Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents
Changdae Oh, Wendi Li, Seongheon Park, Samuel Yeh, Tanwi Mallick, and Sharon Li
Under Review, 2026
Publications
You can also find my articles on my Google Scholar profile.
Tracing Agentic Failure from the Flow of Success
Samuel Yeh, Yiwen Zhu, Shaleen Deep, and Sharon Li
Under Review, 2026
Multi-Head Recurrent Memory Agents
Jiatong Li, Samuel Yeh, and Sharon Li
Under Review, 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
Under Review, 2026
DECOR: Auditing LLM Deception via Information Manipulation Theory
Linyue Cai, Samuel Yeh, Jwala Dhamala, Rahul Gupta, and Sharon Li
Under Review, 2026
How Retrieved Context Shapes Internal Representations in RAG
Samuel Yeh and Sharon Li
The 64th Annual Meeting of the Association for Computational Linguistics, 2026
Towards Reducible Uncertainty Modeling for Reliable Large Language Model Agents
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, 2026
LUMINA: Detecting Hallucinations in RAG System with Context–Knowledge Signals
Samuel Yeh, Sharon Li, and Tanwi Mallick
The Fourteenth International Conference on Learning Representations, 2026
[code]
Simulating and Understanding Deceptive Behaviors in Long-Horizon Interactions
Yang Xu, Xuanming Zhang, Samuel Yeh, Jwala Dhamala, Ousmane Dia, Rahul Gupta, and Sharon Li
The Fourteenth International Conference on Learning Representations, 2026
Cognition-of-Thought Elicits Social-Aligned Reasoning in Large Language Models
Xuanming Zhang, Yuxuan Chen, Min-Hsuan Yeh, and Yixuan Li
Socially Responsible and Trustworthy Foundation Models at NeurIPS 2025, 2025
MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems
Xuanming Zhang, Yuxuan Chen, Samuel Yeh, and Sharon Li
Advances in Neural Information Processing Systems (NeurIPS) Spotlight, 2025
[code]
Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment
Samuel Yeh and Sharon Li
Advances in Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track, 2025
[code]
HalluEntity: Benchmarking and Understanding Entity-Level Hallucination Detection
Min-Hsuan Yeh, Max Kamachee, Seongheon Park, and Yixuan Li
Transactions on Machine Learning Research (TMLR) J2C Certification, 2025
[dataset]
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
International Conference on Machine Learning (ICML) Position Track, 2025
Steer LLM Latents for Hallucination Detection
Seongheon Park, Xuefeng Du, Min-Hsuan Yeh, Haobo Wang, and Yixuan Li
International Conference on Machine Learning (ICML), 2025
[code]
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
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024
[dataset]
Analyzing the Relationship Between Difference and Ratio-Based Fairness Metrics
Min-Hsuan Yeh, Blossom Metevier, Austin Hoag, and Philip Thomas
ACM Conference on Fairness, Accountability, and Transparency (FAccT), 2024
Multi-VQG: Generating Engaging Questions for Multiple Images
Min-Hsuan Yeh, Vincent Chen, Ting-Hao Huang, and Lun-Wei Ku
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022
[dataset]
Lying Through One’s Teeth: A Study on Verbal Leakage Cues
Min-Hsuan Yeh and Lun-Wei Ku
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021