Papers by Jie Feng

Depression Detection on Social Media with Large Language Models (2025.emnlp-industry)

Challenge:	Large language models (LLMs) have extensive world knowledge, but often generate inaccurate geospatial knowledge.
Approach:	They propose a framework for evaluation of large language models to mitigate hallucinations . they use Kahneman-Tversky Optimization to align LLMs with their reality .
Outcome:	The proposed evaluation framework uncovers hallucinations in 20 advanced LLMs.

Copied to clipboard

Xiaochong Lan, Zhiguang Han, Yiming Cheng, Li Sheng, Jie Feng, Chen Gao, Yong Li

Semantic Text Processing

Challenge:	Existing methods for analyzing social media data lack a systematic integration of medical knowledge, causing a critical treatment gap.
Approach:	They propose a framework that leverages Large Language Models to integrate medical knowledge into social media data.
Outcome:	The proposed framework can be used to distinguish depression from transient mood changes.

WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning (2026.acl-long)

Copied to clipboard

Junjie Wang, Zequn Xie, Dan Yang, Jie Feng, Yue Shen, Duolin Sun, Meixiu Long, Yihan Jiao, Zhehao Tan, Jian Wang, Peng Wei, Jinjie Gu

Structured Data in NLP

Challenge:	Open-source web agents rely on long tool-call trajectories with cyclic reasoning loops and exploration of unproductive branches.
Approach:	They propose a framework that compresses web agent trajectories via graph-based pruning.
Outcome:	The proposed framework reduces tool-call rounds by 20% while improving accuracy and efficiency while maintaining the same level of performance as existing models.

Prompt-based Generation of Natural Language Explanations of Synthetic Lethality for Cancer Drug Discovery (2024.lrec-main)

Copied to clipboard

Ke Zhang, Yimiao Feng, Jie Zheng

EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding (2025.findings-acl)

Challenge:	Synthetic lethality (SL) is a genetic interaction where a single gene mutation allows cell survival, but simultaneous mutations in two genes lead to cell death.
Approach:	They propose a prompt-based pipeline for generating natural language explanations using a dataset derived from New Bing .
Outcome:	The proposed pipeline improves on existing biomedical language models in terms of text quality and explainability.

Copied to clipboard

Mingxu Tao, Jie Hu, Mingchuan Yang, Yunhuai Liu, Dongyan Zhao, Yansong Feng

Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation (P19-1)

Challenge:	Existing methods to enhance performance of Large language models are limited due to the cost of training data and privacy concerns.
Approach:	They propose a method that enhances a finetuned model with its inferior version and adopts contrastive decoding to reduce predicted errors.
Outcome:	The proposed method outperforms existing methods in data-scarcity scenarios across three domains and shows that it is more robust and robust.

Copied to clipboard

Chenze Shao, Yang Feng, Jinchao Zhang, Fandong Meng, Xilin Chen, Jie Zhou

Incremental Transformer with Deliberation Decoder for Document Grounded Conversations (P19-1)

Challenge:	Experimental results show that the Reinforce-NAT system surpasses the baseline NAT system by a significant margin on BLEU without decelerating the decoding speed.
Approach:	They propose a sequence-level training method and a Transformer decoder to fuse the target sequential information into the top layer of the decoded Transformer.
Outcome:	The proposed model surpasses the baseline NAT system on BLEU without decelerating the decoding speed and achieves comparable translation performance to the autoregressive Transformer model with considerable speedup.

Copied to clipboard

Zekang Li, Cheng Niu, Fandong Meng, Yang Feng, Qian Li, Jie Zhou

HIRAG: Hierarchical-Thought Instruction-Tuning Retrieval-Augmented Generation (2025.findings-emnlp)

Challenge:	Existing dialogue systems do not exploit document knowledge effectively enough.
Approach:	They propose a Transformer-based architecture for document grounded conversations that incorporates document knowledge into a two-pass decoder to improve context coherence and knowledge correctness.
Outcome:	The proposed model outperforms baselines on context coherence and knowledge relevance on a real-world document grounded dataset.

Copied to clipboard

Yihan Jiao, Zhehao Tan, Dan Yang, Duolin Sun, Jie Feng, Yue Shen, Jian Wang, Peng Wei

Semantic Text Processing

Challenge:	In-depth research on the specific capabilities needed by the RAG generation model is lacking, leading to inconsistent document quality and retrieval system imperfections.
Approach:	They propose that RAG models should possess three progressively hierarchical abilities: (1) Filtering: the ability to select relevant information; (2) Combination: the capability to combine semantic information across paragraphs; (3) RAG-specific reasoning: the capacity to further process external knowledge using internal knowledge.
Outcome:	Experiments show that the proposed method significantly improves the model’s open-book examination capability on datasets such as RGB, PopQA, MuSiQue, HotpotQA, and PubmedQA.

AlignBench: Benchmarking Chinese Alignment of Large Language Models (2024.acl-long)

Copied to clipboard

Xiao Liu, Xuanyu Lei, Shengyuan Wang, Yue Huang, Andrew Feng, Bosi Wen, Jiale Cheng, Pei Ke, Yifan Xu, Weng Lam Tam, Xiaohan Zhang, Lichao Sun, Xiaotao Gu, Hongning Wang, Jing Zhang, Minlie Huang, Yuxiao Dong, Jie Tang

LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces (2026.findings-acl)

Challenge:	Effective evaluation of alignment for emerging Chinese LLMs is still significantly lacking, calling for real-scenario grounded, open-ended, challenging and automatic evaluations tailored for alignment.
Approach:	They propose a multi-dimensional benchmark for evaluating LLMs’ alignment in Chinese with 8 main categories, 683 real-scenario rooted queries and corresponding human verified references.
Outcome:	The benchmark uses a human-in-the-loop data curation pipeline, 683 real-scenario rooted queries and human verified references.

Copied to clipboard

Yukang Feng, Jianwen Sun, Zelai Yang, Jiaxin Ai, Chuanhao Li, Zizhen Li, Fanrui Zhang, Kang He, Rui Ma, Jifan Lin, Jie Sun, Yang Xiao, Sizhuo Zhou, Wenxiao Wu, Yiming Liu, Pengfei Liu, Shenglin Zhang, Kaipeng Zhang

Multimodality

Challenge:	Existing benchmarks for agentic programming in long-horizon command-line interface tasks are limited by short task horizons, data contamination from GitHub scraping, and a lack of fine-grained evaluation metrics.
Approach:	They propose a benchmark to evaluate agentic capabilities across long-horizon command-line interface tasks.
Outcome:	The proposed benchmarks cover four engineering categories: from scratch, feature addition, bug fixing, and refactoring.

CARL: Constraint-Aware Reinforcement Learning for Planning with LLMs (2026.findings-acl)

Copied to clipboard

Qiuyi Qi, Jinjian Zhang, Mutian Bao, Tian Liang, Guocong Li, Dongnan Liu, Wei Zhou, Jie Liu, Ming Kong, Linjian Mo, Feng Zhang, Qiang Zhu

Reasoning

Challenge:	Existing approaches to constraint-aware planning fail to enhance the model’s intrinsic focus on constraints.
Approach:	They propose a constraint-aware reinforcement learning framework that encourages constraint focus and penalizes neglect of LLMs.
Outcome:	The proposed framework outperforms existing frameworks and state-of-the-art reasoning models in a number of real-world applications.

Deep Cognitive Reasoning Network for Multi-hop Question Answering over Knowledge Graphs (2021.findings-acl)

Copied to clipboard

Jianyu Cai, Zhanqiu Zhang, Feng Wu, Jie Wang

Structured Data in NLP

Challenge:	Knowledge Graphs (KGs) store structured human knowledge with nodes and edges being entities and relations between them.
Approach:	They propose a deep cognitive reasoning network that uses two phases to find answers in large candidate entity sets.
Outcome:	The proposed method significantly outperforms state-of-the-art methods on benchmark datasets.

AutoQual: An LLM Agent for Automated Discovery of Interpretable Features for Review Quality Assessment (2025.emnlp-industry)

Copied to clipboard

Xiaochong Lan, Jie Feng, Yinxing Liu, null Xinleishi, Yong Li

GDLLM: A Global Distance-aware Modeling Approach Based on Large Language Models for Event Temporal Relation Extraction (2025.findings-emnlp)

Challenge:	Existing methods for assessing review quality are unscalable across domains and fail to adapt to evolving content patterns.
Approach:	They propose an LLM-based agent framework that automates the discovery of interpretable features.
Outcome:	The proposed framework improves on a large-scale online platform with a billion-level user base.

Copied to clipboard

Jie Zhao, Wanting Ning, Yuxiao Fei, Yubo Feng, Lishuang Li

MOOCCube: A Large-scale Data Repository for NLP Applications in MOOCs (2020.acl-main)

Challenge:	Existing approaches to analyzing large language models are limited by their pre-trained knowledge of Small Language Models(SLMs).
Approach:	They propose a global distance-aware modeling approach based on Large Language Models (LLMs) they first present a distance-based graph structure utilizing Graph Attention Network(GAT)
Outcome:	The proposed approach significantly improves minority relation class learning ability on two publicly available datasets, TB-Dense and MATRES.

Copied to clipboard

Jifan Yu, Gan Luo, Tong Xiao, Qingyang Zhong, Yuquan Wang, Wenzheng Feng, Junyi Luo, Chenyu Wang, Lei Hou, Juanzi Li, Zhiyuan Liu, Jie Tang

Information Extraction & Text Mining

Challenge:	Massive open online courses (MOOCs) are a popular educational platform for advanced research.
Approach:	They propose to use MOOCCube to build a large-scale data repository of over 700 MOOC courses, 100k concepts, 8 million student behaviors with an external resource.
Outcome:	The proposed datasets show that they can facilitate research in MOOCs.

MFinMeeting: A Multilingual, Multi-Sector, and Multi-Task Financial Meeting Understanding Evaluation Dataset (2025.findings-acl)

Copied to clipboard

Jie Zhu, Junhui Li, Yalong Wen, Xiandong Li, Lifan Guo, Feng Chen

Conversations Are Not Flat: Modeling the Dynamic Information Flow across Dialogue Utterances (2021.acl-long)

Challenge:	Existing financial benchmarks rely on news articles, earnings reports, or announcements, making it challenging to capture the real-world dynamics of financial meetings.
Approach:	They propose a multilingual, multi-sector, and multi-task dataset called MFinMeeting that supports English, Chinese, and Japanese .
Outcome:	The proposed benchmark supports English, Chinese, and Japanese, enhancing comprehension of financial discussions in diverse linguistic contexts.

Copied to clipboard

Zekang Li, Jinchao Zhang, Zhengcong Fei, Yang Feng, Jie Zhou

Counterfactual Data Augmentation via Perspective Transition for Open-Domain Dialogues (2022.emnlp-main)

Challenge:	Recent intelligent open-domain chatbots have made substantial progress thanks to the rapid development of large-scale pre-training approaches.
Approach:	They propose a dynamic flow mechanism to model the context flow and a model to capture the information dynamics across dialogue utterances.
Outcome:	The proposed model outperforms the DialoGPT on the dialogue generation task.

Copied to clipboard

Jiao Ou, Jinchao Zhang, Yang Feng, Jie Zhou

Do MLLMs Understand Pointing? Benchmarking and Enhancing Referential Reasoning in Egocentric Vision (2026.findings-acl)

Challenge:	Existing methods to augment dialogue datasets are labor-intensive and time-consuming . Currently, smoking is harmful for your health.
Approach:	They propose a data augmentation method to augment dialogue responses with different semantics by counterfactual inference.
Outcome:	The proposed method outperforms baselines on multiple downstream tasks.

Copied to clipboard

Chentao Li, Zirui Gao, Mingze Gao, Yinglian Ren, Jianjiang Feng, Jie Zhou

Multimodality

Challenge:	Egocentric AI agents rely on pointing to resolve referential ambiguities in natural language commands.
Approach:	They propose a question-answering benchmark to evaluate and enhance pointing reasoning in egocentric views.
Outcome:	The proposed benchmark evaluates and enhances pointing reasoning in egocentric views.

Addressing Inquiries about History: An Efficient and Practical Framework for Evaluating Open-domain Chatbot Consistency (2021.findings-acl)

Copied to clipboard

Zekang Li, Jinchao Zhang, Zhengcong Fei, Yang Feng, Jie Zhou

Open-Set Living Need Prediction with Large Language Models (2025.findings-acl)

Challenge:	Existing methods to evaluate consistency capacity of open-domain chatbots are costly and low-efficient.
Approach:	They propose an efficient framework for evaluating consistency of open-domain chatbots . they use human judges to interact with chatbot, which is costly and low-efficient .
Outcome:	The proposed framework can assess the consistency capacity of chatbots and achieve a high ranking correlation with the human evaluation.

Copied to clipboard

Xiaochong Lan, Jie Feng, Yizhou Sun, Chen Gao, Jiahuan Lei, Xinleishi Xinleishi, Hengliang Luo, Yong Li

Semantic Text Processing

Challenge:	Existing approaches to living need prediction treat it as a closed-set classification problem, severely limiting their ability to capture diversity and complexity of living needs.
Approach:	They propose a system leveraging large language models for unrestricted need prediction that leverages Maslow's hierarchy of needs to align predictions with human living needs.
Outcome:	The proposed system outperforms closed-set approaches on need-based life service recall by an average of 19.37% on real-world datasets.

Prompts Can Play Lottery Tickets Well: Achieving Lifelong Information Extraction via Lottery Prompt Tuning (2023.acl-long)

Copied to clipboard

Zujie Liang, Feng Wei, Yin Jie, Yuxi Qian, Zhenghong Hao, Bing Han

Enhancing Large Vision-Language Models with Ultra-Detailed Image Caption Generation (2025.emnlp-main)

Challenge:	Existing research on information extraction tasks focuses on one specific task, but in real-world scenarios, new data of different IE tasks and domains come in a stream over time.
Approach:	They propose a parameter- and deployment-efficient prompt tuning method to evaluate the UIE system under a “lifelong learning” setting.
Outcome:	The proposed method is able to learn new tasks without forgetting old ones and expand knowledge and functionalities without retraining the whole system.

Copied to clipboard

Yu Zeng, Yukun Qi, Yiming Zhao, Xikun Bao, Lin Chen, Zehui Chen, Shiting Huang, Jie Zhao, Feng Zhao

Multimodality

Challenge:	Existing pipelines for generating high-quality, ultra-detailed image captions are limited by the scarcity of image caption data.
Approach:	They propose a pipeline for generating high-quality, ultra-detailed image captions that integrates both pre-processing and post-processor stages.
Outcome:	The proposed pipeline improves LVLMs' perception and cognitive abilities across multiple vision-language benchmarks.

BFS-Prover: Scalable Best-First Tree Search for LLM-based Automatic Theorem Proving (2025.acl-long)

Copied to clipboard

Ran Xin, Chenguang Xi, Jie Yang, Feng Chen, Hang Wu, Xia Xiao, Yifan Sun, Shen Zheng, Ming Ding

Information Retrieval

Challenge:	Existing approaches to theorem proving in large language models rely on value functions and/or Monte Carlo Tree Search (MCTS), but the potential of simpler methods like Best-First Tree Search remains underexplored.
Approach:	They propose a scalable expert iteration framework that implements strategic data filtering at each expert iteration round, excluding problems solvable via beam search node expansion to focus on harder cases.
Outcome:	The proposed framework achieves a state-of-the-art score of 72.95 on the MiniF2F test set and challenges the perceived necessity of complex tree search methods.

A Contextual Hierarchical Attention Network with Adaptive Objective for Dialogue State Tracking (2020.acl-main)

Copied to clipboard

Yong Shan, Zekang Li, Jinchao Zhang, Fandong Meng, Yang Feng, Cheng Niu, Jie Zhou

AgentMove: A Large Language Model based Agentic Framework for Zero-shot Next Location Prediction (2025.naacl-long)

Challenge:	Existing methods for dialogue state tracking ignore the slot imbalance problem and treat all slots indiscriminately, which limits the learning of hard slots.
Approach:	They propose to employ a contextual hierarchical attention network to enhance the DST by learning contextual representations.
Outcome:	The proposed approach achieves 52.68% and 58.55% joint accuracy on multiWOZ 2.0 and MultiWOZ 2.1 datasets and significantly improves performance (+1.24% and +5.98%)

Copied to clipboard

Jie Feng, Yuwei Du, Jie Zhao, Yong Li

GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs (2026.findings-acl)

Challenge:	Existing methods to apply large language models to zero-shot next location prediction tasks are limited due to their limited computational power.
Approach:	They propose a systematic agentic prediction framework to achieve generalized next location prediction.
Outcome:	The proposed framework surpasses the leading baseline by 3.33% to 8.57% across 8 out of 12 metrics.

Copied to clipboard

Meixiu Long, Duolin Sun, Dan Yang, Yihan Jiao, Lei Liu, Jiahai Wang, Binbin Hu, Yue Shen, Jie Feng, Zhehao Tan, Junjie Wang, Lianzhen Zhong, Jian Wang, Peng Wei, Jinjie Gu

COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values (2026.findings-eacl)

Challenge:	Existing rankers excel in lexical-matching scenarios, while they struggle with complex queries requiring deep reasoning.
Approach:	They propose a new paradigm that balances flexibility and context awareness to unlock the full potential of groupwise reranking.
Outcome:	The proposed approach achieves a state-of-the-art 65.2 NDCG@10 on BRIGHT and surpasses baselines by 2.1 points on R2MED while delivering a 6.4 inference speedup.

Copied to clipboard

Siwei Wu, JinCheng Ren, Xeron Du, Shuyue Guo, Xingwei Qu, Yiming Liang, Jie Liu, Yunwen Li, Tyler Loakman, Tianyu Zheng, Boyu Feng, Huaqing Yuan, Zili Wang, Jiaheng Liu, Wenhao Huang, Chenglin Cai, Haoran Que, Jian Yang, Yuelin Bai, Zekun Moore Wang, Zhouliang Yu, Qunshu Lin, Ding Pan, Yuchen Eleanor Jiang, Tiannan Wang, Wangchunshu Zhou, Shenzhi Wang, Xingyuan Bu, Minghao Liu, Guoyin Wang, Ge Zhang, Chenghua Lin

GTM: A Generative Triple-wise Model for Conversational Question Generation (2021.acl-long)

Challenge:	Existing Chinese preference datasets suffer from limited scale, restricted domain coverage, and insufficiently rigorous data validation.
Approach:	They propose an LLM-based data annotation pipeline with no human intervention to annotate Chinese preference datasets.
Outcome:	The proposed pipeline outperforms existing Chinese preference datasets on AlignBench and Chinese Reward Benchmark.

Copied to clipboard

Lei Shen, Fandong Meng, Jinchao Zhang, Yang Feng, Jie Zhou

Natural Language Interfaces

Challenge:	Experimental results show that opendomain conversational question generation improves the quality of questions in terms of fluency, coherence and diversity over competitive baselines.
Approach:	They propose a triple-wise model with hierarchical variations for open-domain conversational question generation using a post-question-answer triple and one-to-many semantic mappings.
Outcome:	The proposed model significantly improves the quality of questions in terms of fluency, coherence and diversity over baselines.

Enhancing Context Modeling with a Query-Guided Capsule Network for Document-level Translation (D19-1)

Copied to clipboard

Zhengxin Yang, Jinchao Zhang, Fandong Meng, Shuhao Gu, Yang Feng, Jie Zhou

Machine Translation

Challenge:	Context modeling is essential to generate coherent and consistent translation for document-level Neural Machine Translations.
Approach:	They propose a query-guided capsule network to cluster context information into different perspectives from which the target translation may concern.
Outcome:	The proposed model outperforms baseline models on multiple datasets of different domains.

CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation (2024.acl-long)

Copied to clipboard

Pei Ke, Bosi Wen, Andrew Feng, Xiao Liu, Xuanyu Lei, Jiale Cheng, Shengyuan Wang, Aohan Zeng, Yuxiao Dong, Hongning Wang, Jie Tang, Minlie Huang

HoWToBench: Holistic Evaluation for LLM’s Capability in Human-level Writing using Tree of Writing (2026.acl-long)

Challenge:	Existing models for NLP evaluations lack the ability to generate informative critiques in pointwise grading and pairwise comparison especially without references.
Approach:	They propose a method which can acquire pointwise grading critiques with pseudo references and revise these critiques via multi-path prompting to obtain informative evaluation data in different tasks and settings.
Outcome:	The proposed method outperforms all open-source models and even GPT-4 in system-level correlations of pointwise grading.

Copied to clipboard

Andrew Zhuoer Feng, Cunxiang Wang, Yu Luo, Lin Fan, Irene Zhou, Zikang Wang, Xiaotao Gu, Jie Tang, Hongning Wang, Minlie Huang

Challenge:	Evaluating the writing capabilities of large language models remains a significant challenge due to the multidimensional nature of writing skills and the limitations of existing metrics.
Approach:	They propose to model the aggregation weights of sub-features in a tree-structured workflow and propose a Chinese writing benchmark that mitigates biases.
Outcome:	The proposed tree-of-writing (ToW) measures the writing capabilities of large language models (LLMs) in Chinese and shows that it mitigates biases and achieves a 0.93 Pearson correlation with human judgments.

Defining and Evaluating Visual Language Models’ Basic Spatial Abilities: A Perspective from Psychometrics (2025.acl-long)

Copied to clipboard

Wenrui Xu, Dalin Lyu, Weihang Wang, Jie Feng, Chen Gao, Yong Li

Token-level Adaptive Training for Neural Machine Translation (2020.emnlp-main)

Challenge:	Existing studies assessing the spatial abilities of VLMs lack a solid theoretical foundation and lack measurable data.
Approach:	They propose a psychometric framework defining five basic spatial abilities in Visual Language Models.
Outcome:	The proposed framework defines five basic spatial abilities in Visual Language Models (VLMs) it provides a comprehensive evaluation benchmark and methodological perspective for embodied AI development .

Copied to clipboard

Shuhao Gu, Jinchao Zhang, Fandong Meng, Yang Feng, Wanying Xie, Jie Zhou, Dong Yu

Multilinguality

Challenge:	Existing token imbalance phenomenon in natural language as different tokens appear with different frequencies, which leads to different learning difficulties for tokens in Neural machine translation (NMT).
Approach:	They propose to assign tokens with different frequencies to target tokens during training to encourage the model to pay more attention to low-frequency tokens.
Outcome:	The proposed model yields consistent improvements on ZH-EN, EN-RO, and EN-DE translation tasks, especially on sentences that contain more low-frequency tokens.

STAPO: Selective Trajectory-Aware Policy Optimization for LLM Agent Training (2026.acl-long)

Copied to clipboard

Qiuyi Qi, Tian Liang, Mutian Bao, Jinjian Zhang, Dongnan Liu, Wei Zhou, Linjian Mo, Ming Kong, Jie Liu, Feng Zhang, Qiang Zhu