作者位次 #3/4NeurIPS 2026Poster· Deep Learning / Generative Models and Autoencoders
Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-Training
Anas Barakat · Souradip Chakraborty · Khushbu Pahwa · Amrit Singh Bedi
强化学习与后训练OpenReview