Rethinking Fine-Tuning when Scaling Test-Time Compute: Limiting Confidence Improves Mathematical Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Feng, Raventos, Allan, Cheng, Nan, Ganguli, Surya, Druckmann, Shaul
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!