Awarded the Shimo Zhong Scholarship (the highest honor in the Department of Computer Science at Tsinghua University) and the Siebel Scholars Award; participated in multiple competitions and won prizes, such as first place in the COLIEE 2024 Legal Case Retrieval Task and first place in the COLIEE 2023 Legal Case Retrieval Task; published several papers, e.g., 'Calibraeval: Calibrating prediction distribution to mitigate selection bias in LLMs-as-judges' (ACL 2025 main).
Research Experience
As a Ph.D. student at THUIR lab, focusing on research related to large language models, including post-training strategies, vertical knowledge injection, and efficient reinforcement learning algorithms.
Education
Sep 2022 - present: Ph.D. student at the Department of Computer Science and Technology, Tsinghua University, supervised by Prof. Yiqun Liu; Sep 2018 - Jun 2022: B.S. in Electronic Engineering, Beihang University; Sep 2019 - Jun 2022: Minor in Mathematics, Beihang University.
Background
Research interests include post-training strategies of large language models, vertical knowledge injection, efficient reinforcement learning algorithms, reward modeling and the application of LLM as a judge, performance evaluation, model evolution, and bias mitigation. Also deeply interested in complex problem decomposition and solving, multi-agent collaboration, retrieval-augmented generation (RAG), and information retrieval.
Miscellany
Personal interests include collaborating and exchanging ideas with researchers, exploring the application of large language models in areas like complex problem decomposition and solving, multi-agent collaboration, retrieval-augmented generation (RAG), and information retrieval.