CV
Education
- B.S. in School of Mechanical Science and Engineering, Huazhong University of Science and Technology, 2015-2019
- Ph.D in School of Computer Science and Technology, Huazhong University of Science and Technology, advised by Ruixuan Li, 2019-2024
Work experience
- 2024-: Postdoc in Huazhong University of Science and Technology
Research Interests
My research primarily focuses on explainable artificial intelligence, utilizing theoretical tools such as causality, probabilistic graphical models, and information theory. I have published a series of papers in the field of explainable AI, including top-tier machine learning conferences such as NeurIPS, KDD, and ACL. The objective of my work is to identify simple and principled approaches that are both practical and scalable.
Currently, I am interested in various research areas related to large language models, especially data quality and interpretability.
Publications
Notes: “$\Delta$” means primarily recommended for reading.
Wei Liu, Zhiying Deng, Zhongyu Niu, Jun Wang, Haozhao Wang, YuanKai Zhang, Ruixuan Li. $\Delta$“Is the MMI Criterion Necessary for Interpretability? Degenerating Non-causal Features to Plain Noise”. In NeurIPS 2024.
Wei Liu, Haozhao Wang, Jun Wang, Zhiying Deng, YuanKai Zhang, Cheng Wang, Ruixuan Li. “Enhancing the Rationale-Input Alignment for Self-explaining Rationalization”. In ICDE 2024.
Jie Han, Yixiong Zou, Haozhao Wang, Jun Wang,Wei Liu, Yao Wu, Tao Zhang, Ruixuan Li. “Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Filling”. In AAAI 2024.
Wei Liu, Jun Wang, Haozhao Wang, Ruixuan Li, Zhiying Deng, YuanKai Zhang, Yang Qiu. $\Delta$“D-Separation for Causal Self-Explanation”. In NeurIPS 2023.
Wei Liu, Jun Wang, Haozhao Wang, Ruixuan Li, Yang Qiu, YuanKai Zhang, Jie Han, Yixiong Zou. $\Delta$“Decoupled Rationalization with Asymmetric Learning Rates: A Flexible Lipschitz Restraint”. In KDD 2023.
Wei Liu, Haozhao Wang, Jun Wang, Ruixuan Li, Xinyang Li, YuanKai Zhang, Yang Qiu. “MGR: Multi-generator Based Rationalization”. In ACL 2023 (oral presentation).
Zhiying Deng, Jianjun Li, Zhiqiang Guo, Wei Liu, Li Zou, Guohui Li. “Multi-view Multi-aspect Neural Networks for Next-basket Recommendation”. In SIGIR 2023.
Wei Liu, Haozhao Wang, Jun Wang, Ruixuan Li, Chao Yue, Yuankai Zhang. “FR: Folded Rationalization with a Unified Encoder”. In NeurIPS 2022.