by Zimin Zhang Papers
2 papers found
Conference
How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence
Hongzhe Du, Weikai Li, Min Cai et al.
COLM 2025paperarXiv:2504.02904
5
citations
The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning
Shivam Agarwal, Zimin Zhang, Lifan Yuan et al.
NEURIPS 2025arXiv:2505.15134
102
citations