李霏
开通时间：..
最后更新时间：..
武汉大学国家网络安全学院副教授，博/硕士生导师，中国计算机学会、中国中文信息学会、中国人工智能学会会员，中国中文信息学会情感计算专委会、社会媒体处理专委会、大模型与生成专委会委员。主要从事自然语言处理、大模型安全、社会计算、情感分析、信息抽取等方向的研究。论文方面，在相关方向的期刊和会议上发表论文100余篇。近年来主持和参与国家重点研发计划、国家科技重大专项、中国计算机学会-蚂蚁科研基金等多个项目。教学方面，主讲本科生和研究生的《自然语言处理》、《AI程序设计实训》等课程。
实验室常年招收硕士研究生、博士研究生，欢迎对以上方向感兴趣的同学通过邮箱lifei_csnlp@whu.edu.cn联系我
语言和认知计算实验室主页： http://lacc.whu.edu.cn
在研项目
[1] 大模型在国际金融场景下对于低资源语言的持续学习和架构拓展机制研究，中国计算机学会-蚂蚁科研基金，主持，在研
[2] 大模型遗忘学习方法研究，主持，在研
[3] 新一代人工智能国家科技重大专项，多模态大模型内生安全关键技术与示范应用---多模态多语言大模型自进化价值对齐，参与，在研
[4] 国家重点研发计划，多语言多模态科技情报数据内容识别技术研究，主持，在研
代表性论文（详细列表 https://scholar.google.com/citations?user=AoMmysMAAAAJ&hl=zh-CN ）
Zheng, Li, Xin Zhang, Shuyi He, Fei Li, Chong Teng, Jiang-Ming Yang, Donghong Ji, and Zhuang Li. "Are Emotion and Rhetoric Neurons in LLM? Neuron Recognition and Adaptive Masking for Emotion-Rhetoric Prediction Steering." In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 4206-4216. 2026.
Xue, Yingjie, Xingyou Xia, Jun Zhang, Yunbo Cao, Dengpan Ye, Guotong Geng, and Fei Li. "SHARP: Self-adaptive Harmful Category-aware Prompt Generation for Black-box Jailbreaking." In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 45291-45303. 2026.
Zheng, Li, Yanyi Luo, Hao Fei, Yuzhe Ding, Yujie Huang, Fei Li, Chong Teng, and Donghong Ji. "Dynamic Emotion and Personality Profiling for Multimodal Deception Detection." In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 3930-3940. 2026.
Wang, Zixuan, Yun Hu, Mengying Yuan, Kang He, Fei Li, Huisheng Ma, Donghong Ji, and Chong Teng. "CodEOE: A Benchmark for Jointly Extracting Cross-Document Events and Opinions From Social Media." In ICASSP 2026-2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 18992-18996. IEEE, 2026.
Huang, Yujie, Li Zheng, Qiujing Xu, Xu Han, Jinbo Li, Changpeng Huan, E. Cheng, Fei Li, Chong Teng, and Donghong Ji. "Nested Opinion Sextuple Extraction: Design of the Task, Dataset and Extraction Model." IEEE Transactions on Affective Computing (2026).
Li Zheng, Sihang Wang, Hao Fei, Zuquan Peng, Fei Li, Jianming Fu, Chong Teng, and Donghong Ji. 2025. Enhancing Hyperbole and Metaphor Detection with Their Bidirectional Dynamic Interaction and Emotion Knowledge. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 489–499, Vienna, Austria. Association for Computational Linguistics.
Wu, X., Mao, X., Li, F., Zhang, X., Zhang, X., Zhou, J., ... & Li, Z. (2025). EVOREFUSE: Evolutionary Prompt Optimization for Evaluation and Mitigation of LLM Over-Refusal to Pseudo-Malicious Instructions. NeurIPS.
Xiaorui Wu, Xiaofeng Mao, Fei Li, Xin Zhang, Xuanhong Li, Chong Teng, Donghong Ji, and Zhuang Li. 2025. TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data Synthesis. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15077–15099, Vienna, Austria. Association for Computational Linguistics.
Liu J, Li B, Yang X, et al. M 3 D: a Multimodal, Multilingual and Multitask Dataset for Grounded Document-level Information Extraction[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025.
Zheng L, Fei H, Chen L, et al. STPar: A Structure-Aware Triaffine Parser for Screenplay Character Coreference Resolution[J]. Transactions of the Association for Computational Linguistics, 2025, 13: 923-937.
获奖
2026年，中国大学生计算机设计大赛中南地区赛一等奖《AlertClaw--基于微信ClawBot与智能体论坛的实时舆情监测系统》，指导教师
2026年，中国大学生计算机设计大赛中南地区赛一等奖《万象智体--多智能体协同的跨模态舆情分析系统》，指导教师
2025年，EMNLP Outstanding Paper Award，DiscoSG: Towards Discourse-Level Text Scene Graph Parsing throughIterative Graph Refinement
2025年，第一届全国大学生人工智能安全竞赛，二等奖，PrivaGuard:基于随机噪声定向注入的大模型隐私保护机制，指导教师
2025年，中国大学生计算机设计大赛, 国赛二等奖,智模万象--基于微调DeepSeek的多模态舆情洞察系统，指导教师
2025年，“自强杯”大学生课外学术科技作品竞赛，笔韵智枢—大数据驱动的智能一体化字体创作引擎，指导教师
