Interpretable Math Word Problem Solution Generation via Step-by-step Planning

Mengxue Zhang, Zichao Wang, Zhichao Yang, Weiqi Feng, Andrew Lan


Abstract
Solutions to math word problems (MWPs) with step-by-step explanations are valuable, especially in education, to help students better comprehend problem-solving strategies. Most existing approaches only focus on obtaining the final correct answer. A few recent approaches leverage intermediate solution steps to improve final answer correctness but often cannot generate coherent steps with a clear solution strategy. Contrary to existing work, we focus on improving the correctness and coherence of the intermediate solutions steps. We propose a step-by-step planning approach for intermediate solution generation, which strategically plans the generation of the next solution step based on the MWP and the previous solution steps. Our approach first plans the next step by predicting the necessary math operation needed to proceed, given history steps, then generates the next step, token-by-token, by prompting a language model with the predicted math operation. Experiments on the GSM8K dataset demonstrate that our approach improves the accuracy and interpretability of the solution on both automatic metrics and human evaluation.
Anthology ID:
2023.acl-long.379
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6858–6877
Language:
URL:
https://aclanthology.org/2023.acl-long.379
DOI:
10.18653/v1/2023.acl-long.379
Bibkey:
Cite (ACL):
Mengxue Zhang, Zichao Wang, Zhichao Yang, Weiqi Feng, and Andrew Lan. 2023. Interpretable Math Word Problem Solution Generation via Step-by-step Planning. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6858–6877, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Interpretable Math Word Problem Solution Generation via Step-by-step Planning (Zhang et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp22-frontmatter/2023.acl-long.379.pdf