Structure Enables Effective Self-Localization of Errors in LLMs

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Samanta, Ankur, Magesh, Akshayaa, Jain, Ayush, Asadi, Kavosh, Yu, Youliang, Jiang, Daniel, Vidolov, Boris, Hassani, Kaveh, Sajda, Paul, Bhandari, Jalaj, Efroni, Yonathan
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918533043060736
author Samanta, Ankur
Magesh, Akshayaa
Jain, Ayush
Asadi, Kavosh
Yu, Youliang
Jiang, Daniel
Vidolov, Boris
Hassani, Kaveh
Sajda, Paul
Bhandari, Jalaj
Efroni, Yonathan
author_facet Samanta, Ankur
Magesh, Akshayaa
Jain, Ayush
Asadi, Kavosh
Yu, Youliang
Jiang, Daniel
Vidolov, Boris
Hassani, Kaveh
Sajda, Paul
Bhandari, Jalaj
Efroni, Yonathan
contents Self-correction in language models remains elusive. In this work, we explore whether language models can explicitly localize errors in incorrect reasoning, as a path toward building AI systems that can effectively correct themselves. We introduce a prompting method that structures reasoning as discrete, semantically coherent thought steps, and show that models can localize errors more reliably within this structure than in conventional, unstructured chain-of-thought reasoning. Motivated by how the human brain monitors errors at discrete decision points and resamples alternatives, we introduce Iterative Correction Sampling of Thoughts (Thought-ICS), a self-correction framework. Thought-ICS iteratively prompts the model to generate reasoning one discrete and complete thought at a time--where each thought represents a deliberate decision by the model--creating natural boundaries for precise error localization. Upon verification, the model localizes the first erroneous step, and the system backtracks to generate alternative reasoning from the last correct point. When asked to correct reasoning verified as incorrect by an oracle, Thought-ICS achieves 20-40% self-correction lift. In a completely autonomous setting without external verification, it outperforms contemporary self-correction baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2602_02416
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Structure Enables Effective Self-Localization of Errors in LLMs
Samanta, Ankur
Magesh, Akshayaa
Jain, Ayush
Asadi, Kavosh
Yu, Youliang
Jiang, Daniel
Vidolov, Boris
Hassani, Kaveh
Sajda, Paul
Bhandari, Jalaj
Efroni, Yonathan
Artificial Intelligence
Self-correction in language models remains elusive. In this work, we explore whether language models can explicitly localize errors in incorrect reasoning, as a path toward building AI systems that can effectively correct themselves. We introduce a prompting method that structures reasoning as discrete, semantically coherent thought steps, and show that models can localize errors more reliably within this structure than in conventional, unstructured chain-of-thought reasoning. Motivated by how the human brain monitors errors at discrete decision points and resamples alternatives, we introduce Iterative Correction Sampling of Thoughts (Thought-ICS), a self-correction framework. Thought-ICS iteratively prompts the model to generate reasoning one discrete and complete thought at a time--where each thought represents a deliberate decision by the model--creating natural boundaries for precise error localization. Upon verification, the model localizes the first erroneous step, and the system backtracks to generate alternative reasoning from the last correct point. When asked to correct reasoning verified as incorrect by an oracle, Thought-ICS achieves 20-40% self-correction lift. In a completely autonomous setting without external verification, it outperforms contemporary self-correction baselines.
title Structure Enables Effective Self-Localization of Errors in LLMs
topic Artificial Intelligence
url https://arxiv.org/abs/2602.02416