Yea Eun Kwon

Yeaeun Kwon is a PhD student in the College of Information Science at the University of Arizona. Her research interests center on AI alignment and trustworthiness, with a particular focus on bias in large language models (LLMs) as a critical barrier to building safe and reliable AI systems. She investigates how LLMs reflect and reproduce social dynamics embedded in society and how they exhibit biases that parallel human cognitive and social biases surfacing in natural language, treating these behaviors as concrete, measurable instances of misalignment between model outputs and human values.

She aims to develop methods that make LLMs more aligned, transparent and trustworthy for human-AI interaction, while also examining the broader societal implications of AI.