Wooseok Seo

Hi! I am a 1st year PhD student at MIRLAB, part of the School of Computing at Yonsei University, advised by Prof. Youngjae Yu.

My research interest is in building trustworthy and interpretable AI Agents. Recently, I am specifically interested in:

• Evaluating and Mitigating Hallucinations of Language Models: Is hallucination inevitable for LLMs? How can we develop truthful models and correctly evaluate them?
• Interpreting and Monitoring Model Reasoning: Are language models producing faithful reasoning? If so, how can we leverage this to better understand and improve them? If not, how should we build more faithful models?

I am also interested in leveraging models to evaluate or improve other models, or utilizing them to augment human capabilities. Please reach me via email to chat about research! 🤗

Email  /  GitHub  /  Google Scholar  /  LinkedIn  /  Twitter

Research

Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers

V.I.P. : Iterative Online Preference Distillation for Efficient Video Diffusion Models

Layout-and-Retouch: A Dual-stage Framework for Improving Diversity in Personalized Image Generation

Academic Services

Reviewer

• COLM, 2025

Design and source code from Jon Barron