When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs
Transactions of the Association for Computational Linguistics · 04.11.2024 · 12 · 1417-1440
DOI: 10.1162/tacl_a_00713 ↗Kurz gefasst
Fachartikel in der Zeitschrift Transactions of the Association for Computational Linguistics, online erschienen am 04.11.2024. Verfasst von Ryo Kamoi und 4 weiteren Autor:innen. Die Arbeit wurde bisher 116-mal zitiert (Crossref) und nennt 122 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Self-correction is an approach to improving responses from large language models (LLMs) by refining the responses using LLMs during inference. Prior work has proposed various self-correction frameworks using different sources of feedback, including self-evaluation and external feedback. However, there is still no consensus on the question of when LLMs can correct their own mistakes, as recent studies also report negative results. In this work, we critically survey broad papers and discuss the conditions required for successful self-correction. We first find that prior studies often do not define their research questions in detail and involve impractical frameworks or unfair evaluations that over-evaluate self-correction. To tackle these issues, we categorize research questions in self-correction research and provide a checklist for designing appropriate experiments. Our critical survey based on the newly categorized research questions shows that (1) no prior work demonstrates successful self-correction with feedback from prompted LLMs, except for studies in tasks that are exceptionally suited for self-correction, (2) self-correction works well in tasks that can use reliable external feedback, and (3) large-scale fine-tuning enables self-correction.
Zitieren
APA
Kamoi, R., Zhang, Y., Zhang, N., Han, J., & Zhang, R. (2024). When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs. Transactions of the Association for Computational Linguistics, 12, 1417-1440. https://doi.org/10.1162/tacl_a_00713
Vancouver
Kamoi R, Zhang Y, Zhang N, Han J, Zhang R. When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs. Transactions of the Association for Computational Linguistics. 2024;12:1417-1440. doi:10.1162/tacl_a_00713
BibTeX
@article{Kamoi2024,
author = {Kamoi, Ryo and Zhang, Yusen and Zhang, Nan and Han, Jiawei and Zhang, Rui},
title = {When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs},
journal = {Transactions of the Association for Computational Linguistics},
year = {2024},
volume = {12},
pages = {1417--1440},
doi = {10.1162/tacl_a_00713}
}
EUVIMED