Skip to content
conftrace_
2025 ICML ICML 2025

ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Hyunseok Lee, Seunghyuk Oh, Jaehyung Kim, Jinwoo Shin, Jihoon Tack

Topics

Machine Learning > Core Methods > Representation Learning Artificial Intelligence > Core AI > Large Language Models Artificial Intelligence > Core AI > Reasoning

Keywords

curriculum learning intrinsic self-correction large language model self-verification confidence-aware decoding reasoning correction
Download PDF