Wen-Kai Li

Wenkai Li is a Research Scientist at Fujitsu Research of America and a master's student in the Language Technologies Institute at Carnegie Mellon University. His research focuses on AI safety, mechanistic interpretability, LLM reasoning and post-training, and human-centered AI. He is known for his work on embedding realistic human personality traits into large language models through supervised fine-tuning and preference optimization, notably through the BIG5-CHAT dataset, as well as contributions to automated model documentation and multilingual AI terminology translation.