Bowen Yi
Papers
1
Total Citations
2
H-Index
1
About
Bowen Yi is an emerging researcher working at the intersection of natural language processing, human-computer interaction, and conversational AI. His work focuses critically on the reliability and validity of using large language models (LLMs) as proxies for human participants in dialogue research — a question with significant implications for how the research community designs and evaluates studies going forward. Yi's most notable contribution to date, "Real or Robotic? Assessing Whether LLMs Accurately Simulate Qualities of Human Responses in Dialogue" (2024), tackles a pressing methodological challenge: as researchers increasingly turn to LLMs to reduce the cost and complexity of collecting human dialogue data, how trustworthy are these simulations? By developing dedicated datasets and evaluation frameworks, Yi's work provides the field with concrete tools to interrogate this assumption rather than accept it uncritically. Though early in his research career — with his work already accumulating citations — Yi is addressing a timely and consequential problem. As LLM-based simulation becomes more widespread in NLP research pipelines, his contributions help ensure the field maintains scientific rigor. Researchers and students working on dialogue systems, crowdsourcing methodology, or human-AI interaction will find his work both practically relevant and thought-provoking.
Research Focus
Key Achievements
Top Papers
- 1