I am now a PhD student (2022-) in Computer Science and Technology at Shanxi University, supervised by Prof. Ru Li. Meanwhile, I am co-supervised by Prof. Xiaoli Li, who is affiliated with the Institute for Infocomm Research at A*Star, Singapore. Before that, I received my B.S. degree from Shanxi University in 2020, majoring in computer science and technology.
My research interests focus on explainable natural language processing, including explainable probing, rationalization, and reasoning. I am also interested in explicit knowledge and implicit knowledge, such as FrameNet KBs and Parameterized PLMs. Feel free to contact me by email if you are interested in discussing or collaborating with me. It has been attented times.
🔥 News
- 2025.01: One paper on Explainable Knowledge Probing is accepted in DASFAA2025, a long oral presentation.
- 2024.11: One paper on Explainable Multi-hop Reasoning is accepted in COLING2025.
- 2024.08: We attend the 2024 Annual Conference of the ACL in Bangkok, Thailand.
- 2024.05: One paper on Self-explaining Rationalization is accepted in ACL2024.
- 2023.04: One Journal paper on FrameNet Knowledge is accepted on MIR2024.
- 2022.10: We share our tutorial on winning the championship on CCL2022.
- 2022.09: 🏆 We get the First Prize on CMRC2022 (the 1st rank) in the 21st China National Conference on Computational Linguistics.
- 2022.05: Two Journal papers on Machine Reading Comprehension are accepted to the Journal of Chinese Information Processing.
- 2021.05: One paper on Explainable Evaluation is accepted in Findings of ACL2021.
📝 Selected Publications
(* = equal contribution)
Explaining Black-box Language Models with Knowledge Probing Systems: A Post-hoc Explanation Perspective (A long oral presentation)
Yunxiao Zhao, Hao Xu, Zhiqiang Wang, Xiaoli Li, Jiye Liang, Ru Li.
- Pre-trained Language Models (PLMs) are trained on large amounts of unlabeled data, and they exhibit remarkable reasoning skills. However, the trustworthiness challenges have become increasingly evident. To alleviate this problem, we propose a novel knowledge-guided probing approach called KnowProb in a post-hoc explanation way, which aims to probe whether black-box PLMs understand implicit knowledge beyond the given text, rather than focusing only on the surface-level content of the text.
Hao Xu*, Yunxiao Zhao*, Jiayang Zhang, Zhiqiang Wang, Ru Li.
- Explainable multi-hop question answering aims to utilize multi-source intensive documents retrieved to derive the answer. However, it is challenging to model the importance of knowledge retrieved. In this paper, we propose LOG, a novel optimized retrieval method to discover more beneficial knowledge from a local-to-global perspective, facilitating multi-hop reasoning, notably for long-chain reasoning.
AGR: Reinforced Causal Agent Guided Self-explaining Rationalization
Yunxiao Zhao, Zhiqiang Wang, Xiaoli Li, Jiye Liang, Ru Li.
- We propose a novel approach AGR (Agent-Guided Rationalization), guiding the next action of the model based on its current training state. We introduce causal intervention calculus to quantify the causal effects inherent during rationale training, and utilize the reinforcement learning process to refine their learning bias.
A comprehensive Overview of CFN From a Commonsense Perspective
Ru Li, Yunxiao Zhao, Zhiqiang Wang, Xuefeng Su, Shaoru Guo, Yong Guan, Xiaoqi Han, Hongyan Zhao.
- We conduct a comprehensive overview of Chinese FrameNet from a commonsense perspective, covering topics such as scenario commonsense representation, Chinese FrameNet resources, and its applications. We also summarize recent breakthroughs and identify future research directions.
🎖 Honors and Awards
- 2024.06 The First Class Award Scholarship of the Graduate School, Shanxi University, in 2024.
- 2023.06 The First Class Award Scholarship of the Graduate School, Shanxi University, in 2023.
- 2022.10 The Champion Award on CMRC2022, Chinese Information Processing Society of China (CIPS), in 2022.
- 2022.06 The First Class Award Scholarship of the Graduate School, Shanxi University, in 2022.
- 2021.06 The First Class Award Scholarship of the Graduate School, Shanxi University, in 2021.
- 2021.05 The Outstanding Graduate Student.
📖 Educations
- 2022.09 - 2026.06 (now), School of Computer and Information Technology, Shanxi University. Ph.D. Student.
- 2020.09 - 2022.06, School of Computer and Information Technology, Shanxi University. Master Student.
- 2016.09 - 2020.06, School of Computer and Information Technology, Shanxi University. Undergraduate.
💬 Invited Talks
💻 Internships
- 2019.12 - 2020.06, Taiyuan, China.