I am a final-year computer science Ph.D. candidate at University of Toronto in the Natural Language Processing Group. I am interested in Large Language Models (LLM) and their applications in Natural Language Processing (NLP).

My current research is focused on developing interpretable and efficient methods of aligning LLMs with human values to improve their safety, trustworthiness and transparency. I am particularly interested in understanding and mitigating undesirable LLM outputs including harmful content, non-factual hallucinations, and private information. I was fortunate to have the opportunity of interning at Meta AI (FAIR).

During my PhD, I also studied computational models for generating creative language use such as metaphor and idiom.

For more information, you can find my CV here.

Contact: jadeleiyu [at] cs [dot] toronto [dot] edu