conftrace_

confidence-aware reasoning

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

ppo training (1) reasoning capabilities (1) stem reasoning (1) large language model (1) confidence estimation (1) chain-of-thought reasoning (1) reward modeling (1) reinforcement learning (1)

Papers

Beyond Correctness: Confidence-Aware Reward Modeling for Enhancing Large Language Model Reasoning EMNLP 2025