Post-Training Shifts Confidence: A Three-Stage Analysis of How SFT, RL, and OPD Shape Pre-, Intra-, and Post-CoT Calibration
Large language models have made strong reasoning gains through supervised fine-tuning, reinforcement learning, and on-policy distillation, yet these post-training methods are usually evaluated only by final-answer accuracy. We study how they reshape confidence during reasoning. We introduce a three-stage calibration framework that evaluates confidence before, during, and after chain-of-thought generation, corresponding to difficulty estimation, early termination, and answer aggregation. Through a controlled comparison on mathematical reasoning benchmarks, we find that OPD provides the most use
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 53%New benchmark exposes reasoning gaps in top models →
- FuzzyOverlapping authors or contributors · 62%hiyouga/LlamaFactory →
“Shared author/contributor keys: lin”
- FuzzyOverlapping authors or contributors · 62%Zeyi-Lin/HivisionIDPhotos →
“Shared author/contributor keys: lin”
- LinkedLinked via arxiv author · 85%Shuhao Li →
“Post-Training Shifts Confidence: A Three-Stage Analysis of How SFT, RL, and OPD Shape Pre-, Intra-, and Post-CoT Calibra”
- LinkedLinked via arxiv author · 85%Guodong Du →
“Post-Training Shifts Confidence: A Three-Stage Analysis of How SFT, RL, and OPD Shape Pre-, Intra-, and Post-CoT Calibra”
- LinkedLinked via arxiv author · 85%Anhao Zhao →
“Post-Training Shifts Confidence: A Three-Stage Analysis of How SFT, RL, and OPD Shape Pre-, Intra-, and Post-CoT Calibra”
- LinkedLinked via arxiv author · 85%Wanyu Lin →
“Post-Training Shifts Confidence: A Three-Stage Analysis of How SFT, RL, and OPD Shape Pre-, Intra-, and Post-CoT Calibra”
- LinkedLinked via arxiv author · 85%Tianyu Yuan →
“Post-Training Shifts Confidence: A Three-Stage Analysis of How SFT, RL, and OPD Shape Pre-, Intra-, and Post-CoT Calibra”