LLMs cannot find reasoning errors, but can correct them given the error location

Gladys Tyen, Hassan Mansoor, Victor Carbune, Peter Chen, Tony Mak


Abstract
While self-correction has shown promise in improving LLM outputs in terms of style and quality (e.g. Chen et al., 2023b; Madaan et al.,2023), recent attempts to self-correct logical or reasoning errors often cause correct answers to become incorrect, resulting in worse performances overall (Huang et al., 2023). In this paper, we show that poor self-correction performance stems from LLMs’ inability tofind logical mistakes, rather than their ability to correct a known mistake. Firstly, we benchmark several state-of-the-art LLMs ontheir mistake-finding ability and demonstrate that they generally struggle with the task, even in highly objective, unambiguous cases. Secondly, we test the correction abilities of LLMs – separately from mistake finding – using a backtracking setup that feeds ground truth mistake location information to the model. We show that this boosts downstream task performance across our 5 reasoning tasks, indicating that LLMs’ correction abilities are robust. Finally, we show that it is possible to obtain mistake location information without ground truth labels or in-domain training data. We train a small classifier with out-of-domain data, which exhibits stronger mistake-finding performance than prompting a large model. We release our dataset of LLM-generated logical mistakes, BIG-Bench Mistake, to enable further research into locating LLM reasoning mistakes.
Anthology ID:
2024.findings-acl.826
Volume:
Findings of the Association for Computational Linguistics ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand and virtual meeting
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13894–13908
Language:
URL:
https://aclanthology.org/2024.findings-acl.826
DOI:
10.18653/v1/2024.findings-acl.826
Bibkey:
Cite (ACL):
Gladys Tyen, Hassan Mansoor, Victor Carbune, Peter Chen, and Tony Mak. 2024. LLMs cannot find reasoning errors, but can correct them given the error location. In Findings of the Association for Computational Linguistics ACL 2024, pages 13894–13908, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
Cite (Informal):
LLMs cannot find reasoning errors, but can correct them given the error location (Tyen et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2024.findings-acl.826.pdf