Instructing Large Language Models to Identify and Ignore Irrelevant Conditions

Zhenyu Wu, Chao Shen, Meng Jiang


Abstract
Math word problem (MWP) solving requires generating a reasoning path based on a given problem description that often contains irrelevant conditions.Existing chain-of-thought (CoT) prompting methods elicited multi-step reasoning abilities of large language models (LLMs) to solve MWPs.However, they were seriously confused by the irrelevant conditions, resulting in low accuracy.In this paper, we propose a novel approach named I3C that instructs LLMs to identify and ignore irrelevant conditions.It identifies a set of irrelevant condition candidates that have a weak semantic relevance with the question.Then it prompts LLMs to verify the irrelevant conditions.Lastly it instructs the LLMs with the verification on relevant and irrelevant conditions to avoid confusion and improve reasoning paths.Moreover, we propose to select (problem, reasoning paths) pairs as demonstrations to enhance I3C with few-shot reasoning. We develop I3C-Select that selects the most confusing problems based on the semantic relevance measurement.We conduct extensive experiments on eight MWP datasets.I3C can be combined with any CoT prompting methods to improve the performance of solving MWPs.Notably, with GPT-3.5-Turbo and I3C-Select, we achieve an accuracy of 96.0 and 94.1 on GSM-IC2-1K and GSM-ICM-1K, respectively, significantly outperforming the state-of-the-art few-shot prompting method Complex-CoT by +11.7 and +11.1.Our implementation is made publicly available at https://wzy6642.github.io/I3C.github.io/.
Anthology ID:
2024.naacl-long.379
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6799–6819
Language:
URL:
https://aclanthology.org/2024.naacl-long.379
DOI:
Bibkey:
Cite (ACL):
Zhenyu Wu, Chao Shen, and Meng Jiang. 2024. Instructing Large Language Models to Identify and Ignore Irrelevant Conditions. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 6799–6819, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Instructing Large Language Models to Identify and Ignore Irrelevant Conditions (Wu et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.379.pdf
Copyright:
 2024.naacl-long.379.copyright.pdf