评分 6 · 来源：cs.AI updates on arXiv.org · 发布于 2026-04-14
评分依据：PRM efficiency is a relevant topic for LLM training. Contrastive MI approach offers moderate novelty over existing MC estimation methods.
Efficient Process Reward Modeling via Contrastive Mutual Information
发布
采集
学术前沿 6.0 分
— PRM efficiency is a relevant topic for LLM training. Contrastive MI approach offers moderate novelty over existing MC estimation methods.