About me

Hi! I’m a second year CS Ph.D. student at UW-Madison advised by Prof. Sharon Li. My research interests are reliable machine learning and hallucination detection.

I’ve also worked with Prof. Philip Thomas as a Master’s student at UMass-Amherst, and with Dr. Lun-Wei Ku as a research assistant at the Natural Language Processing and Sentiment Analysis (NLPSA) Lab at Academia Sinica, Taiwan.

Publication

(conference, journal, and * denotes equal contribution)

• MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems
  Xuanming Zhang, Yuxuan Chen, Min-Hsuan Yeh, and Yixuan Li
  [paper]
  NeurIPS 2025 Spotlight

• Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment
  Min-Hsuan Yeh and Yixuan Li
  [paper] [code]
  NeurIPS 2025 Datasets and Benchmarks Track

• HalluEntity: Benchmarking and Understanding Entity-Level Hallucination Detection
  Min-Hsuan Yeh, Max Kamachee, Seongheon Park, and Yixuan Li
  [paper] [dataset]
  TMLR 2025 J2C Certification (Top 10%)

• Position: Challenges and Future Directions of Data-Centric AI Alignment
  Min-Hsuan Yeh, Jeffrey Wang, Xuefeng Du, Seongheon Park, Leitian Tao, Shawn Im, and Yixuan Li
  [paper]
  ICML 2025 Position Track

• Steer LLM Latents for Hallucination Detection
  Seongheon Park, Xuefeng Du, Min-Hsuan Yeh, Haobo Wang, and Yixuan Li
  [paper]
  ICML 2025

• COCOLOFA: A Dataset of News Comments with Common Logical Fallacies Written by LLM-Assisted Crowds
  Min-Hsuan Yeh, Ruyuan Wan, and Ting-Hao ‘Kenneth’ Huang
  [paper] [dataset]
  EMNLP 2024

• Analyzing the Relationship Between Difference and Ratio-Based Fairness Metrics
  Min-Hsuan Yeh, Blossom Metevier, Austin Hoag, and Philip Thomas
  [paper]
  FAccT 2024

• Multi-VQG: Generating Engaging Questions for Multiple Images
  Min-Hsuan Yeh, Vincent Chen, Ting-Hao ‘Kenneth’ Huang, and Lun-Wei Ku
  [paper] [dataset]
  EMNLP 2022

• Lying Through One’s Teeth: A Study on Verbal Leakage Cues
  Min-Hsuan Yeh and Lun-Wei Ku
  [paper]
  EMNLP 2021

Preprints

• LUMINA: Detecting Hallucinations in RAG System with Context–Knowledge Signals
  Min-Hsuan Yeh, Yixuan Li, and Tanwi Mallick
  [paper]

• Cognition-of-Thought Elicits Social-Aligned Reasoning in Large Language Models
  Xuanming Zhang, Yuxuan Chen, Min-Hsuan Yeh, and Yixuan Li
  [paper]

• Simulating and Understanding Deceptive Behaviors in Long-Horizon Interactions
  Yang Xu, Xuanming Zhang, Yuxuan Chen, Min-Hsuan Yeh, Jwala Dhamala, Ousmane Dia, Rahul Gupta, and Yixuan Li

Education

• Ph.D. in Computer Science, University of Wisconsin-Madison
  Advisor: Prof. Sharon Yixuan 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

• W.J. Cody Associates, Argonne National Laboratory
  Supervisor: Dr. Tanwi Mallick, May. 2025 - Jul. 2025
• Research Assistant Intern, CrowdAI Lab
  Advisor: Prof. Ting-Hao ‘Kenneth’ Huang, Jun. 2023 - Feb. 2024
• Research Assistant, NLPSA, Academia Sinica
  Advisor: Prof. Lun-Wei Ku, May 2020 - Jul. 2022

Academic Services

• Conference Reviewer: COLING’25, ICLR’25, ACL’25, ACL’24, COLING’24