Inject a Turn, Not a Token: Learning Where to Redirect LLM Reasoning for Self-Correction

Paper recorded by Signals 4 on 2026-10-09 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-09 on arXiv · recorded by Signals 4 on 2026-10-12

Category: cs.CL · 自然语言处理 · first seen 2026-10-12

Abstract

Large language models struggle to reliably identify and correct errors in their own reasoning. Unlike prior training-based approaches that fine-tune an LLM to generate revisions or feedback, we learn where to intervene in failed rollouts and determine how to redirect them. To choose where to intervene, we train a 130K-parameter MLP head on a frozen encoder using only final-answer correctness. For

Read on arXiv →