I am a 3rd-year Ph.D. student at the University of Wisconsin-Madison Computer Sciences department. I am advised by Professor Sharon Li.

My research centers on developing reliable and trustworthy AI systems, with a particular focus on data-centric alignment and hallucination detection in large language models (LLMs). I investigate how preference feedback data influence alignment, and I design benchmarks and methodologies to detect hallucinations in challenging scenarios—such as long-form text generation and retrieval-augmented generation.

Research Interests

• Reliable Machine Learning
• Hallucination Detection
• Data-centric AI Alignment

📌 I am actively seeking internship opportunities for 2027 Summer!

📢 News [09.24.2026] Four of my papers (Failure attribution for AI agents, Multi-head recurrent memory agents, Progress advantage for agents, and VLA runtime monitoring) have been accepted at NeurIPS 2026! 🎉

[04.07.2026] Two of my papers (Analysis of RAG Systems and Uncertainty Quantification for Agentic Systems) have been accepted at ACL 2026! 🎉

Selected Publications

Full list of publications in Publications, and see Google Scholar for the most updated list.

• Tracing Agentic Failure from the Flow of Success
  Samuel Yeh, Yiwen Zhu, Shaleen Deep, and Sharon Li
  Advances in Neural Information Processing Systems (NeurIPS), 2026
• Multi-Head Recurrent Memory Agents
  Jiatong Li, Samuel Yeh, and Sharon Li
  Advances in Neural Information Processing Systems (NeurIPS), 2026
• Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents
  Changdae Oh, Wendi Li, Seongheon Park, Samuel Yeh, Tanwi Mallick, and Sharon Li
  Advances in Neural Information Processing Systems (NeurIPS), 2026
• Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring
  Seongheon Park, Wendi Li, Changdae Oh, Samuel Yeh, Zsolt Kira, Michael Hagenow, and Sharon Li
  Advances in Neural Information Processing Systems (NeurIPS), 2026
• How Retrieved Context Shapes Internal Representations in RAG
  Samuel Yeh and Sharon Li
  Findings of the Association for Computational Linguistics: ACL 2026 (ACL Findings), 2026
• Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities
  Changdae Oh, Seongheon Park, To Eun Kim, Jiatong Li, Wendi Li, Samuel Yeh, Xuefeng Du, Hamed Hassani, Paul Bogdan, Dawn Song, Sharon Li
  The 64th Annual Meeting of the Association for Computational Linguistics (ACL), 2026

Education

• Ph.D. in Computer Science, University of Wisconsin-Madison
  Advisor: Prof. Sharon Li
  Sep. 2024 - Present

• M.S. in Computer Science, University of Massachusetts-Amherst
  Sep. 2022 - May 2024

• B.S. in Computer Science, National Taiwan University of Science and Technology
  Sep. 2016 - Jan. 2020

Experience

• Research Assistant, Microsoft Research
  Supervisor: Shaleen Deep, Jan. 2026 - May. 2026

• W.J. Cody Associates, Argonne National Laboratory
  Supervisor: Dr. Tanwi Mallick, May. 2025 - Jul. 2025

• Research Assistant Intern, CrowdAI Lab, Penn State University
  Supervisor: Prof. Ting-Hao ‘Kenneth’ Huang, Jun. 2023 - Feb. 2024

• Research Assistant, NLPSA, Academia Sinica
  Supervisor: Prof. Lun-Wei Ku, May 2020 - Jul. 2022

Academic Services

Conference Reviewer

• NeurIPS: ‘26
• ICLR: ‘25, ‘26
• ACL: ‘24, ‘25, ‘26
• COLING: ‘24, ‘25

Misc.

I am a ramen and coffee lover.

Hobbies:

• Roasting coffee
• Making pour-over coffee
• Crocheting
• Cooking
• Biking
• Badminton
• Maintaining my wife’s website