Papers by Han He

Semi-Supervised Reward Modeling via Iterative Self-Training (2024.findings-emnlp)

Challenge:	Prompt Engineering (PE) is renowned for improving IE performance through prompt modifications, but the realm of sample design for downstream fine-tuning remains unexplored.
Approach:	They propose a methodical approach to enhancing LLMs’ post-tuning performance by refining input, output, and reasoning designs.
Outcome:	The proposed approach outperforms heuristic design strategies on three complex IE tasks with four additional LLMs.

Copied to clipboard

Yifei He, Haoxiang Wang, Ziyan Jiang, Alexandros Papangelis, Han Zhao

Encoding Spreadsheets for Large Language Models (2024.emnlp-main)

Challenge:	Reward models capture values and preferences of humans and are used in Reinforcement Learning with Human Feedback (RLHF) Traditionally, training large language models relies on extensive human-annotated preference data, which poses significant challenges in terms of scalability and cost.
Approach:	They propose a method that enhances RM training using unlabeled data.
Outcome:	The proposed approach improves reward models without incurring additional labeling costs on unlabeled datasets.

Copied to clipboard

Haoyu Dong, Jianbo Zhao, Yuzhang Tian, Junyu Xiong, Mengyu Zhou, Yun Lin, José Cambronero, Yeye He, Shi Han, Dongmei Zhang

ScaleLLM: A Resource-Frugal LLM Serving Framework by Optimizing End-to-End Efficiency (2024.emnlp-industry)

Challenge:	Spreadsheets are characterized by their extensive two-dimensional grids, flexible layouts, and varied formatting options, which pose significant challenges for large language models (LLMs).
Approach:	They propose a structural-anchor-based compression, inverse index translation, and data-format-aware aggregation module to compress spreadsheets effectively.
Outcome:	The proposed method outperforms the existing model in GPT4 and achieves a state-of-the-art 78.9% F1 score.

Copied to clipboard

Yuhang Yao, Han Jin, Alay Shah, Shanshan Han, Zijian Hu, Dimitris Stripelis, Yide Ran, Zhaozhuo Xu, Salman Avestimehr, Chaoyang He

Green & Sustainable NLP

Challenge:	Large language models (LLMs) are widely used in commercial applications . low latency is crucial due to system latency, query concurrency, and computational resources constraints.
Approach:	They propose a system that can be resource-efficiently served by addressing bottlenecks beyond LLM inference . they propose 4.3 speed up over vLLM and 1.5 higher throughput .
Outcome:	The proposed system outperforms state-of-the-arts with 1.5 higher throughput . it achieves 4.3 speed up with 64 concurrent requests on Mixtral 8x7B .

All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG (2026.acl-long)

Copied to clipboard

Dan Wang, Guozhao Mo, Yafei Shi, Cheng Zhang, Bo Zheng, Boxi Cao, Xuanang Chen, Yaojie Lu, Hongyu Lin, Ben He, Xianpei Han, Le Sun

Multilinguality

Challenge:	Existing mRAG systems suffer from a language bias during reranking, systematically favoring English and the query’s native language.
Approach:	They propose a language-agnostic utility-driven reranker alignment technique to mitigate language bias during re-ranking.
Outcome:	The proposed approach mitigates language bias and consistently improves mRAG performance across languages.

Red-Teaming LLM Multi-Agent Systems via Communication Attacks (2025.findings-acl)

Copied to clipboard

Pengfei He, Yuping Lin, Shen Dong, Han Xu, Yue Xing, Hui Liu

Robustness in NLP

Challenge:	Large Language Model-based Multi-Agent Systems (LLM-MAS) have revolutionized complex problem-solving capability by enabling agent collaboration through message-based communications.
Approach:	They propose an attack that exploits communication mechanisms in Large Language Model-based Multi-Agent Systems (LLM-MAS) by intercepting and manipulating inter-agent messages.
Outcome:	The proposed attack exploits communication mechanisms in large language model-based multi-agent systems by intercepting and manipulating inter-agencies.

Towards Robust Numerical Question Answering: Diagnosing Numerical Capabilities of NLP Systems (2022.emnlp-main)

Copied to clipboard

Jialiang Xu, Mengyu Zhou, Xinyi He, Shi Han, Dongmei Zhang

Robustness in NLP

Challenge:	Numerical Question Answering is the task of answering questions that require numerical capabilities.
Approach:	They propose to conduct numerical capability diagnosis on a series of Numerical Question Answering systems and datasets.
Outcome:	The proposed approach relieves existing systems’ lack of robust numerical capabilities.

Rethinking Smoothness for Fast and Adaptable Entity Alignment Decoding (2025.findings-naacl)

Copied to clipboard

Yuanyi Wang, Han Li, Haifeng Sun, Lei Zhang, Bo He, Wei Tang, Tianhao Yan, Qi Qi, Jingyu Wang

TensorOpera Router: A Multi-Model Router for Efficient LLM Inference (2024.emnlp-industry)

Challenge:	Existing methods for integrating knowledge graphs rely on entity and relation embeddings . Fig. 1 shows how to decode knowledge graph in under 6 seconds .
Approach:	They propose a framework that only utilizes entity embeddings to decode knowledge graphs.
Outcome:	The proposed framework reconstructs KG representation by maximizing smoothness of entity embeddings.

Copied to clipboard

Dimitris Stripelis, Zhaozhuo Xu, Zijian Hu, Alay Shah, Han Jin, Yuhang Yao, Jipeng Zhang, Tong Zhang, Salman Avestimehr, Chaoyang He

Green & Sustainable NLP

Challenge:	Large Language Models (LLMs) have demonstrated remarkable performance across a diverse set of domain-specific tasks.
Approach:	They propose a non-monolithic LLM querying system that seamlessly integrates various LLM experts into a single query interface and dynamically routes incoming queries to the most high-performant expert based on query’s requirements.
Outcome:	The proposed model improves query efficiency by 40% and costs by 30% while maintaining or enhancing model performance by 10%.

HermEs: Interactive Spreadsheet Formula Prediction via Hierarchical Formulet Expansion (2023.acl-long)

Copied to clipboard

Wanrong He, Haoyu Dong, Yihuai Gao, Zhichao Fan, Xingzhuo Guo, Zhitao Hou, Xiao Lv, Ran Jia, Shi Han, Dongmei Zhang

Challenge:	HermEs is a spreadsheet formula prediction language that is difficult for Excel users without programming experience to master.
Approach:	They propose a hierarchical approach to formula prediction via HiEraRchical forMulet ExpanSion . they propose generating formulas in a fixed order using hierarchically generated formulas .
Outcome:	The proposed approach improves formula prediction accuracy by guaranteeing correct grammar and streamlining token-level decoding with high-level Formulet.

TransS-Driven Joint Learning Architecture for Implicit Discourse Relation Recognition (2020.acl-main)

Copied to clipboard

Ruifang He, Jian Wang, Fengyu Guo, Yugui Han

Challenge:	Existing approaches to implicit discourse relation recognition lack connectives as strong linguistic clues.
Approach:	They propose a transS-driven joint learning architecture to translate discourse relations in low-dimensional embedding space and exploit the semantic features of arguments to assist discourse understanding.
Outcome:	The proposed model outperforms existing systems on the Penn Discourse TreeBank.

BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem Solving (2025.acl-long)

Copied to clipboard

Teng Wang, Wing Yin Yu, Zhenqi He, Zehua Liu, HaileiGong HaileiGong, Han Wu, Xiongwei Han, Wei Shi, Ruifeng She, Fangzhou Zhu, Tao Zhong

Navigating the Infinite Dynamic Web Space: Effective In-Context Exploration via Cognitive Multi-Agent Collaboration (2026.eacl-long)

Challenge:	Existing datasets in operations research domain lack detailed annotations of the modeling process, focusing only on objective values.
Approach:	They propose an annotation-based tree-of-thought tree-based reasoning algorithm that integrates reinforcement learning into a tree- of-though.
Outcome:	The proposed algorithm outperforms state-of-the-art methods on StructuredOR, NL4OPT, and MAMO-ComplexLP datasets.

Copied to clipboard

Guozhao Mo, Yanjiang Liu, Yafei Shi, Jiawei Chen, Yang Li, Yaojie Lu, Hongyu Lin, Ben He, Le Sun, Bo Zheng, Xianpei Han

Linguistics & Cognitive NLP

Challenge:	Existing methods for dynamic web navigation rely on greedy strategies or value estimation, struggle to achieve effective backtracking and are heavily dependent on proprietary models.
Approach:	They propose a cognitive multi-agent collaboration framework that enhances cyberspace exploration capability through In-Context Exploration.
Outcome:	The proposed framework surpasses the proprietary model Claude-3.5 Sonnet on the WebArena benchmark.

CaMML: Context-Aware Multimodal Learner for Large Models (2024.acl-long)

Copied to clipboard

Yixin Chen, Shuai Zhang, Boran Han, Tong He, Bo Li

Memorizing is Not Enough: Deep Knowledge Injection Through Reasoning (2025.acl-long)

Challenge:	a lightweight module for tuning large multimodal models is introduced . CaMML integrates contextual samples into large models, enabling them to make inferences .
Approach:	They introduce a lightweight module for tuning large multimodal models . they have developed two models that have shown exceptional performance .
Outcome:	The proposed model outperforms LLaVA-1.5 on ten widely recognized datasets with a noticeable margin.

Copied to clipboard

Ruoxi Xu, Yunjie Ji, Boxi Cao, Yaojie Lu, Hongyu Lin, Xianpei Han, Ben He, Yingfei Sun, Xiangang Li, Le Sun

Can Multiple Responses from an LLM Reveal the Sources of Its Uncertainty? (2025.findings-emnlp)

Challenge:	Existing knowledge injection frameworks focus on knowledge memorization and retrieval, but static nature of large language models leads to outdated information as the real world evolves or when adapting to domain-specific knowledge.
Approach:	They propose a four-tier knowledge injection framework that defines the levels of knowledge injection: memorization, retrieval, reasoning, and association.
Outcome:	The proposed framework defines the levels of knowledge injection: memorization, retrieval, reasoning, and association.

Copied to clipboard

Yang Nan, Pengfei He, Ravi Tandon, Han Xu

Challenge:	Large language models can produce unreliable or misleading outputs, posing challenges for real-world applications.
Approach:	They employ an auxiliary LLM to analyze the patterns of disagreement among LLMs . they validate their framework on AmbigQA, OpenBookQA, and MMLU-Pro .
Outcome:	The proposed model can be used to diagnose uncertainty sources in a model with an auxiliary model.

ConsistentChat: Building Skeleton-Guided Consistent Multi-Turn Dialogues for Large Language Models from Scratch (2025.emnlp-main)

Copied to clipboard

Jiawei Chen, Xinyan Guan, Qianhao Yuan, Mo Guozhao, Weixiang Zhou, Yaojie Lu, Hongyu Lin, Ben He, Le Sun, Xianpei Han

Dialogue Systems & Conversational Agents

Challenge:	Existing instruction data synthesis methods focus on single-turn instructions and neglect cross-turn coherence, resulting in context drift and reduced task completion rates.
Approach:	They propose a framework that constrains multi-turn instruction synthesis by explicitly modeling human conversational intent.
Outcome:	The proposed framework outperforms existing models trained on single-turn and multi-turn instruction datasets.

AUGUST: an Automatic Generation Understudy for Synthesizing Conversational Recommendation Datasets (2023.findings-acl)

Copied to clipboard

Yu Lu, Junwei Bao, Zichen Ma, Xiaoguang Han, Youzheng Wu, Shuguang Cui, Xiaodong He

ConRPG: Paraphrase Generation using Contexts as Regularizer (2021.emnlp-main)

Challenge:	Existing work on conversational recommendation systems lacks high-quality data . existing datasets lack large-scale and high-level data based on human annotators .
Approach:	They propose an automatic dataset synthesis approach that generates large-scale recommendation dialogues using structured graphs based on user-item information from the real world.
Outcome:	The proposed approach can generate large-scale and high-quality recommendation dialogues . it exploits user preferences, knowledge graphs, and conversation ability from existing datasets based on real-world data .

Copied to clipboard

Yuxian Meng, Xiang Ao, Qing He, Xiaofei Sun, Qinghong Han, Fei Wu, Chun Fan, Jiwei Li

Text Generation

Challenge:	Existing methods for paraphrase generation lack reliable supervision signals.
Approach:	They propose an unsupervised paradigm for paraphrase generation based on contextual language models, candidate filtering and paraphrase model training based upon the selected candidates.
Outcome:	The proposed paradigm outperforms existing paraphrase generation methods in supervised and unsupervised setups.

Beyond Human Labels: A Multi-Linguistic Auto-Generated Benchmark for Evaluating Large Language Models on Resume Parsing (2025.emnlp-main)

Copied to clipboard

Zijian Ling, Han Zhang, Jiahao Cui, Zhequn Wu, Xu Sun, Guohao Li, Xiangjian He

DialMed: A Dataset for Dialogue-based Medication Recommendation (2022.coling-1)

Challenge:	Efficient resume parsing is critical for global hiring, yet the lack of dedicated benchmarks for evaluating large language models (LLMs) on multilingual, structure-rich resumes hinders progress.
Approach:	They propose to use a human-in-the-loop pipeline to generate 2,500 synthetic resumes spanning 50 templates, 30 career fields, and 5 languages to evaluate large language models.
Outcome:	The proposed benchmarks show that the models perform poorly on multilingual resumes and lack of standardized templates.

Copied to clipboard

Zhenfeng He, Yuqiang Han, Zhenqiu Ouyang, Wei Gao, Hongxu Chen, Guandong Xu, Jian Wu

ChatGPT Is a Knowledgeable but Inexperienced Solver: An Investigation of Commonsense Problem in Large Language Models (2024.lrec-main)

Challenge:	Existing studies on medication recommendation mainly rely on EHRs, but some details of interactions between doctors and patients may be ignored or omitted in EHR.
Approach:	They propose to use medical dialogues to recommend medications with medical dialogue data . they propose to model dialogue structure and disease knowledge aware network .
Outcome:	The proposed method is a promising solution to recommend medications with medical dialogues.

Copied to clipboard

Ning Bian, Xianpei Han, Le Sun, Hongyu Lin, Yaojie Lu, Ben He, Shanshan Jiang, Bin Dong

Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding (2026.acl-long)

Challenge:	acquiring and representing commonsense in machines has posed a long-standing challenge (Li et al., 2021; Zhang e t al, 2022; Zhou e al. 2023) .
Approach:	They use a commonsense-based LLM to evaluate ChatGPT's commonsensing abilities by analyzing 11 datasets and generating knowledge descriptions.
Outcome:	The proposed model can achieve good QA accuracies while still struggling with certain domains of datasets.

Copied to clipboard

Ke Ma, Jiaqi Tang, Bin Guo, Xueting Han, Ruonan Xu, Qingfeng He, Ziheng Wang, Xu Wang, Qifeng Chen, Zhiwen Yu, Yunhao Liu

Sentiment Knowledge Enhanced Self-supervised Learning for Multimodal Sentiment Analysis (2023.findings-acl)

Challenge:	Existing methods for streaming video understanding are query-agnostic and implicitly model video evidence.
Approach:	They propose a framework that establishes explicit, structured alignment between the accumulated video evidence and the query’s expected response conditions via scene graphs.
Outcome:	The proposed model achieves more interpretable and accurate response timing decisions on both proactive and reactive tasks.

Copied to clipboard

Fan Qian, Jiqing Han, Yongjun He, Tieran Zheng, Guibin Zheng

Sentiment Analysis

Challenge:	Existing studies have used general approaches to alleviate the overfitting of supervised models based on video data with sentiment annotations.
Approach:	They propose to capture common sentimental patterns in unlabeled videos using sentiment knowledge and non-verbal behavior to embed sentiment information into pre-trained multimodal representations.
Outcome:	The proposed model outperforms the baseline and achieves new State-Of-The-Art (SOTA) results.

Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models (2025.findings-acl)

Copied to clipboard

Yingqian Cui, Pengfei He, Jingying Zeng, Hui Liu, Xianfeng Tang, Zhenwei Dai, Yan Han, Chen Luo, Jing Huang, Zhen Li, Suhang Wang, Yue Xing, Jiliang Tang, Qi He

RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging (2025.emnlp-main)

Challenge:	Chain-of-Thought (CoT) reasoning has improved the performance of large language models (LLMs) however, the detailed reasoning process in CoT often incurs long generation times and high computational costs due to the inclusion of unnecessary steps.
Approach:	They propose a method to identify critical reasoning steps using perplexity as a measure of their importance.
Outcome:	The proposed method achieves a better balance between reasoning accuracy and efficiency of CoT.

Copied to clipboard

Bowen Wang, Haiyuan Wan, Liwen Shi, Chen Yang, Peng He, Yue Ma, Haochen Han, Wenhao Li, Tiao Tan, Yongjian Li, Fangming Liu, Gong Yifan, Sheng Zhang

Table-LLM-Specialist: Language Model Specialists for Tables using Iterative Fine-tuning (2025.emnlp-main)

Challenge:	Existing models that require task labels or performance trade-offs are susceptible to catastrophic forgetting.
Approach:	They propose a representation-aware model merging framework for continual learning without access to historical data.
Outcome:	The proposed framework outperforms baselines in knowledge retention and generalization across five NLP tasks and multiple continual learning scenarios.

Copied to clipboard

Junjie Xing, Yeye He, Mengyu Zhou, Haoyu Dong, Shi Han, Dongmei Zhang, Surajit Chaudhuri

AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time (2025.emnlp-main)

Challenge:	Language models such as GPT and Llama have shown remarkable ability on diverse natural language tasks, yet their performance on complex table tasks is suboptimal.
Approach:	They propose a generator-validator paradigm to iteratively generate-then-validate training data from language models to fine-tune stronger Table-Specialist models that can specialize in a given task, without using manually-labeled data.
Outcome:	The proposed model outperforms vanilla language models on diverse table tasks and can match or surpass GPT-4 level quality.

Copied to clipboard

Junyu Zhang, Runpei Dong, Han Wang, Xuying Ning, Haoran Geng, Peihao Li, Xialin He, Yutong Bai, Jitendra Malik, Saurabh Gupta, Huan Zhang

R3-SQL: Ranking Reward and Resampling for Text-to-SQL (2026.findings-acl)

Challenge:	Existing monotonic scaling methods for large reasoning models are not reliable.
Approach:	They propose a universal framework for modulating reasoning progress in large reasoning models at test time.
Outcome:	The proposed framework unifies and generalizes existing monotonic scaling methods and enables flexible and dense slow-to-fast reasoning modulation.

Copied to clipboard

Hojae Han, Yeonseok Jeong, Seung-won Hwang, Zhewei Yao, Yuxiong He

Why LLMs Hallucinate on Structured Knowledge: A Mechanistic Analysis of Reasoning over Linearized Representations (2026.acl-long)

Challenge:	Existing rankers assign inconsistent scores to functionally equivalent SQL queries . ranking cannot recover when the correct SQL is absent from the pool.
Approach:	They propose a Text-to-SQL framework that rewards ranking and resampling . it first groups candidates by execution result and ranks groups for consistency .
Outcome:	The proposed framework achieves 75.03 execution accuracy on BIRD-dev, a new state of the art among methods using models with disclosed sizes.

Copied to clipboard

Shanghao Li, Jinda Han, Yibo Wang, Yuanjie Zhu, Zihe Song, Langzhou He, Kenan Kamel A Alghythee, Philip S. Yu

On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigation (2025.findings-acl)

Challenge:	Existing literature primarily addresses this problem through external interventions such as retrieval augmentation and prompt engineering at the input or output level.
Approach:	They find that LLMs can still produce hallucinated outputs when using structured external knowledge.
Outcome:	The proposed models fail to ground the provided knowledge, causing the model to revert to parametric memory.

Copied to clipboard

Xueru Wen, Jie Lou, Xinyu Lu, Yuqiu Ji, Xinyan Guan, Yaojie Lu, Hongyu Lin, Ben He, Xianpei Han, Debing Zhang, Le Sun

Facilitating Long Context Understanding via Supervised Chain-of-Thought Reasoning (2025.emnlp-main)

Challenge:	Large language models exhibit behavior that deviates from the boundaries of their knowledge during response generation.
Approach:	They propose a framework that allows large language models to explore their knowledge boundaries and self-correct generation behavior through fine-grained feedback signals.
Outcome:	The proposed framework enables LLMs to explore their knowledge boundaries and self-correct generation behavior through fine-grained feedback signals.

Copied to clipboard

Jingyang Lin, Andy Wong, Tian Xia, Shenghua He, Hui Wei, Mei Han, Jiebo Luo

AnaMeta: A Table Understanding Dataset of Field Metadata Knowledge Shared by Multi-dimensional Data Analysis Tasks (2023.findings-acl)

Challenge:	Recent advances in Large Language Models (LLMs) have enabled them to process increasingly longer sequences, ranging from 2K to 2M tokens and even beyond.
Approach:	They propose a synthetic dataset in the financial domain that integrates Chain-of-Thought reasoning into LLMs in a supervised manner to facilitate effective long-context understanding.
Outcome:	The proposed model outperforms standard GPT-4o-mini on the Loong benchmark and fine tunes LLaMA-3.1-8B-Instruct on the model, achieving a 28.0% gain on the financial subset.

Copied to clipboard

Xinyi He, Mengyu Zhou, Mingjie Zhou, Jialiang Xu, Xiao Lv, Tianle Li, Yijia Shao, Shi Han, Zejian Yuan, Dongmei Zhang

Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring (2025.naacl-long)

Challenge:	Tabular data analysis is performed everyday across various domains.
Approach:	They propose to use a dataset of 467k tables with supervision labels for four types of field metadata.
Outcome:	The proposed framework improves the understanding capability of tabular models by incorporating distribution and knowledge information.

Copied to clipboard

Honglin Mu, Han He, Yuxin Zhou, Yunlong Feng, Yang Xu, Libo Qin, Xiaoming Shi, Zeming Liu, Xudong Han, Qi Shi, Qingfu Zhu, Wanxiang Che

EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents (2025.acl-long)

Challenge:	Existing black-box jailbreak methods often rely on model feedback . existing methods may be intercepted by content moderators during the search process .
Approach:	They propose a method that guides malicious prompt construction by local training a mirror model of the target black-box model through benign data distillation.
Outcome:	The proposed method achieves a 92% attack success rate and 80% stealth rate on a subset of AdvBench.

Copied to clipboard

Cheng Qian, Peixuan Han, Qinyu Luo, Bingxiang He, Xiusi Chen, Yuji Zhang, Hongyi Du, Jiarui Yao, Xiaocheng Yang, Denghui Zhang, Yunzhu Li, Heng Ji

PersLEARN: Research Training through the Lens of Perspective Cultivation (2023.acl-demo)

Challenge:	Existing language model agents excel in planning and reasoning, but lack creativity in unfamiliar environments.
Approach:	They propose a benchmark suite of room escape game environments to challenge agents with creative reasoning, unconventional tool use and iterative problem-solving to uncover implicit goals.
Outcome:	The proposed framework can perform with 40% fewer steps and hints and performs robustly across difficulty levels.

Copied to clipboard

Yu-Zhe Shi, Shiqian Li, Xinyi Niu, Qiao Xu, Jiawen Liu, Yifan Xu, Shiyu Gu, Bingru He, Xinyang Li, Xinyu Zhao, Zijian Zhao, Yidong Lyu, Zhen Li, Sijia Liu, Lin Qiu, Jinhao Ji, Lecheng Ruan, Yuxi Ma, Wenjuan Han, Yixin Zhu

Challenge:	PersLEARN is a tool designed to facilitate the cultivation of scientific perspectives . junior researchers struggle to identify the perspectives reflected in the literature and struggle to develop their own viewpoints.
Approach:	They propose a tool to facilitate the cultivation of scientific perspectives by interacting with a prompt-based model and allowing students to develop their own perspectives explicitly.
Outcome:	The proposed tool outperforms baseline approaches across multiple domains of literature from different perspectives.

Exploring Memorization in Fine-tuned Language Models (2024.acl-long)

Copied to clipboard

Shenglai Zeng, Yaxin Li, Jie Ren, Yiding Liu, Han Xu, Pengfei He, Yue Xing, Shuaiqiang Wang, Jiliang Tang, Dawei Yin

An MRC Framework for Semantic Role Labeling (2022.coling-1)

Challenge:	Existing studies have shown that pre-trained langauge models tend to memorize and regenerate segments of their pre-training corpus when prompted appropriately.
Approach:	They conduct the first comprehensive analysis to explore language models’ memorization during fine-tuning across tasks.
Outcome:	The proposed analysis shows that memorization presents a strong disparity among different fine-tuning tasks.

Copied to clipboard

Nan Wang, Jiwei Li, Yuxian Meng, Xiaofei Sun, Han Qiu, Ziyao Wang, Guoyin Wang, Jun He

Semantic Parsing

Challenge:	Existing work on semantic role labels ignores the semantic connection between the two tasks . et al. (2010) defined two types of semantic roles: core roles and non-core roles.
Approach:	They propose to use machine reading comprehension to bridge the gap between these two tasks . they formalize predicate disambiguation as multiple-choice machine reading understanding .
Outcome:	The proposed framework achieves state-of-the-art or comparable results to previous work . it uses the descriptions of candidate senses of a given predicate as options to select the correct sense .

The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG) (2024.findings-acl)

Copied to clipboard

Shenglai Zeng, Jiankun Zhang, Pengfei He, Yiding Liu, Yue Xing, Han Xu, Jie Ren, Yi Chang, Shuaiqiang Wang, Dawei Yin, Jiliang Tang

COPR: Continual Human Preference Learning via Optimal Policy Regularization (2025.findings-acl)

Challenge:	Retrieval-augmented generation (RAG) is a powerful technique to facilitate language model generation with proprietary and private data, where data privacy is . a privacy issue that is currently under-explored, is posed by RAG.
Approach:	They propose to use retrieval-augmented generation (RAG) to facilitate language model generation with proprietary and private data where data privacy is a pivotal concern.
Outcome:	The proposed attack methods demonstrate that RAG can mitigate the old risks, i.e., leakage of the LLMs’ training data.

Copied to clipboard

Han Zhang, Lin Gui, Yu Lei, Yuanzhao Zhai, Yehong Zhang, Zhuo Zhang, Yulan He, Hui Wang, Yue Yu, Kam-Fai Wong, Bin Liang, Ruifeng Xu

Data Poisoning for In-context Learning (2025.findings-naacl)

Challenge:	Reinforcement Learning from Human Feedback (RLHF) is effective for aligning Large Language Models with human preferences, but its complex process limits its ability to continually learn human feedback.
Approach:	They propose a non-RL offline method to convert historical optimal policies into optimization constraints when continually learning new preferences.
Outcome:	The proposed method outperforms strong CL baselines in terms of reward-based evaluations and human assessment.

Copied to clipboard

Pengfei He, Han Xu, Yue Xing, Hui Liu, Makoto Yamada, Jiliang Tang

Graph Hawkes Transformer for Extrapolated Reasoning on Temporal Knowledge Graphs (2022.emnlp-main)

Challenge:	In-context learning (ICL) has emerged as a capability of large language models (LLMs) but there is limited understanding of its vulnerability against data poisoning attacks.
Approach:	They propose an attack method that exploits ICL’s unique learning mechanisms by identifying discrete text perturbations that influence LLM hidden states.
Outcome:	The proposed attack method exploits ICL’s learning mechanisms by identifying discrete text perturbations that influence LLM hidden states.

Copied to clipboard

Haohai Sun, Shangyi Geng, Jialun Zhong, Han Hu, Kun He

Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios (2026.findings-acl)

Challenge:	Existing methods for entity prediction cannot predict when an event will occur . there are many facts not related to the query that can confuse the model .
Approach:	They propose a temporal knowledge Graph reasoning model based on Graph Hawkes Transformer . the model captures instantaneous structural and temporal evolution information .
Outcome:	The proposed model performs much better under long-term evolution scenarios.

Copied to clipboard

Changhao Pan, Rui Yang, Han Wang, Zhuan Zhou, Xuming He, Wenxiang Guo, Ziyue Jiang, Ruiqi Li, Yu Zhang, Chenyuhao Wen, Ke Lei, Xiang Yin, Jingyu Lu, Zhiyuan Zhu, Zhou Zhao

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

Challenge:	Existing evaluation benchmarks for long-form speech are limited to limited domains, creating a significant gap with the diverse downstream applications.
Approach:	They propose a benchmark that decomposes "long-form speech quality" into specific, disentangled dimensions.
Outcome:	The proposed benchmark decomposes “long-form speech quality” into specific, disentangled dimensions.

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

ChipSeek: Optimizing Verilog Generation via EDA-Integrated Reinforcement Learning (2026.acl-long)

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

Zhirong Chen, Kaiyan Chang, Zhuolin Li, Cangyuan Li, Xinyang He, Chujie Chen, Mengdi Wang, Haobo Xu, Yinhe Han, Huawei Li, Ying Wang

Green & Sustainable NLP

Challenge:	Existing approaches to optimize Register-Transfer Level (RTL) code fail to simultaneously optimize functional correctness and hardware efficiency metrics such as Power, Performance, and Area (PPA).
Approach:	They propose a hierarchical reward based reinforcement learning framework that integrates direct feedback from EDA simulators and synthesis tools into a reward mechanism.
Outcome:	The proposed framework integrates direct feedback from EDA simulators and synthesis tools into a hierarchical reward based reinforcement learning framework.

CHURRO: Making History Readable with an Open-Weight Large Vision-Language Model for High-Accuracy, Low-Cost Historical Text Recognition (2025.emnlp-main)

Copied to clipboard

Sina Semnani, Han Zhang, Xinyan He, Merve Tekgurler, Monica Lam

Visual Data in NLP

Challenge:	Existing vision-language models are not equipped to read diverse languages and scripts found in historical materials.
Approach:	They propose to train an open-weight vision-language model for historical text recognition on CHURRO-DS, the largest historical text-recognition dataset to date.
Outcome:	The proposed model outperforms existing vision-language models on CHURRO-DS, the largest historical text recognition dataset to date.

CAST: Achieving Stable LLM-based Text Analysis for Data Analytics (2026.findings-acl)

Copied to clipboard

Jinxiang Xie, Zihao Li, Wei He, Rui Ding, Shi Han, Dongmei Zhang

Low-Resource NLP

Challenge:	Text analysis of tabular data relies on two core operations: summarization for corpus-level theme extraction and tagging for row-level labeling.
Approach:	They propose a framework that enhances output stability by constraining the model’s latent reasoning trajectory.
Outcome:	The proposed framework improves stability by constraining the model's latent reasoning trajectory.

Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models (2026.findings-acl)

Copied to clipboard

Yuan Sui, Yufei He, Tri Cao, Sophia Simeng Han, Yulin Chen, Bryan Hooi

BERT-QE: Contextualized Query Expansion for Document Re-ranking (2020.findings-emnlp)

Challenge:	Recent advances on prompting and post-training have enabled LLMs to perform step-wise reasoning tasks, but they tend to explore unproductive solution paths without effective backtracking or strategy adjustment.
Approach:	They propose a framework that empowers LLMs to “think about how to think” and dynamically adapts reasoning strategies in real-time.
Outcome:	The proposed framework outperforms previous SOTA methods by 9-12% in accuracy while reducing inference time by 28-35% under the same compute budget.

Copied to clipboard

Zhi Zheng, Kai Hui, Ben He, Xianpei Han, Le Sun, Andrew Yates

CoCoNUTS: Concentrating on Content while Neglecting Uninformative Textual Styles for AI-Generated Peer Review Detection (2026.acl-long)

Challenge:	Existing methods to expand query use pseudo relevance feedback (PRF) but they are under-equipped to evaluate the relevance of information pieces used for expansion.
Approach:	They propose a query expansion model that leverages the BERT model to select relevant document chunks for expansion.
Outcome:	The proposed model significantly outperforms existing models on the TREC Robust04 and GOV2 test collections.

Copied to clipboard

Yihan Chen, Jiawei Chen, Guozhao Mo, Xuanang Chen, Ben He, Xianpei Han, Le Sun

Challenge:	Existing detectors rely on stylistic cues to distinguish between surface-level language refinement and genuine content generation.
Approach:	They propose a content-based detection paradigm to detect substantive AI-generation . they propose 'CoCoDet' detector that can detect surface-level language refinement .
Outcome:	The proposed detector achieves a macro F1 score of 98.24% on permissible machine-polished reviews and maintains 3.89% false positive rate on real-world reviews.

An Adaptive Prompt Generation Framework for Task-oriented Dialogue System (2023.findings-emnlp)

Copied to clipboard

Jun Gao, Liuyu Xiang, Huijia Wu, Han Zhao, Yiqi Tong, Zhaofeng He

Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Data (2026.acl-long)

Challenge:	Existing black-box large language models (LLMs) have excellent performance in task-oriented dialogue (TOD) tasks, but obtaining suitable prompts for specific tasks is challenging.
Approach:	They propose a black-box large language model that generates domain and slot information in the belief state, which serves as prior knowledge for subsequent prompt generation.
Outcome:	The proposed framework outperforms existing prompting methods on the MultiWOZ 2.0 dataset.

Copied to clipboard

Yuxuan Lu, Jing Huang, Yan Han, Bingsheng Yao, Sisong Bei, Yaochen Xie, Yisi Sang, Qi He, Dakuo Wang

Unleashing the True Potential of Sequence-to-Sequence Models for Sequence Tagging and Structure Parsing (2023.tacl-1)

Challenge:	Recent research shows that LLM Agents can generate “believable” human behaviors via prompt-only methods, leaving open questions of whether they can accurately generate step-by-step actions in multi-turn interaction tasks.
Approach:	They propose to use shopping data to evaluate LLMs' ability to accurately generate step-by-step actions in a multi-turn interaction task.
Outcome:	The proposed model achieves 17.26% action generation accuracy and 33.86% F1 score on final purchase prediction, representing improvements of 5.4% and 13.85% over baselines.

Copied to clipboard

Han He, Jinho D. Choi

Syntactic Text Processing

Challenge:	Sequence-to-Sequence (S2S) models have been successful on text generation tasks . however, learning complex structures with S2S models remains challenging .
Approach:	They propose to use constrained decoding to model part-of-speech tagging, named entity recognition, constituency, and dependency parsing tasks with 3 lexically diverse linearization schemas and corresponding constrained coding methods.
Outcome:	The proposed methods outperform the state-of-the-art on four core tasks.

PhiloGPT: A Philology-Oriented Large Language Model for Ancient Chinese Manuscripts with Dunhuang as Case Study (2024.emnlp-main)

Copied to clipboard

Yuqing Zhang, Baoyi He, Yihan Chen, Hangqi Li, Han Yue, Shengyu Zhang, Huaiyong Dou, Junchi Yan, Zemin Liu, Yongquan Zhang, Fei Wu

DUET: Joint Exploration of User–Item Profiles in Recommendation System (2026.findings-acl)

Challenge:	philology requires years of professional training in extensive knowledge memorization and manual textual retrieval.
Approach:	They curated the PhiloCorpus-ZH, a rich collec-tion of ancient Chinese texts spanning a millennium with 30 diverse topics, including firsthand folk copies.
Outcome:	The PhiloCorpus-ZH corpus facilitated the development of the first LLM tailored for discovering ancient Chinese manuscripts.

Copied to clipboard

Yue Chen, Yifei Sun, Lu Wang, Fangkai Yang, Pu Zhao, Minjie Hong, Yifei Dong, Minghua He, Nan Hu, Jianjin Zhang, Zhiwei Dai, Yuefeng Zhan, Weihao Han, Hao Sun, Qingwei Lin, Weiwei Deng, Feng Sun, Qi Zhang, Saravan Rajmohan, Dongmei Zhang

Challenge:	Existing LLMs are opaque and difficult to interpret, resulting in limited interpretability.
Approach:	They propose an interaction-aware profile generator that jointly produces user and item profiles conditioned on both user history and item evidence.
Outcome:	The proposed model outperforms baselines on three real-world datasets.

Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework (2026.findings-acl)

Copied to clipboard

Jiaqi Weng, Han Zheng, Hanyu Zhang, Ej Zhou, Qinqin He, Jialing Tao, Hui Xue, Zhixuan Chu, Xiting Wang

Explainability & Interpretability in NLP

Challenge:	Existing studies on how SAEs derive most fine-grained latent features for safety remain unexplored.
Approach:	They propose a framework for interpreting SAE features in safety-critical domains . they train a suite of SAEs with human-readable explanations and systematic evaluations based on pornography, politics, violence, and terror .
Outcome:	The proposed framework reduces interpretation cost by 55% and improves safety-critical features.

XMC-Agent : Dynamic Navigation over Scalable Hierarchical Index for Incremental Extreme Multi-label Classification (2024.findings-acl)

Copied to clipboard

Yanjiang Liu, Tianyun Zhong, Yaojie Lu, Hongyu Lin, Ben He, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Zhongyi Liu, Xianpei Han, Le Sun

Information Retrieval

Challenge:	Existing methods for XMC struggle with the growing set of labels due to their static label assumptions, and embedding-based methods struggle with complex mapping relationships due to late interaction paradigm.
Approach:	They propose a large language model (LLM) powered agent framework for extreme multi-label classification, XMC-Agent, which can effectively learn, manage and predict the extremely large and dynamically increasing set of labels.
Outcome:	The proposed framework can learn, manage and predict the extremely large and dynamically growing set of labels and achieves state-of-the-art performance on three standard datasets.

GLIMPSE: Do Large Vision-Language Models Truly Think With Videos or Just Glimpse at Them? (2025.emnlp-main)

Copied to clipboard

Yiyang Zhou, Linjie Li, Shi Qiu, Zhengyuan Yang, Yuyang Zhao, Siwei Han, Yangfan He, Kangqi Li, Haonian Ji, Zihao Zhao, Haibo Tong, Lijuan Wang, Huaxiu Yao

Visual Question Decomposition on Multimodal Large Language Models (2024.findings-emnlp)

Challenge:	Existing video benchmarks often resemble image-based questions with scans of only a few key frames, without deep temporal reasoning.
Approach:	They propose a video benchmark to assess whether large vision-language models can genuinely think with videos rather than perform superficial frame-level analysis.
Outcome:	The proposed benchmark consists of 3,269 videos and over 4,342 highly visual-centric questions across 11 categories, including Trajectory Analysis, Temporal Reasoning, and Forensics Detection.

Copied to clipboard

Haowei Zhang, Jianzhe Liu, Zhen Han, Shuo Chen, Bailan He, Volker Tresp, Zhiqiang Xu, Jindong Gu

OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems (2024.acl-long)

Challenge:	Existing methods for question decomposition focus on unimodal language models, but question decomposing capability of Multimodal Large Language Models (MLLMs) has yet to be explored.
Approach:	They propose a finetuning dataset and a training objective for selective decomposition to enhance the model's question decomposing capability.
Outcome:	The proposed dataset shows that existing models struggle to produce high-quality sub-questions.

Copied to clipboard

Chaoqun He, Renjie Luo, Yuzhuo Bai, Shengding Hu, Zhen Thai, Junhao Shen, Jinyi Hu, Xu Han, Yujie Huang, Yuxiang Zhang, Jie Liu, Lei Qi, Zhiyuan Liu, Maosong Sun

MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)

Challenge:	Large Language Models (LLMs) and Large Multimodal Models have exceeded general human capabilities in various tasks.
Approach:	They present an Olympiad-level bilingual multimodal scientific benchmark featuring 8,476 problems from Olympiad level mathematics and physics competitions.
Outcome:	The best performing model, GPT-4V, attains an average score of 17.97% on OlympiadBench, with a mere 10.74% in physics, highlighting the benchmark rigor and the intricacy of physical reasoning.

Copied to clipboard

Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie

Self-Steering Optimization: Autonomous Preference Optimization for Large Language Models (2025.findings-acl)

Challenge:	Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models.
Approach:	They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts.
Outcome:	The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings .

Copied to clipboard

Hao Xiang, Bowen Yu, Hongyu Lin, Keming Lu, Yaojie Lu, Xianpei Han, Ben He, Le Sun, Jingren Zhou, Junyang Lin

CoCoST: Automatic Complex Code Generation with Online Searching and Correctness Testing (2024.emnlp-main)

Challenge:	Prior research focused on developing data generation methods, while insufficient attention has been paid to quality control mechanisms and often produces inaccurate and unhelpful data.
Approach:	They propose an algorithm that automatically generates high-quality preference data, eliminating manual annotation requirements.
Outcome:	The proposed algorithm outperforms baselines in human preference alignment and reward optimization.

Copied to clipboard

Xinyi He, Jiaru Zou, Yun Lin, Mengyu Zhou, Shi Han, Zejian Yuan, Dongmei Zhang

Scaling Laws for Multilingual Language Models (2025.findings-acl)

Challenge:	Existing methods to improve code generation from natural language descriptions are difficult due to complex structure, subtle bugs, and lack of supplementary contents.
Approach:	They propose a framework that enhances complex code generation by online searching for more information with planned queries and correctness testing for code refinement.
Outcome:	The proposed framework improves the quality of complex code generation on the DS-1000 and ClassEval datasets.

Copied to clipboard

Yifei He, Alon Benhaim, Barun Patra, Praneetha Vaddamanu, Sanchit Ahuja, Parul Chopra, Vishrav Chaudhary, Han Zhao, Xia Song

Rule or Story, Which is a Better Commonsense Expression for Talking with Large Language Models? (2024.acl-long)

Challenge:	Existing scaling laws for language models are limited to a limited number of languages, but they can be applied to arbitrary number of different languages.
Approach:	They propose a scaling law for general-purpose decoder-only language models trained on multilingual data that shifts focus from individual languages to language families.
Outcome:	The proposed scaling law can be applied to models trained on multilingual data . it can be used to predict performance across multiple languages and models .

Copied to clipboard

Ning Bian, Xianpei Han, Hongyu Lin, Yaojie Lu, Ben He, Le Sun

On the Generalization of Training-based ChatGPT Detection Methods (2024.findings-emnlp)

Challenge:	Experimental results show that stories outperform rules as the expression for retrieving commonsense from LLMs, exhibiting higher generation confidence and commonsensense accuracy.
Approach:	They investigate the commonsense ability of large language models expressed through stories and rules to retrieve commonsensing knowledge from LLMs.
Outcome:	The stories outperform rules as commonsense expressions on 28 commonsensense QA datasets, exhibiting higher generation confidence and commonsence accuracy.

Copied to clipboard

Han Xu, Jie Ren, Pengfei He, Shenglai Zeng, Yingqian Cui, Amy Liu, Hui Liu, Jiliang Tang

TableLoRA: Low-rank Adaptation on Table Structure Understanding for Large Language Models (2025.acl-long)

Challenge:	Existing studies show that training-based methods are ineffective to detect LLM generated texts from unseen tasks or topics which are not collected during training.
Approach:	They propose to train classification models to distinguish LLMs from human texts by a distribution shift caused by prompts, text lengths, topics, and language tasks.
Outcome:	The proposed methods can detect LLMs from black-box models, but they suffer from distribution shifts due to a wide range of factors, including prompts, text lengths, topics, and language tasks.

Copied to clipboard

Xinyi He, Yihao Liu, Mengyu Zhou, Yeye He, Haoyu Dong, Shi Han, Zejian Yuan, Dongmei Zhang

User Feedback Alignment for LLM-powered Exploration in Large-scale Recommendation Systems (2025.acl-industry)

Challenge:	Tabular data are crucial in many fields and their understanding by large language models (LLMs) under high parameter efficiency paradigm is important.
Approach:	They propose a module that uses 2D LoRA to encode low-rank information on cell positions to improve table serialization and representation of two-dimensional structured information within a one-dimensional sequence.
Outcome:	Experiments on four tabular-related datasets show that TableLoRA outperforms vanilla LoRA and surpasses table encoding methods tested in control.

Copied to clipboard

Jianling Wang, Yifan Liu, Yinghao Sun, Xuejian Ma, Yueqi Wang, He Ma, Zhengyang Su, Minmin Chen, Mingyan Gao, Onkar Dalal, Ed H. Chi, Lichan Hong, Ningren Han, Haokai Lu

InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) can be used to broaden user experiences beyond established preferences and reinforce feedback loops.
Approach:	They propose a hierarchical approach that combines hierarchic planning with LLM inference-time scaling to improve recommendation relevancy without compromising novelty.
Outcome:	The proposed approach shows significant gains in both user satisfaction and exploration diversity.

Copied to clipboard

Xiaotian Han, Yiren Jian, Xuefeng Hu, Haogeng Liu, Yiqi Wang, Qihang Fan, Yuang Ai, Huaibo Huang, Ran He, Zhenheng Yang, Quanzeng You

Construction of Paired Knowledge Graph - Text Datasets Informed by Cyclic Evaluation (2024.lrec-main)

Challenge:	InfiMM-WebMath-40B is a dataset of interleaved image-text documents . it consists of 24 million web pages, 85 million image URLs, and 40 billion text tokens .
Approach:	InfiMM-WebMath-40B is a high-quality dataset of interleaved image-text documents . it contains 24 million web pages, 85 million image URLs, and 40 billion text tokens .
Outcome:	InfiMM-WebMath-40B is a high-quality dataset of interleaved image-text documents . it consists of 24 million web pages, 85 million image URLs, and 40 billion text tokens .

Copied to clipboard

Ali Mousavi, Xin Zhan, He Bai, Peng Shi, Theodoros Rekatsinas, Benjamin Han, Yunyao Li, Jeffrey Pound, Joshua M. Susskind, Natalie Schluter, Ihab F. Ilyas, Navdeep Jaitly

Structured Data in NLP

Challenge:	Prior studies have shown that sequence-to-sequence models learn to hallucinate when the conditioning data has poor correlation with the sequence being produced.
Approach:	They construct a dataset that pairs Knowledge Graphs (KG) and text together and compare their results to a cyclic evaluation model.
Outcome:	The proposed model performs better on cyclic generation of KGs than on KG-T, but less well on synchronization of KTs.

Can LLM Graph Reasoning Generalize beyond Pattern Memorization? (2024.findings-emnlp)

Copied to clipboard

Yizhuo Zhang, Heng Wang, Shangbin Feng, Zhaoxuan Tan, Xiaochuang Han, Tianxing He, Yulia Tsvetkov

Structured Data in NLP

Challenge:	Existing studies seek to enhance the graph reasoning capabilities of Large Language Models (LLMs) by specialized instruction tuning.
Approach:	They propose to evaluate LLM graph reasoning generalization using in-distribution settings . they propose to use three strategies to improve LLM generalization .
Outcome:	The proposed benchmark evaluates LLM graph reasoning generalization with in-distribution settings only . it shows that LLMs struggle to generalize across reasoning and real-world patterns .

Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (2024.emnlp-main)

Copied to clipboard

Yuping Lin, Pengfei He, Han Xu, Yue Xing, Makoto Yamada, Hui Liu, Jiliang Tang

Expanding the Boundaries of Vision Prior Knowledge in Multi-modal Large Language Models (2026.eacl-long)

Challenge:	Large language models (LLMs) are susceptible to a type of attack known as jailbreaking, which misleads LLMs to output harmful contents.
Approach:	They propose to leverage hidden representations into existing jailbreak targets to move the attacks along the acceptance direction.
Outcome:	The proposed methods are validated using the objective of existing jailbreak attacks.

Copied to clipboard

Qiao Liang, Yanjiang Liu, Weixiang Zhou, Ben He, Yaojie Lu, Hongyu Lin, Jia Zheng, Xianpei Han, Le Sun, Yingfei Sun

Efficient Paths and Dense Rewards: Probabilistic Flow Reasoning for Large Language Models (2026.acl-long)

Challenge:	Existing research treats MLLMs as unified systems optimized through end-to-end training, but the impact of vision encoder’s prior knowledge is seldom investigated.
Approach:	They propose a metric to quantify the effect of prior knowledge on MLLM performance by integrating prior knowledge at the vision encoder level into a training framework.
Outcome:	The proposed training framework incorporates prior knowledge at the vision encoder level, and significantly boosts visual understanding capabilities of MLLMs.

Copied to clipboard

Yan Liu, Feng Zhang, Zhanyu Ma, Jun Xu, Jiuchong Gao, Jinghua Hao, Renqing He, Han Liu, Yangdong Deng

RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking (2026.findings-acl)

Challenge:	Existing approaches to mitigate inference inefficiency and optimization difficulty are fragmented and constrained by inherent trade-offs.
Approach:	They propose a framework that reconceptualizes discrete reasoning steps as a continuous probabilistic flow, quantifying the contribution of each step toward the ground-truth answer.
Outcome:	The proposed framework achieves a superior balance between inference efficiency and reasoning performance on challenging benchmarks.

Copied to clipboard

Jiaru Zou, Dongqi Fu, Sirui Chen, Xinrui He, Zihao Li, Yada Zhu, Jiawei Han, Jingrui He

Structured Data in NLP

Challenge:	Retrieval-Augmented Generation (RAG) integrates knowledge from tables with an external knowledge base to improve the answer relevance and accuracy.
Approach:	They propose a table-corpora-aware RAG framework called T-RAG to integrate external knowledge into Large Language Models (LLMs) they then develop a multi-table question answering benchmark called MultiTableQA which spans 3 different task types, 57,193 tables, and 23,758 questions in total.
Outcome:	The proposed framework achieves state-of-the-art accuracy, recall, and runtime performance, with improvements of up to 9.4%.

UltraEval: A Lightweight Platform for Flexible and Comprehensive Evaluation for LLMs (2024.acl-demos)

Copied to clipboard

Chaoqun He, Renjie Luo, Shengding Hu, Ranchi Zhao, Jie Zhou, Hanghao Wu, Jiajie Zhang, Xu Han, Zhiyuan Liu, Maosong Sun

Generation-Augmented Retrieval for Open-Domain Question Answering (2021.acl-long)

Challenge:	Existing evaluation platforms are complex and poorly modularized, hindering seamless incorporation into researcher’s workflows.
Approach:	They propose a lightweight evaluation framework characterized by lightweight, comprehensiveness, modularity, and efficiency that integrates models, data, and metrics into a unified evaluation workflow.
Outcome:	The proposed evaluation framework is lightweight, comprehensive, modular, and efficient.

Copied to clipboard

Yuning Mao, Pengcheng He, Xiaodong Liu, Yelong Shen, Jianfeng Gao, Jiawei Han, Weizhu Chen

SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training (2024.acl-long)

Challenge:	Existing approaches to answer open-domain questions use sparse representations and sparsity.
Approach:	They propose a method which augments a query by generating relevant contexts from heuristically discovered contexts without external supervision.
Outcome:	The proposed approach outperforms state-of-the-art dense retrieval methods on natural questions and triviaQA datasets.

Copied to clipboard

Nan He, Weichen Xiong, Hanwen Liu, Yi Liao, Lei Ding, Kai Zhang, Guohua Tang, Xiao Han, Yang Wei

The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders (2021.emnlp-main)

Challenge:	Current methods focus on detecting and removing duplicates, which risks the loss of valuable information and neglects the varying degrees of duplication.
Approach:	They propose a method that maintains dataset integrity while selectively reducing the sampling weight of data with high commonness.
Outcome:	The proposed method significantly improves training efficiency on deduplicated datasets and improves downstream accuracy by 1.77%.

Copied to clipboard

Han He, Jinho D. Choi

Learning to Bootstrap for Entity Set Expansion (D19-1)

Challenge:	Multi-task learning with transformer encoders (MTL) has emerged as a powerful technique to improve performance on closely-related tasks for both accuracy and efficiency.
Approach:	They propose a multi-task learning technique that uses transformer encoders to improve performance on closely-related tasks.
Outcome:	The proposed method performs better on five NLP tasks than single-task learning on similar tasks.

Copied to clipboard

Lingyong Yan, Xianpei Han, Le Sun, Ben He

Information Extraction & Text Mining

Challenge:	Existing bootstrapping methods for Entity Set Expansion suffer from two problems: 1) delayed feedback and sparse supervision.
Approach:	They propose a method that estimates delayed feedback and adaptively scores entities given sparse supervision signals.
Outcome:	The proposed method can estimate delayed feedback for pattern evaluation and adaptively score entities given sparse supervision signals.

Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data (2025.emnlp-main)

Copied to clipboard

Shenglai Zeng, Jiankun Zhang, Pengfei He, Jie Ren, Tianqi Zheng, Hanqing Lu, Han Xu, Hui Liu, Yue Xing, Jiliang Tang

On the Zero-Shot Generalization of Machine-Generated Text Detectors (2023.findings-emnlp)

Challenge:	Existing literature suggests that RAG systems may face privacy issues when the retrieval process involves private data.
Approach:	They propose a two-stage synthetic data generation paradigm that uses attributes to preserve contextual information from the original data.
Outcome:	The proposed approach preserves key contextual information from the original data while reducing privacy risks.

Copied to clipboard

Xiao Pu, Jingyu Zhang, Xiaochuang Han, Yulia Tsvetkov, Tianxing He

DenseSSM: State Space Models with Dense Hidden Connection for Efficient Large Language Models (2025.naacl-long)

Challenge:	rampant proliferation of large language models generates text indistinguishable from human-written language.
Approach:	They train neural detectors on outputs of a new generator and test their performance on held-out generators.
Outcome:	The proposed detectors can be built on training data from medium-sized models.

Copied to clipboard

Wei He, Kai Han, Yehui Tang, Chengcheng Wang, Yujie Yang, Tianyu Guo, Yunhe Wang

TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning (2024.findings-emnlp)

Challenge:	Large language models (LLMs) face excessive computational and memory requirements due to the commonly used Transformer architecture.
Approach:	They propose a method to enhance the flow of hidden information between layers in large language models by selectively integrating shallow-layer hidden states into deeper layers.
Outcome:	The proposed method maintains parallelizability and inference efficiency of SSMs while significantly boosting performance on public benchmarks.

Copied to clipboard

Yuan Sui, Jiaru Zou, Mengyu Zhou, Xinyi He, Lun Du, Shi Han, Dongmei Zhang

Seg2Act: Global Context-aware Action Generation for Document Logical Structuring (2024.emnlp-main)

Challenge:	Existing solutions for table reasoning tasks are mainly tested on small tables and face scalability issues and struggle with complex queries due to incomplete or dispersed data across different table sections.
Approach:	They propose a table reasoning pre-processor suite that can be used to leverage large language models (LLMs) in table-based tasks.
Outcome:	The proposed method improves LLMs’ reasoning capabilities in various tabular tasks and enhances interaction between LLM and tabular data by employing effective pre-processing.

Copied to clipboard

Zichao Li, Shaojie He, Meng Liao, Xuanang Chen, Yaojie Lu, Hongyu Lin, Yanxiong Lu, Xianpei Han, Le Sun

Challenge:	Document logical structuring is crucial for document intelligence due to the complexity of text segment dependencies in the document.
Approach:	They propose an end-to-end, generation-based method for document logical structuring that generates the action sequence via a global context-aware generative model and updates its global context and current logical structure based on the generated actions.
Outcome:	Experiments on ChCatExt and HierDoc datasets show that Seg2Act performs better than previous methods in both supervised and transfer learning settings.

Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors (2026.acl-long)

Copied to clipboard

Rui Yin, Tianxu Han, Naen Xu, Changjiang Li, Ping He, Chunyi Zhou, Jun Wang, Zhihui Fu, Tianyu Du, Jinbao Li, Shouling Ji

ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models (2025.acl-long)

Challenge:	Existing methods to inject safety-aligned large language models rely on token-level mappings, which do not guarantee sustained harmful output.
Approach:	They propose a method that directly modifies model weights to map a trigger to an attacker-specified response.
Outcome:	The proposed method achieves high triggered attack success while maintaining non-triggered safety and general utility.

Copied to clipboard

Xuxu Liu, Siyuan Liang, Mengya Han, Yong Luo, Aishan Liu, Xiantao Cai, Zheng He, Dacheng Tao

Can Graph Neural Networks Learn Language with Extremely Weak Text Supervision? (2025.acl-long)

Challenge:	Existing backdoor models are limited in coverage of attack, system integrity and backdoor alignment . ELBA-Bench provides over 1300 experiments encompassing 12 attack methods, 18 datasets, and 12 LLMs.
Approach:	They propose a framework that allows attackers to inject backdoor through parameter efficient fine-tuning or without fine-uning techniques.
Outcome:	ELBA-Bench provides over 1300 experiments encompassing 12 attack methods, 18 datasets, and 12 LLMs.

Copied to clipboard

Zihao Li, Lecheng Zheng, Bowen Jin, Dongqi Fu, Baoyu Jing, Yikun Ban, Jingrui He, Jiawei Han

Faithful, Unfaithful or Ambiguous? Multi-Agent Debate with Initial Stance for Summary Evaluation (2025.naacl-long)

Challenge:	Graph Neural Networks (GNNs) with CLIP pipeline are difficult because of the scarcity of labeled data and text supervision, different levels of downstream tasks, and conceptual gaps between domains.
Approach:	They propose a multi-modal prompt learning paradigm to adapt pre-trained GNNs to downstream tasks with weak text supervision.
Outcome:	The proposed model can generalize graphs to unseen classes with weak text supervision.

Copied to clipboard

Mahnaz Koupaee, Jake W. Vincent, Saab Mansour, Igor Shalyminov, Han He, Hwanjun Song, Raphael Shu, Jianfeng He, Yi Nian, Amy Wing-mei Wong, Kyu J. Han, Hang Su

Challenge:	Existing approaches to evaluate faithfulness of summaries are often fooled by the fluency of the text and struggle with identifying errors.
Approach:	They propose an approach to summary faithfulness evaluation where multiple LLM-based agents are assigned initial stances and forced to come up with a reason to justify belief.
Outcome:	The proposed approach can identify ambiguities and have even stronger performance on non-ambiguous summaries.

AutoVecCoder: Teaching LLMs to Generate Explicitly Vectorized Code (2026.findings-acl)

Copied to clipboard

ShangZhan Li, Xinyu Yin, Xuanyu Jin, Ye He, Yuxin Zhou, Yuxuan Li, Xu Han, Wanxiang Che, Qi Shi, Ting Liu, Maosong Sun

Optimizing NLU Reranking Using Entity Resolution Signals in Multi-domain Dialog Systems (2021.naacl-industry)

Challenge:	Current development practices face a dichotomy between automation and performance.
Approach:	They propose a framework to empower LLMs with the capability of automated explicit vectorization.
Outcome:	The proposed framework achieves state-of-the-art performance on the SSE and AVX subsets of SimdBench.

Copied to clipboard

Tong Wang, Jiangning Chen, Mohsen Malmir, Shuyan Dong, Xin He, Han Wang, Chengwei Su, Yue Liu, Yang Liu

Dialogue Systems & Conversational Agents

Challenge:	In dialog systems, the Natural Language Understanding component makes the interpretation decision before the mentioned entities are resolved.
Approach:	They propose to leverage Entity Resolution (ER) features in NLU reranking to learn model weights . they propose a score distribution matching method to ensure the models are calibrated .
Outcome:	The proposed approach outperforms the baseline model on multiple domain evaluations.

Steering LVLMs via Sparse Autoencoder for Hallucination Mitigation (2025.findings-emnlp)

Copied to clipboard

Zhenglin Hua, Jinghan He, Zijun Yao, Tianxu Han, Haiyun Guo, Yuheng Jia, Junfeng Fang

New Terms, New Toxicity: Consensus-based Chinese Neologism Toxicity Detection via Search-Augmented LLMs (2026.acl-long)

Challenge:	Existing approaches to address hallucinations in large vision-language models require substantial computational cost and time.
Approach:	They propose to leverage sparse autoencoders to identify semantic directions closely associated with faithfulness or hallucination, extracting more precise and disentangled hallucinian-related representations.
Outcome:	The proposed method outperforms existing decoding approaches while maintaining transferability across different model architectures with negligible additional time overhead.

Copied to clipboard

Shiyao Cui, QingLin Zhang, Di Wang, Yida Lu, Zhexin Zhang, Jinhua Gao, Jinglin Yang, Min He, Han Qiu, Minlie Huang

Information Retrieval

Challenge:	Neologisms can foster new linguistic consensus by stabilizing shared meanings and usage in common communicative norms.
Approach:	They propose a taxonomy that captures the origins and consensus-verification criteria of toxic neologisms . they propose 'SeTox' framework that integrates real-time web context for naeologim detection .
Outcome:	The proposed framework outperforms large-scale models in detecting neologism toxicity.

Enhancing Generalization in Natural Language Inference by Syntax (2020.findings-emnlp)

Copied to clipboard

Qi He, Han Wang, Yue Zhang

Sens-Merging: Sensitivity-Guided Parameter Balancing for Merging Large Language Models (2025.findings-acl)

Challenge:	Pre-trained language models such as BERT have the state-of-the-art performance on natural language inference (NLI).
Approach:	They propose to use dependency trees to enhance generalization of BERT in a natural language inference task by leveraging on a graph convolutional network to represent a syntax-based matching graph with heterogeneous matching patterns.
Outcome:	The proposed method makes BERT more robust on syntactic changes.

Copied to clipboard

Shuqi Liu, Han Wu, Bowei He, Xiongwei Han, Mingxuan Yuan, Linqi Song

Cheems: A Practical Guidance for Building and Evaluating Chinese Reward Models from Scratch (2025.acl-long)

Challenge:	Existing task vector-based model merging methods apply uniform coefficients across all parameters, overlooking varying parameter importance both within and across tasks.
Approach:	They propose a sensitivity-guided coefficient adjustment method that optimizes existing model merging techniques by operating at both task-specific and cross-task levels.
Outcome:	The proposed method outperforms existing model merging techniques on mistral 7B and LLaMA2 7B/13B models and enables them to outperformed specialized models.

Copied to clipboard

Xueru Wen, Jie Lou, Zichao Li, Yaojie Lu, XingYu XingYu, Yuqiu Ji, Guohai Xu, Hongyu Lin, Ben He, Xianpei Han, Le Sun, Debing Zhang

Challenge:	Existing Chinese resources are small in scale and limited to specific domains, making them insufficient for LLM post-training.
Approach:	They propose a Chinese-annotated reward model and a preference dataset to address this gap . they evaluate Chinese RMs on CheemsBench and construct an RM that captures human preferences .
Outcome:	The proposed RM achieves state-of-the-art performance on CheemsBench and CheeMePreference.

Learning Joint Structural and Temporal Contextualized Knowledge Embeddings for Temporal Knowledge Graph Completion (2023.findings-acl)

Copied to clipboard

Yifu Gao, Yongquan He, Zhigang Kan, Yi Han, Linbo Qiao, Dongsheng Li

Contrastive Distant Supervision for Debiased and Denoised Machine Reading Comprehension (2023.findings-emnlp)

Challenge:	Existing methods that incorporate time information into static knowledge graph embedding ignore the contextual nature of the TKG structure.
Approach:	They propose a method that employs pre-trained language models to learn joint Structural and Temporal Contextualized Knowledge Embeddings.
Outcome:	The proposed method is superior to existing methods that ignore the contextual nature of the TKG structure.

Copied to clipboard

Ning Bian, Hongyu Lin, Xianpei Han, Ben He, Le Sun

TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting (2021.emnlp-main)

Challenge:	Distant supervision (DS) is a promising learning approach for machine reading comprehension (MRC) however, the annotated dataset will inevitably lead to mislabeled instances, resulting in answer bias and context noise problems.
Approach:	They propose an algorithm that can learn to distinguish confusing and noisy instances via confidence-aware contrastive learning.
Outcome:	The proposed algorithm can learn to distinguish confusing and noisy instances via confidence-aware contrastive learning.

Copied to clipboard

Haohai Sun, Jialun Zhong, Yunpu Ma, Zhen Han, Kun He

MRT: Multi-modal Short- and Long-range Temporal Convolutional Network for Time-sync Comment Video Behavior Prediction (2024.lrec-main)

Challenge:	Existing methods focus on reasoning at past timestamps to complete the missing facts, and there are only a few works of reasoning on known TKGs to forecast future facts.
Approach:	They propose a time-shaped reward method that captures historical knowledge graph snapshots and a new representation method for unseen entities to improve the inductive inference ability of the model.
Outcome:	The proposed method improves on four benchmark datasets with higher explainability, less calculation, and fewer parameters when compared with existing state-of-the-art methods.

Copied to clipboard

Weihao Zhao, Weidong He, Hao Wang, Haoyang Bi, Han Wu, Chen Zhu, Tong Xu, Enhong Chen

Global Bootstrapping Neural Network for Entity Set Expansion (2020.findings-emnlp)

Challenge:	Using time-sync comments, it is difficult to understand user behavior due to complexity of interactions between users, videos, and comments.
Approach:	They propose a novel time-sync comment behavior prediction model that takes historical behavior into account and optimizes it on the basis of user preferences.
Outcome:	The proposed model improves the performance of time-sync comments on visual frames and textual comments on two cats playing simultaneously.

Copied to clipboard

Lingyong Yan, Xianpei Han, Ben He, Le Sun

Refining and Synthesis: A Simple yet Effective Data Augmentation Framework for Cross-Domain Aspect-based Sentiment Analysis (2024.findings-acl)

Challenge:	Recent studies have shown that end-to-end bootstrapping methods only leverage local semantics rather than global semantics.
Approach:	They propose a global-sighted encoder to capture and encode local and global semantics into entity embedding and an attention-guided decoder to sequentially expand new entities based on these embeddables.
Outcome:	The proposed network achieves state-of-the-art on two bootstrapping datasets.

Copied to clipboard

Haining Wang, Kang He, Bobo Li, Lei Chen, Fei Li, Xu Han, Chong Teng, Donghong Ji

Sentiment Analysis

Challenge:	Aspect-based Sentiment Analysis (ABSA) data augmentation has attracted increasing attention in recent years due to data sparsity.
Approach:	They propose a framework to augment ABSA data using pseudo labels for target domain . they refine generated labeled data using a natural language inference filter .
Outcome:	The proposed framework outperforms 7 strong baselines on 4 kinds of ABSA tasks.

Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks (2025.findings-naacl)

Copied to clipboard

Samuele Poppi, Zheng Xin Yong, Yifei He, Bobbie Chern, Han Zhao, Aobo Yang, Jianfeng Chi

Robustness in NLP

Challenge:	Recent advances in Large Language Models have sparked concerns about their safety.
Approach:	They propose a method to identify safety-related information in the model parameter space . they propose to use a few adversarially chosen examples to fine-tune LLMs .
Outcome:	The proposed method can break safety alignment in multilingual LLMs using a few examples . it also shows that the proposed method jailbreaks LLM models adapted to new languages .

Reasoning with Graphs: Structuring Implicit Knowledge to Enhance LLMs Reasoning (2025.findings-acl)

Copied to clipboard

Haoyu Han, Yaochen Xie, Hui Liu, Xianfeng Tang, Sreyashi Nag, William Headden, Yang Li, Chen Luo, Shuiwang Ji, Qi He, Jiliang Tang

CRUXEVAL-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution (2025.acl-long)

Challenge:	Large language models (LLMs) have demonstrated remarkable success across a wide range of tasks, however, they still face challenges in reasoning tasks that require understanding and inferring relationships between distinct pieces of information within text sequences.
Approach:	They propose to construct explicit graphs from context and leverage them to enhance LLM reasoning performance on reasoning tasks.
Outcome:	Extensive experiments show that the proposed method improves both logical reasoning and multi-hop question answering tasks.

Copied to clipboard

Ruiyang Xu, Jialun Cao, Yaojie Lu, Ming Wen, Hongyu Lin, Xianpei Han, Ben He, Shing-Chi Cheung, Le Sun