Papers by Lei Deng

HTMuon: Improving Muon via Heavy-Tailed Spectral Correction (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have recently achieved remarkable progress on complex reasoning tasks by leveraging extended Chain-of-Thought (CoT) techniques.
Approach:	They propose a method that uses Extended Chain-of-Thought (EFT) to reduce the number of output tokens by nearly 40% while maintaining the accuracy of the reasoning.
Outcome:	The proposed method reduces the number of output tokens by nearly 40% while maintaining the accuracy of the reasoning.

Copied to clipboard

Tianyu Pang, Yujie Fang, Zihang Liu, Shenyang Deng, Lei Hsiung, Shuhua Yu, Yaoqing Yang

LightNER: A Lightweight Tuning Paradigm for Low-resource NER via Pluggable Prompting (2022.coling-1)

Challenge:	Muon’s orthogonalized update rule suppresses the emergence of heavy-tailed weight spectra and over-emphasizes the training along noise-dominated directions.
Approach:	They propose to preserve Muon's ability to capture parameter interdependencies while producing heavier-tailed updates and inducing heavier-tail weight spectra.
Outcome:	The proposed algorithm suppresses the emergence of heavy-tailed weight spectra and over-emphasizes training along noise-dominated directions.

Copied to clipboard

Xiang Chen, Lei Li, Shumin Deng, Chuanqi Tan, Changliang Xu, Fei Huang, Luo Si, Huajun Chen, Ningyu Zhang

Low-Resource NLP

Challenge:	Existing approaches for Named Entity Recognition (NER) use extensive labeled data for model training, which struggles in low-resource scenarios.
Approach:	They propose a lightweight tuning paradigm for low-resource NER via pluggable prompting . they construct a learnable verbalizer of entity categories without any label-specific classifiers .
Outcome:	The proposed model outperforms baselines and class transfer models in low-resource scenarios.

Translating a Math Word Problem to a Expression Tree (D18-1)

Copied to clipboard

Lei Wang, Yan Wang, Deng Cai, Dongxiang Zhang, Xiaojiang Liu

Temp-R1: A Unified Autonomous Agent for Complex Temporal KGQA via Reverse Curriculum Reinforcement Learning (2026.acl-long)

Challenge:	Sequence-to-sequence (SEQ2SEQ) models have been successfully applied to automatic math word problem solving.
Approach:	They propose an equation normalization method to normalize duplicated equations and propose an ensemble model to combine their advantages.
Outcome:	The proposed model outperforms the previous state-of-the-art models on the math word problem solving.

Copied to clipboard

Zhaoyan Gong, Zhiqiang Liu, Songze Li, Xiaoke Guo, Yuanxiang Liu, Xinle Deng, Zhizhen Liu, Lei Liang, Huajun Chen, Wen Zhang

Good Visual Guidance Make A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation Extraction (2022.findings-naacl)

Challenge:	Existing methods rely on fixed workflows and expensive closed-source APIs, limiting flexibility and scalability.
Approach:	They propose a temporal reasoning agent that trains on difficult questions first . they expand the action space with specialized internal actions alongside external action .
Outcome:	The proposed agent improves 19.8% over baselines on complex questions and multi-tasks.

Copied to clipboard

Xiang Chen, Ningyu Zhang, Lei Li, Yunzhi Yao, Shumin Deng, Chuanqi Tan, Fei Huang, Luo Si, Huajun Chen

Information Extraction & Text Mining

Challenge:	Existing approaches for named entity recognition and relation extraction suffer from error sensitivity when irrelevant object images are incorporated in texts.
Approach:	They propose a hierarchical visual prefix fusion NeTwork for visual-enhanced entity and relation extraction using pluggable visual prefixed visual features.
Outcome:	The proposed method achieves state-of-the-art on three benchmark datasets.

PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance (2022.emnlp-main)

Copied to clipboard

Yang Deng, Wenqiang Lei, Wenxuan Zhang, Wai Lam, Tat-Seng Chua

STYLE: Improving Domain Transferability of Asking Clarification Questions in Large Language Model Powered Conversational Agents (2024.findings-acl)

Challenge:	Existing studies on financial question answering systems focus on passively responding to user queries.
Approach:	They propose a new dataset to facilitate conversational question answering over hybrid contexts in finance . they propose PACIFIC to combine clarification question generation and CQA .
Outcome:	The proposed method performs multi-task learning over all sub-tasks in PACIFIC . it incorporates a simple ensemble strategy to alleviate error propagation issue .

Copied to clipboard

Yue Chen, Chen Huang, Yang Deng, Wenqiang Lei, Dingnan Jin, Jia Liu, Tat-Seng Chua

How to Enable Effective Cooperation Between Humans and NLP Models: A Survey of Principles, Formalizations, and Beyond (2025.acl-long)

Challenge:	Existing methods for addressing ambiguities in conversational search systems are one-size-fits-all and struggle to achieve effective domain transferability.
Approach:	They propose a method to provide search engines with strategies regarding when to ask clarification questions in a post-hoc manner.
Outcome:	The proposed method improves search performance 10% on four unseen domains.

Copied to clipboard

Chen Huang, Yang Deng, Wenqiang Lei, Jiancheng Lv, Tat-Seng Chua, Jimmy Huang

Semantic Text Processing

Challenge:	Using large language models, intelligent models have evolved into autonomous agents . this paradigm has yielded remarkable progress in numerous NLP tasks in recent years .
Approach:	They present a review of human-model cooperation, exploring its principles, formalizations, and open challenges.
Outcome:	The proposed model-model cooperation paradigm has been a key focus of recent research . it is a novel paradigm that can be applied to a variety of tasks .

Breaking the Stigma! Unobtrusively Probe Symptoms in Depression Disorder Diagnosis Dialogue (2025.findings-naacl)

Copied to clipboard

Jieming Cao, Chen Huang, Yanan Zhang, Ruibo Deng, Jincheng Zhang, Wenqiang Lei

E2EDev: Benchmarking Large Language Models in End-to-End Software Development Task (2026.acl-long)

Challenge:	Recent efforts to improve depression-diagnosis-oriented dialogue systems ignore the Stigma preventing users from open conversations about their struggles.
Approach:	They propose a method to promote a sense of unobtrusiveness within the dialogue system and assessing depression disorder by probing symptoms.
Outcome:	The proposed method improves on baselines including unobtrusiveness evaluation of dialogue content and diagnostic accuracy.

Copied to clipboard

Jingyao Liu, Chen Huang, Zhizhao Guan, Wenqiang Lei, Yang Deng

CogEmp:A Cognitive Empathy-Oriented Dialogue System for Structured Psychological Counseling (2026.findings-acl)

Challenge:	Existing E2ESD benchmarks are limited by coarse-grained requirement specifications and unreliable evaluation protocols.
Approach:	They propose a benchmark to assess whether generated software meets user needs . they use a fine-grained set of user requirements and a fully automated testing pipeline .
Outcome:	E2EDev is a benchmark to assess whether generated software meets user needs through mimicking real user interactions.

Copied to clipboard

Yiguo Deng, Xia Lei, Yuan Zhang, Long Ye

Dialogue Systems & Conversational Agents

Challenge:	Existing models lack accurate modeling of cognitive empathy, especially the ability to understand users’ emotions and their underlying psychological causes.
Approach:	They propose a model tailored for the Chinese cultural context that integrates cognitive empathy into LLMs.
Outcome:	The proposed model outperforms existing models in key evaluation metrics, particularly in empathy, comprehensibility, and professionalism.

Logic-Thinker: Teaching Large Language Models to Think more Logically. (2025.findings-emnlp)

Copied to clipboard

Chengyao Wen, Qiang Cheng, Shaofei Wang, Zhizhen Liu, Deng Zhao, Lei Liang

Strength Lies in Differences! Improving Strategy Planning for Non-collaborative Dialogues via Diversified User Simulation (2024.emnlp-main)

Challenge:	Recent Large Reasoning Models (LRMs) have demonstrated the ability to generate long chains of thought (LongCoT) LongCoT still faces challenges such as redundancy and logical incoherence.
Approach:	They propose a neural-symbolic reasoning framework that generates chains of thought . they propose Logic-Thinker, which transforms symbolic solvers into chains of thoughts .
Outcome:	The proposed framework outperforms models fine-tuned with ThinkerCoT on logic reasoning tasks.

Copied to clipboard

Tong Zhang, Chen Huang, Yang Deng, Hongru Liang, Jia Liu, Zujie Wen, Wenqiang Lei, Tat-Seng Chua

Editing Conceptual Knowledge for Large Language Models (2024.findings-emnlp)

Challenge:	Non-collaborative dialogue agents are expected to engage in strategic conversations with diverse users, and this poses two main challenges for existing dialogue agents: 1) the inability to integrate user-specific characteristics into the strategic planning; 2) the difficulty of training strategic planners that can be generalized to diverse users.
Approach:	They propose to integrate a user-aware strategic planning module and a population-based training paradigm into a non-collaborative dialogue agent for securing a mutual agreement that leans favorably towards the system's objectives.
Outcome:	The proposed model can be used to achieve a mutual agreement that leans favorably towards the system's objectives.

Copied to clipboard

Xiaohan Wang, Shengyu Mao, Shumin Deng, Yunzhi Yao, Yue Shen, Lei Liang, Jinjie Gu, Huajun Chen, Ningyu Zhang

Semantic Text Processing

Challenge:	Existing knowledge editing methods can modify concept-level definitions, but they can distort instantial knowledge in LLMs, leading to poor performance.
Approach:	They construct a benchmark dataset ConceptEdit and establish new metrics for evaluation to investigate the editing capability of LLMs.
Outcome:	The proposed methods can modify concept definitions but can distort instantial knowledge in LLMs, leading to poor performance.

CLAMBER: A Benchmark of Identifying and Clarifying Ambiguous Information Needs in Large Language Models (2024.acl-long)

Copied to clipboard

Tong Zhang, Peixin Qin, Yang Deng, Chen Huang, Wenqiang Lei, Junhong Liu, Dingnan Jin, Hongru Liang, Tat-Seng Chua

Semantic Text Processing

Challenge:	Large language models are used to meet user information needs, but their effectiveness in dealing with user queries that contain various types of ambiguity remains unknown.
Approach:	They propose a benchmark for evaluating large language models using a well-organized taxonomy.
Outcome:	The proposed model is based on a well-organized taxonomy and compares it with other models.

ConReader: Exploring Implicit Relations in Contracts for Contract Clause Extraction (2022.emnlp-main)

Copied to clipboard

Weiwen Xu, Yang Deng, Wenqiang Lei, Wenlong Zhao, Tat-Seng Chua, Wai Lam

Information Extraction & Text Mining

Challenge:	Existing CCE methods treat contracts as plain text, creating a barrier to understanding complex contracts.
Approach:	They propose a framework to model implicit relations in legal contracts to improve contract understanding . they propose Term-Definition Relation captures the relation between important terms and their definitions .
Outcome:	The proposed framework improves on two CCE tasks in conventional and zero-shot settings.

Knowledge as A Bridge: Improving Cross-domain Answer Selection with External Knowledge (C18-1)

Copied to clipboard

Yang Deng, Ying Shen, Min Yang, Yaliang Li, Nan Du, Wei Fan, Kai Lei

Question Answering

Challenge:	Existing approaches to answer selection are limited in domains with limited labeled data.
Approach:	They propose a Knowledge-aware Attentive Network framework for cross-domain answer selection that uses the knowledge base as a bridge to enable knowledge transfer from the source domain to the target domain.
Outcome:	The proposed model outperforms strong competitors by a noticeable margin in cross-domain answer selection.

Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration (2023.findings-emnlp)

Copied to clipboard

Yang Deng, Lizi Liao, Liang Chen, Hongru Wang, Wenqiang Lei, Tat-Seng Chua

CoTrust: Privacy-Preserving Collaboration Between Large and Small Language Models in Trusted Execution Environments (2026.findings-acl)

Challenge:	Recent studies have shown that ChatGPT has limitations such as failing to ask clarifying questions to ambiguous queries or refusing problematic user requests.
Approach:	They propose a Proactive Chain-of-Thought prompting scheme which augments LLMs with the goal planning capability over descriptive reasoning chains to trigger proactivity.
Outcome:	The proposed scheme augments LLMs with the goal planning capability over descriptive reasoning chains to trigger the proactivity of LLM-based proactive dialogue systems.

Copied to clipboard

Zhenya Ma, Tingyi Wang, Yongheng Deng, Ziqing Qiao, Yinggui Wang, Tao Wei, Lei Wang, Ju Ren

Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System (2022.acl-long)

Challenge:	Large language models (LLMs) provide powerful text generation capabilities, but accessing sensitive user inputs raises privacy concerns.
Approach:	They propose a privacy-preserving collaborative inference framework that combines large language models with small language models inside TEE to preserve privacy.
Outcome:	Experiments show that CoTrust outperforms unconstrained LLMs on multiple question answering and summarization benchmarks while maintaining strong privacy protection.

Copied to clipboard

Yixuan Su, Lei Shu, Elman Mansimov, Arshit Gupta, Deng Cai, Yi-An Lai, Yi Zhang

DORA: A Dual-Objective Reinforcement Learning Framework for Effective and Efficient Multimodal Agentic Search (2026.acl-long)

Challenge:	Existing pre-trained language models often form a cascaded generation problem . this can lead to error accumulation across different sub-tasks and greater data annotation overhead.
Approach:	They propose a plug-and-play model for task-oriented dialogue that learns primary TOD task completion skills from heterogeneous dialog corpora.
Outcome:	The proposed model learns primary TOD task completion skills from heterogeneous dialog corpora.

Copied to clipboard

Guangming Qin, Yuhao Deng, Yukun Zhao, Zhenyang Li, Junfeng Wang, Dawei Yin, Ye Yuan, Guoren Wang, Yizhou Yan, Chengliang Chai, Lei Cao

Selective Annotation via Data Allocation: These Data Should Be Triaged to Experts for Annotation Rather Than the Model (2024.findings-emnlp)

Challenge:	Existing methods to train large language models overlook quality of intermediate search results . existing methods often invoke search calls during reasoning, making inference inefficient .
Approach:	They propose a dual-objective reinforcement learning framework to improve search strategies of MLLMs . DORA outperforms state-of-the-art methods, achieving up to 8.4% higher accuracy .
Outcome:	The proposed model outperforms state-of-the-art methods while reducing search calls by 9.7%.

Copied to clipboard

Chen Huang, Yang Deng, Wenqiang Lei, Jiancheng Lv, Ido Dagan

Extending Context Window of Large Language Models via Semantic Compression (2024.findings-acl)

Challenge:	Existing methods to obtain high-quality annotations under limited budgets focus on selecting informative data for expert annotations while the rest of the data is assigned to model annotation.
Approach:	They propose a semi-automatic annotation framework that uses error-aware triage and bi-weighting mechanisms to obtain high-quality annotations under limited budget.
Outcome:	The proposed framework outperforms baselines in the data annotation problem under limited budgets.

Copied to clipboard

Weizhi Fei, Xueyan Niu, Pingyi Zhou, Lu Hou, Bo Bai, Lei Deng, Wei Han

SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis (2025.findings-emnlp)

Challenge:	Existing models rely on a quadratic computation to generate long texts . current models impose limitations on the length of text inputs .
Approach:	They propose a semantic compression method that extends the context window of large language models . the method reduces the semantic redundancy of long inputs before passing them to the LLMs .
Outcome:	The proposed method extends the context window of large language models across tasks . it exhibits consistent fluency in text generation while reducing associated computational overhead.

Copied to clipboard

Shuang Sun, Huatong Song, Yuhao Wang, Ruiyang Ren, Jinhao Jiang, Junjie Zhang, Fei Bai, Jia Deng, Xin Zhao, Zheng Liu, Lei Fang, Zhongyuan Wang, Ji-Rong Wen

Self-attention-based Graph-of-Thought for Math Problem Solving (2025.findings-acl)

Challenge:	Existing approaches to deep search training lack high-quality training trajectories, prohibitive computational costs and lack of high-fidelity training data.
Approach:	They propose a framework that synthesizes high-quality training data by simulating real user interactions in live web search environments.
Outcome:	The proposed framework synthesizes high-quality training data by simulating user interactions in live web search environments.

Copied to clipboard

Ruiqiao Bai, Xue Han, Shuo Lei, Junlan Feng, Yanyan Luo, Chao Deng

FactCG: Enhancing Fact Checkers with Graph-Based Multi-Hop Data (2025.naacl-long)

Challenge:	Existing methods for generating reasoning paths in a chain structure are inefficient and non-human-like.
Approach:	They propose a decoding method for a chain-based LLM that constructs a thought graph simultaneously as an LLM inference and generates reasoning steps with a graph-structured self-attention mechanism.
Outcome:	The proposed method improves reasoning accuracy without huge computational over-expensive LLMs and avoids performance degradation issues when the LLM is too small to comprehend complex prompts.

Copied to clipboard

Deren Lei, Yaxi Li, Siyao Li, Mengya Hu, Rui Xu, Ken Archer, Mingyu Wang, Emily Ching, Alex Deng

GraphOTTER: Evolving LLM-based Graph Reasoning for Complex Table Question Answering (2025.coling-main)

Challenge:	Prior research on training grounded factuality classification models to detect hallucinations in large language models (LLMs) has relied on public natural language inference (NLI) data and synthetic data.
Approach:	They propose a method that leverages multi-hop reasoning on context graphs extracted from documents to generate complex multi-level claims without relying on LLMs to decide data labels.
Outcome:	The proposed model outperforms GPT-4-o on the LLM-Aggrefact benchmark with much smaller model size.

Copied to clipboard

Qianlong Li, Chen Huang, Shuai Li, Yuanxin Xiang, Deng Xiong, Wenqiang Lei

Structured Data in NLP

Challenge:	Existing methods for complex table question answering are often implicit, feeding the entire table into prompts.
Approach:	They propose a GraphOTTER that explicitly establishes the reasoning process to pinpoint the correct answers.
Outcome:	The proposed method is able to identify the correct answers on two benchmark datasets and two LLM backbones.

KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents (2025.findings-naacl)

Copied to clipboard

Yuqi Zhu, Shuofei Qiao, Yixin Ou, Shumin Deng, Shiwei Lyu, Yue Shen, Lei Liang, Jinjie Gu, Huajun Chen, Ningyu Zhang