Ask-Before-Detection: Identifying and Mitigating Conformity Bias in LLM-Powered Error Detector for Math Word Problem Solutions
Hang Li, Tianlong Xu, Kaiqi Yang, Yucheng Chu, Yanling Chen, Yichi Song, Qingsong Wen, Hui Liu
Abstract
The rise of large language models (LLMs) offers new opportunities for automatic error detection in education, particularly for math word problems (MWPs). While prior studies demonstrate the promise of LLMs as error detectors, they overlook the presence of multiple valid solutions for a single MWP. Our preliminary analysis reveals a significant performance gap between conventional and alternative solutions in MWPs, a phenomenon we term conformity bias in this work. To mitigate this bias, we introduce the Ask-Before-Detect (AskBD) framework, which generates adaptive reference solutions using LLMs to enhance error detection. Experiments on 200 examples of GSM8K show that AskBD effectively mitigates bias and improves performance, especially when combined with reasoning-enhancing techniques like chain-of-thought prompting.
BibTeX
@inproceedings{li-etal-2025-ask,
title = "Ask-Before-Detection: Identifying and Mitigating Conformity Bias in {LLM}-Powered Error Detector for Math Word Problem Solutions",
author = "Li, Hang and
Xu, Tianlong and
Yang, Kaiqi and
Chu, Yucheng and
Chen, Yanling and
Song, Yichi and
Wen, Qingsong and
Liu, Hui",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.80/",
doi = "10.18653/v1/2025.acl-long.80",
pages = "1597--1609",
ISBN = "979-8-89176-251-0"
}