Shuo Yan

My name is Shuo Yan, and I am a Ph.D. student at the University of Texas at Dallas, advised by Dr. Xiwei Tang. Before joining UT Dallas, I worked as a research assistant at The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), under the supervision of Dr. Benyou Wang and Dr. Anningzhe Gao. I am deeply grateful for the research training and mentorship I received at CUHK-Shenzhen.

My research interests lie broadly in LLM safety, reasoning, and evaluation. I am currently exploring the following topics:

LLM unlearning

• Defining principled boundaries for the knowledge to be unlearned.
• Developing unlearning methods that achieve reliable forgetting while preserving the model’s general capabilities.

LLM reasoning

• Evaluating and improving the quality of intermediate reasoning steps.
• Building game-playing agents capable of competing with highly skilled human players—a topic of both research and personal interest.

LLM evaluation

• Evaluating the reliability of code, research artifacts, and software systems generated by LLMs and coding agents, particularly for non-expert users and in emerging research areas where established evaluation criteria may not yet exist.

Feel free to reach out if you are interested in discussing these topics or exploring potential collaborations.