Weixiang Zhao 赵伟翔
Hello, I am a Ph.D. student at the Research Center for Social Computing and Information Retrieval (SCIR) at Harbin Institute of Technology (HIT), China. I am advised by Prof. Yanyan Zhao and Prof. Bing Qin. And I also collaborate closely with Prof. Wanxiang Che. My research focuses on emotional dialogue systems, sentiment analysis, continual learning, and the alignment of large language models.
Education
- Sept 2021 - Jul 2026 (Expected). Ph.D student in SCIR, Dept. of Computer Science and Technology, Harbin Institute of Technology. Advisor: Prof. Yanyan Zhao and Prof. Bing Qin.
- Sept 2017 - Jul 2021. B.Sc. in Dept. of Computer Science and Engineering, Northeastern University.
Main Publications
Continual Learning of LLMs
- Weixiang Zhao, Shilong Wang, Yulin Hu, Yanyan Zhao, Bing Qin, Xuanyu Zhang, Qing Yang, Dongliang Xu, Wanxiang Che. SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models. ACL 2024 (Main). [paper] [repo]
- Weixiang Zhao, Zhuojun Li, Shilong Wang, Yang Wang, Yulin Hu, Yanyan Zhao, Chen Wei, Bing Qin. Both Matter: Enhancing the Emotional Intelligence of Large Language Models without Compromising the General Intelligence. ACL 2024 (Findings). [paper]
- Weixiang Zhao, Yulin Hu, Jiahe Guo, Xingyu Sui, Tongtong Wu, Yang Deng, Yanyan Zhao, Bing Qin, Wanxiang Che, Ting Liu. Lens: Rethinking Multilingual Enhancement for Large Language Models. arXiv:2410.04407. [paper] [repo]
Alignment of LLMs
- Weixiang Zhao˟, Yulin Hu˟, Yang Deng, Jiahe Guo, Xingyu Sui, Xinyang Han, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu. Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs. arXiv:2502.20968. [paper]
- Weixiang Zhao, Yulin Hu, Zhuojun Li, Yang Deng, Jiahe Guo, Xingyu Sui, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu. Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching. arXiv:2405.13820. [paper]
- Weixiang Zhao, Yulin Hu, Xingyu Sui, Zhuojun Li, Yang Deng, Yanyan Zhao, Bing Qin, Wanxiang Che. The Gains Do not Make Up for the Losses: A Comprehensive Evaluation for Safety Alignment of Large Language Models via Machine Unlearning. Frontiers of Computer Science.
Emotional Dialogue Systems
- Weixiang Zhao, Shilong Wang, Yanpeng Tong, Xin Lu, Zhuojun Li, Yanyan Zhao, Chenxue Wang, Tian Zheng, Bing Qin. A Parental Emotion Coaching Dialogue Assistant for Better Parent-Child Interaction. SCIENCE CHINA Information Sciences.
- Weixiang Zhao, Yanyan Zhao, Xin Lu, Bing Qin. Don’t Lose Yourself! Empathetic Response Generation via Explicit Self-Other Awareness. ACL 2023 (Findings). [paper] [repo]
- Weixiang Zhao, Yanyan Zhao, Shilong Wang, Bing Qin. TransESC: Smoothing Emotional Support Conversation via Turn-Level State Transition. ACL 2023 (Findings). [paper] [repo]
- Weixiang Zhao, Yanyan Zhao, Zhuojun Li, Bing Qin. Knowledge-Bridged Causal Interaction Network for Causal Emotion Entailment. AAAI 2023. [paper] [repo]
- Weixiang Zhao, Yanyan Zhao, Xin Lu, Bing Qin. CauAIN: Causal Aware Interaction Network for Emotion Recognition in Conversations. IJCAI 2022. [paper] [repo]
- Weixiang Zhao, Yanyan Zhao, Bing Qin. MuCDN: Mutual Conversational Detachment Network for Emotion Recognition in Multi-Party Conversations. COLING 2022. [paper] [repo]
- Weixiang Zhao, Yanyan Zhao, Xin Lu, Shilong Wang, Yanpeng Tong, Bing Qin. Is ChatGPT Equipped with Emotional Dialogue Capabilities? arXiv:2304.09582. [paper]
- Xin Lu, Weixiang Zhao, Yanyan Zhao, Bing Qin, Zhentao Zhang, Junjie Wen. A Topic-Enhanced Approach for Emotion Distribution Forecasting in Conversations. ICASSP 2023. [paper] [repo]
- Yanyan Zhao, Xin Lu, Weixiang Zhao, Yijian Tian, Bing Qin. Review of Emotional Dialogue Techniques. Ruan Jian Xue Bao/Journal of Software 2022 (in Chinese). [paper]
Sentiment Analysis
- Weixiang Zhao, Yanyan Zhao, Xin Lu, Bing Qin. An Aspect-Centralized Graph Convolutional Network for Aspect-based Sentiment Classification. NLPCC 2021. [paper] [repo]
- Wenjia Yi, Yanyan Zhao, Jianhua Yuan, Weixiang Zhao, Bing Qin Improving Affective Event Classification with Multi-Perspective Knowledge Injection. CCL 2023. [paper]
Experiences
- Oct 2024 - Now. Visiting Student. National University of Singapore, Singapore. Supervisor: Prof. Tat-Seng Chua.
- Nov 2023 - Sept 2024. Research Intern. Du Xiaoman (Beijing) Science Technology Co., Ltd, Beijing, China. Supervisor: Dr. Qing Yang.
- Nov 2020 - Mar 2021. Intern. ByteDance, Beijing, China.
- Jan 2020 - Feb 2020. Research Intern. Peer Logic Lab, North Carolina State University, Raleigh, The U.S. Supervisor: Dr. Yunkai Xiao and Prof. Ed Gehringer.
Selected Awards and Honors
- National Scholarship, Harbin Institute of Technology, 2024
- Outstanding Student Paper, Harbin Institute of Technology, 2022
- Second-Class Fresh-PhD Fellowship, Harbin Institute of Technology, 2021
- Excellent Thesis, Northeastern University, 2021
- National Scholarship, Northeastern University, 2018&2019