works on
chain-of-thought reasoning 1confidence calibration 1large language models 1post-training methods 1reinforcement learning 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.CL2026

Post-Training Shifts Confidence: A Three-Stage Analysis of How SFT, RL, and OPD Shape CoT Calibration

Shuhao Li, Guodong Du, Anhao Zhao +3

The paper examines how supervised fine-tuning, reinforcement learning, and on‑policy distillation affect confidence estimates of large language models during chain‑of‑thought reaso…