Yifei is a (𝓍-𝟤𝟢𝟤𝟥)-Year Ph.D. student in Computer and Information Science (CIS) at University of Pennsylvania. He is grateful to be advised by Prof. Mark Yatskar, affiliated with Penn NLP.
His research spans LLMs and multimodality, with a primary focus on:
- • scalable evaluation and reward
- • deep research agents
- • applications and utilities in expert-level AI and scientific discovery
In the past, he has also worked with Prof. Lyle Ungar, Prof. João Sedoc, and Prof. Chris Callison-Burch, on fairness, reasoning, and zero-shot learning of NLP and multimodal. He TA'ed in ML / DL / NLP courses, and earned Outstanding Teaching Award. He has background in Computer Science, Mathematics, and Business.
Selected Works
ResearchQA: Evaluating Scholarly Question Answering at Scale Across 75 Fields with Survey-Mined Questions and Rubrics
Li S. Yifei *, Allen Chang *, Chaitanya Malaviya, Mark Yatskar
ResearchQA proposes a scalable evaluation framework for scholarly long-form question answering via data synthesis, benchmarking frontier LLM systems including deep researches by ensembled LLM judges. By distilling survey papers, it yields 21K queries and 160K rubric items across 75 research fields, which are validated by 31 Ph.D. annotators.