text generation, a phenomenon we refer to as the ”Repeat Curse”.
Approach:	They propose a method to induce and analyze the Repeat Curse in large language models by using mechanistic interpretability.
Outcome:	The proposed method induces and analyzes the Repeat Curse in large language models using mechanistic interpretability.

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.

MERIT: Multi-Agent Collaboration for Unsupervised Time Series Representation Learning (2025.findings-acl)

Copied to clipboard

Shu Zhou, Yunyang Xuan, Yuxuan Ao, Xin Wang, Tao Fan, Hao Wang

An Efficient Conversational Smart Compose System (2023.acl-demo)

Challenge:	Existing approaches to time series representation learning are time-consuming and expert-dependent, which are difficult to generalize across different tasks.
Approach:	They propose to use large language model agent to guide unsupervised time series representation learning and a framework to integrate three LLM agents to collaboratively generate positive views for time series data.
Outcome:	The proposed framework integrates large language model (LLM) agent to guide unsupervised time series representation learning and compares it with state-of-the-art baselines on multiple time series datasets.

Copied to clipboard

Yun Zhu, Xiayu Chen, Lei Shu, Bowen Tan, Xinying Song, Lijuan Liu, Maria Wang, Jindong Chen, Ning Ruan

Dialogue Systems & Conversational Agents

Challenge:	a cloud-based smart compose system is designed to improve human-to-human conversation efficiency.
Approach:	They propose a cloud-based smart compose system to improve conversation efficiency . they propose heuristics to achieve the best trade-off between quality and latency .
Outcome:	The proposed system reduces latency without losing composing quality further.

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

From Competition to Synergy: Unlocking Reinforcement Learning for Subject-Driven Image Generation (2026.acl-long)

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

Ziwei Huang, Ying Shu, null Fanghao, Quanyu Long, Wenya Wang, Qiushi Guo, Tiezheng Ge, Leilei Gan

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

Challenge:	a naive application of GRPO leads to conflicting gradient signals and a misalignment with the temporal dynamics of the diffusion process.
Approach:	They propose a framework that uses synergy-aware reward shaping to penalize conflicted reward signals and amplify synergies to provide a sharper and decisive gradient.
Outcome:	The proposed framework outperforms naive GRPO and Time-Aware Dynamic Weighting (TDW) on DreamBench, and achieves a state-of-the-art balance between ID preservation and prompt adherence.

Copied to clipboard

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

Document-level Relation Extraction with Dual-tier Heterogeneous Graph (2020.coling-main)

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

Zhenyu Zhang, Bowen Yu, Xiaobo Shu, Tingwen Liu, Hengzhu Tang, Wang Yubin, Li Guo

Information Extraction & Text Mining

Challenge:	Existing methods focus on extracting relations from single sentence . document-level relation extraction requires a comprehension of the whole document .
Approach:	They propose a graph-based model with Dual-tier Heterogeneous Graph (DHG) for document-level relation extraction.
Outcome:	The proposed model achieves state-of-the-art performance on two widely used datasets.

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

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.

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

Copied to clipboard

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

GKD: A General Knowledge Distillation Framework for Large-scale Pre-trained Language Model (2023.acl-industry)

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

Shicheng Tan, Weng Lam Tam, Yuanchun Wang, Wenwen Gong, Shu Zhao, Peng Zhang, Jie Tang

FinChart-Bench: Benchmarking Financial Chart Comprehension in Vision-Language Models (2026.acl-long)

Challenge:	Existing knowledge distillation frameworks for language models are limited by memory and the use of complex distillation methods on larger-scale PLMs.
Approach:	They propose a general knowledge distillation framework that supports distillation on larger-scale PLMs using various distillation methods.
Outcome:	The proposed framework can support distillation on larger-scale PLMs and 25 mainstream methods on 8 NVIDIA A100 (40GB) GPUs.

Copied to clipboard

Dong Shu, Haoyang Yuan, Yuchen Wang, Yanguang Liu, Huopu Zhang, Mengnan Du

Improving LLM Reasoning through Interpretable Role-Playing Steering (2025.findings-emnlp)

Challenge:	FinChart-Bench is the first benchmark specifically focused on real-world financial charts.
Approach:	They propose a benchmark specifically focused on real-world financial charts.
Outcome:	The proposed benchmark evaluates 26 state-of-the-art LVLMs on FinChart-Bench.

Copied to clipboard

Anyi Wang, Dong Shu, Yifan Wang, Yunpu Ma, Mengnan Du

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

Challenge:	Existing methods for role-playing rely on prompt engineering, which lacks stability and interpretability.
Approach:	They propose a framework that extracts latent representations from role-play prompts and constructs a steering vector that can be injected into the model's residual stream with controllable intensity.
Outcome:	The proposed framework extracts latent representations from role-play prompts, selects the most relevant features based on activation patterns, and constructs a steering vector that can be injected into the model’s residual stream with controllable intensity.

Copied to clipboard

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

CompTab: A Comprehensive Benchmark for Real-World TableQA with Complex Reasoning and Irregular Tables (2026.acl-long)

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

Zhen Yang, Wei Du, Jie Wang, Wenze Zhou, Xiangfeng Meng, Zhengyang Wang, Suping Sun, Ziwei Du, Haodong Zou, Jie Chen, Yongbin Liu, Shicheng Tan, Jiahao Ying, Shu Zhao

M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions (2024.acl-long)

Challenge:	Existing benchmarks focus on well-structured tables and fail to reflect irregular structures and complex reasoning commonly encountered in real-world scenarios.
Approach:	They propose a benchmark to evaluate TableQA under complex reasoning and irregular table conditions.
Outcome:	The proposed framework improves generalization and realism of large language models under complex and irregular table conditions.

Copied to clipboard

Zheng Wang, Shu Teo, Jieer Ouyang, Yongjun Xu, Wei Shi

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

Challenge:	Existing methods for retrieving relevant memories from an external database are coarse-grained and can cause noise and focus on crucial memories.
Approach:	They propose a multiple partition paradigm for RAG where each database partition serves as a basic unit for execution.
Outcome:	The proposed framework outperforms baseline methods on three language generation tasks on seven datasets.

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

When More Thinking Hurts: Overthinking in LLM Test-Time Compute Scaling (2026.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

Shu Zhou, Rui Ling, Junan Chen, Xin Wang, Tao Fan, Hao Wang

Reasoning

Challenge:	Existing research implicitly assumes that longer thinking leads to better results . a recent study suggests that test-time compute scaling is more effective than model scaling .
Approach:	They challenge the assumption that longer thinking yields better results . they show that models exhibit overthinking and marginal returns diminish at higher budgets .
Outcome:	The proposed framework reduces computation significantly while maintaining comparable accuracy.

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

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

Self-Reflective Generation at Test Time (2026.acl-long)

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

Jian Mu, Qixin Zhang, Zhiyong Wang, Menglin Yang, Shuang Qiu, Chengwei Qin, Zhongxiang Dai, Yao Shu

Reasoning

Challenge:	Existing self-reflection mechanisms are reactive and inefficient for large language models . a fundamental tension persists between the ability to execute complex multi-step reasoning and the ability of the model to generate coherent traces.
Approach:	They propose a test-time framework that reflects before generating at uncertain points . SRGen utilizes dynamic entropy thresholding to identify high-uncertainty tokens .
Outcome:	The proposed framework can significantly strengthen large language models' reasoning process.

Example Quality Matters: Multi-Aspects Example Augmentation for Private Library Programming (2026.acl-long)

Copied to clipboard

Yuhao Li, Haifeng Sun, Xuesong Zhang, Shu Yao, Haoyu Zheng, Yvchuan Wang, Huazheng Wang, Zirui Zhuang, Qi Qi, Jianxin Liao, Jingyu Wang