Hi! I am Tianhe Lin, a second-year master’s student at School of Data Science, Fudan University. I’m a member of Knowledge Works Lab led by Prof. Yanghua Xiao and Prof. Deqing Yang. I received my bachelor’s degree in Artificial Intelligence from Fudan University in June 2024.

I am fortunate to collaborate with researchers from both academia and industry. Previously, I interned at Meituan LongCat LLM Team, where I focused on research on LLM-as-a-judge ‍⚖️, and developed several generative judge models 🤖 for open-ended, challenging and automatic evaluation of post-trained LLMs on how they align to human preference.

Research Interests: I have a broad interest in Natural Language Processing. Specifically, I am interested in (but are not limited to):

• Reasoning Capabilities: Interpreting and enhancing the reasoning abilities of LLMs.
• Evaluation: Automatic and reliable evaluation of LLMs, e.g., LLM-as-a-judge.

Besides research, I enjoy cycling🚴‍♀️, marathon🏃‍♂️ and badminton🏸.

Feel free to contact me if you are interested in my work or want to discuss a potential collaboration!

🥳 News

May, 2025   One Paper is accepted to ACL 2025! See you in Vienna!

Mar, 2025   New paper on (implicit) reasoning mechanism of (large) language models!

Mar, 2025   Personal Homepage is now available!