陈文清，2022年7月入选中山大学“百人计划”助理教授，硕士研究生导师，中国计算机学会自然语言处理专委会委员。2022年6月于上海交通大学人工智能研究院获得博士学位，2015年于北京师范大学脑与认知科学研究院获得硕士学位，2012年于华中科技大学电子与信息工程系数理提高班获得学士学位。主要研究方向包括自然语言处理、因果推断、大语言模型、智慧医疗、智慧司法等，目前聚焦基于因果推断的大语言模型偏差分析与缓解。主持国家自然科学基金青年科学基金项目、广东省自然科学基金面上项目等纵向课题，并主持4项大模型横向科研课题，参与国家重点研发计划、上海市级科技重大专项等国家级项目。近5年在ACL、EMNLP、AAAI、IJCAI等自然语言处理与人工智能领域CCF A/B类顶级会议及期刊发表论文30余篇，获国家发明专利授权7项，担任ACL、EMNLP、AAAI等国际顶会程序委员及Neural Networks等期刊审稿人。

学术主页：
Home page: https://chenwq95.github.io/
Google Scholar: https://scholar.google.com/citations?user=aJs9eskAAAAJ&hl=zh-CN
DBLP:  https://dblp.org/pid/31/2740.html

邮箱：

chenwq95@mail.sysu.edu.cn
 

课题组招生

每年招收推免或统考的硕士研究生，招生方向包括自然语言处理 (Natural Language Processing)、大语言模型（Large Language Models）等。欢迎有意向加入中山大学读研的同学，以及有意向参与科研的中山大学大二、大三本科生同学与我联系。优秀的毕业生可推荐到国内外高校深造或到各大互联网公司实习就业。

 

快讯

热烈祝贺课题组2022级本科生徐振杰、唐仡同学大二下学期投稿论文被人工智能领域的CCF A类国际顶会AAAI 2025（Oral Presentation）接收（本科生一作）！

 

教学活动

SSE347   Rust语言与内存安全设计   本科生选修课

SSE413   自然语言处理   本科生选修课

 

出版刊物
Wenqing Chen, Zhixuan Chu. Causal Inference and Natural Language Processing[M]//Machine Learning for Causal Inference. Cham: Springer International Publishing, 2023: 189-206.
 

学术服务

•   顶会审稿人（PC Member）：ACL Rolling Review（Area Chair）、ACL、EMNLP、COLING、AAAI、IJCAI、NeurIPS
•   顶刊审稿人：Neural Networks、Expert Systems With Applications、Cyber Security and Applications
•   出版主席：BlockSys 2024

 

学生深造与工作去向

•   2020与2021级本科生：曲飞宇（Carnegie Mellon University + Dartmouth College Offer）、胡城（腾讯微信事业群）
•   硕士生：研究生期间参与课题组大模型项目与科研，多位硕士生获腾讯、阿里、蚂蚁、字节、美团等大模型算法岗实习Offer（同时收获多Offer）
 

 

主持科研项目

2024 - 2026：（国家级纵向、主持）面向自然语言理解领域基于因果启发的反事实推理方法研究，国家自然科学基金青年科学基金项目
2024 - 2026：（省级纵向、主持）面向大语言模型的反事实提示学习研究，广东省自然科学基金（面上项目）
2024 - 2025：（校级纵向、主持）上海交通大学--人工智能教育部重点实验室开放课题
2025 - 2026：（横向、主持）基于混合专家模型的金融智能体研究，招联金融
2023 - 2024：（横向、主持）基于大语言模型的个性化营销与售后策略研究，招联金融
2024 - 2025：（横向、主持）AI大模型训练与推理的研究技术协作，中国电建集团
2023 - 2024：（横向、主持）基于AI大模型技术的水电数据分析应用研究机器学习训练系统的技术协作，中国电建集团

 

参与项目

2018-2021，国家重点研发计划项目，全流程管控的精细化执行技术及装备研究。

2020-2022，国家重点研发计划项目，基于区块链的老年主动健康智能照护平台研究与应用。

 

部分论文：

  1. Zhenjie Xu, Wenqing Chen*, Xuanying Li, Cheng Hu, Zhixuan Chu, Kui Ren, Zibin Zheng, Zhichao Lu. Mitigating Social Bias in Large Language Models: A Multi-Objective Approach within a Multi-Agent Framework. AAAI 2025 (CCF A)
  2. Zhuohao Li, Wenqing Chen*, Jianxing Yu, Zhichao Lu. Functional Consistency of LLM Code Embeddings: A Self-Evolving Data Synthesis Framework for Benchmarking. Expert Systems with Applications 2025. (SCI, 中科院1区).
  3. Weibin Wu, Zitong Wang, Zhengjie Luo, Wenqing Chen*, Zibin Zheng. Detecting Violations of Physical Common Sense in Images: A Challenge Dataset and Effective Model. ACM MM2025 (CCF A).
  4. Jianxing Yu, Shiqi Wang, Hanjiang Lai, Wenqing Chen, Yanghui Rao, Qinliang Su, Jian Yin. Generating Commonsense Reasoning Questions with Controllable Complexity through Multi-step Structural Composition. COLING 2025 (CCF B)
  5.  Wenqing Chen, Weicheng Wang, Zhixuan Chu, Kui Ren, Zibin Zheng, Zhichao Lu. Self-Para-Consistency: Improving Reasoning Tasks at Low Cost for Large Language Models[C]. ACL 2024 Findings. (CCF A)
  6.  Wenqing Chen, Jidong Tian, Caoyun Fan, Yitian Li, Hao He, Yaohui Jin. Preference-Controlled Multi-Objective Reinforcement Learning for Conditional Text Generation[C]. AAAI 2023. (CCF A)
  7.  Jidong Tian#, Wenqing Chen#, Yitian Li, Caoyun Fan, Hao He, Yaohui Jin. Latent Constraints on Unsupervised Text-Graph Alignment with Information Asymmetry[C]. AAAI 2023. (CCF A)
  8. Caoyun Fan#, Wenqing Chen#, Jidong Tian, Hao He, Yaohui Jin. Improving the Out-Of-Distribution Generalization Capability of Language Models: Counterfactually-Augmented Data is not Enough. ICASSP 2023 (CCF-B)
  9. Caoyun Fan#, Wenqing Chen#, Jidong Tian, Hao He, Yaohui Jin. Accurate use of label dependency in multi-label text classification through the lens of causality. 2023. Applied Intelligence. (SCI，中科院2区)
  10. Caoyun Fan, Jidong Tian, Yitian Li, Wenqing Chen, Hao He, Yaohui Jin. Chain-of-thought tuning: Masked language models can also think step by step in natural language understanding. EMNLP 2023 (CCF-B)
  11.  Wenqing Chen, Jidong Tian, Yitian Li, Hao He, Yaohui Jin. De-Confounded Variational Encoder-Decoder for Logical Table-to-Text Generation[C]. ACL/IJCNLP (1) 2021: 5532-5542. (CCF A)
  12.  Wenqing Chen, Jidong Tian, Caoyun Fan, Hao He, Yaohui Jin. Dependent Multi-Task Learning with Causal Intervention for Image Captioning[C]. IJCAI 2021: 2263-2270. (CCF A)
  13.  Wenqing Chen, Jidong Tian, Liqiang Xiao, Hao He, Yaohui Jin. Exploring Logically Dependent Multi-task Learning with Causal Inference[C]. EMNLP (1) 2020: 2213-2225. (CCF B)
  14.  Wenqing Chen, Jidong Tian, Liqiang Xiao, Hao He, Yaohui Jin. A Semantically Consistent and Syntactically Variational Encoder-Decoder Framework for Paraphrase Generation[C]. COLING 2020: 1186-1198. (CCF B)
  15.  He Chen, Wenqing Chen, Yan Song, Li Sun, Xiaoli Li. EEG Characteristics of Children with Attention-Deficit/Hyperactivity Disorder[J]. Neuroscience 406: 444-456, 2019. (SCI, IF: 3.304)
  16.  Honglun Zhang, Wenqing Chen, Jidong Tian, Hao He, Yaohui Jin. RAG: Facial Attribute Editing by Learning Residual Attributes[J]. IEEE Access 7: 83266-83276, 2019. (SCI, IF: 3.367)
  17.  Jidong Tian, Yitian Li, Wenqing Chen, Liqiang Xiao, Hao He, Yaohui Jin. Weakly Supervised Neural Symbolic Learning for Cognitive Tasks. AAAI 2022: 5888-5896. (CCF A)
  18.  Jidong Tian, YitianLi, Wenqing Chen, Liqiang Xiao, Hao He, Yaohui Jin. Diagnosing the First-Order Logical Reasoning Ability Through LogicNLI[C]. EMNLP (1) 2021: 3738-3747. (CCF B)
  19.  Liqiang Xiao, Honglun Zhang, Wenqing Chen, Yongkun Wang, Yaohui Jin. Transformable Convolutional Neural Network for Text Classification[C]. IJCAI 2018: 4496-4502. (CCF A)
  20.  Honglun Zhang, Liqiang Xiao, Wenqing Chen, Yongkun Wang, Yaohui Jin. Generative Warfare Nets: Ensemble via Adversaries and Collaborators[C]. IJCAI 2018: 3075-3081. (CCF A)
  21.  Honglun Zhang, Liqiang Xiao, Wenqing Chen, Yongkun Wang, Yaohui Jin. Multi-Task Label Embedding for Text Classification[C]. EMNLP 2018: 4545-4553. (CCF B)
  22.  Liqiang Xiao, Honglun Zhang, Wenqing Chen, Yongkun Wang, Yaohui Jin. MCapsNet: Capsule Network for Text with Multi-Task Learning[C]. EMNLP 2018: 4565-4574. (CCF B)
  23.  Liqiang Xiao, Honglun Zhang, Wenqing Chen, Yongkun Wang, Yaohui Jin. Learning What to Share: Leaky Multi-Task Network for Text Classification[C]. COLING 2018: 2055-2065. (CCF B)
  24.  Liqiang Xiao, Honglun Zhang, Wenqing Chen. Gated Multi-Task Network for Text Classification[C]. NAACL-HLT (2) 2018: 726-731. (CCF B)

 

专利

  1. 陈文清，徐奕坤，袁伟乐，郑子彬. "一种金融大模型生成文本的评测方法及装置", CN119538872B, 2025.
  2. 姜华，陈文清，田济东. "具有依赖关系的自然语言多任务建模、预测方法及系统", CN112488290B, 2021.
  3. 姜华，陈文清，田济东. "一种同义句生成方法、系统、终端及存储介质", CN112287641B, 2021.
  4. 姜华，田济东，陈文清，肖力强. "基于强化学习的级联信息提取系统及方法", CN112487811A, 2021.
  5. 金耀辉，何浩，肖力强，陈文清，田济东. "基于预训练语言模型和信息论的自动化文本摘要评测方法", CN112528598A, 2022.
  6. 金耀辉，何浩，肖力强，陈文清，田济东. "混合式文本摘要生成方法、系统、终端及存储介质", CN112464657A, 2022.
  7. 金耀辉，何浩，肖力强，陈文清，田济东. "基于语句融合的文本摘要生成方法、系统、终端及介质", CN112464658A, 2022.