NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks

Swaroop Mishra, Arindam Mitra, Neeraj Varshney, Bhavdeep Sachdeva, Peter Clark, Chitta Baral, Ashwin Kalyan


Abstract
Given the ubiquitous nature of numbers in text, reasoning with numbers to perform simple calculations is an important skill of AI systems. While many datasets and models have been developed to this end, state-of-the-art AI systems are brittle; failing to perform the underlying mathematical reasoning when they appear in a slightly different scenario. Drawing inspiration from GLUE that was proposed in the context of natural language understanding, we propose NumGLUE, a multi-task benchmark that evaluates the performance of AI systems on eight different tasks, that at their core require simple arithmetic understanding. We show that this benchmark is far from being solved with neural models including state-of-the-art large-scale language models performing significantly worse than humans (lower by 46.4 %). Further, NumGLUE promotes sharing knowledge across tasks, especially those with limited training data as evidenced by the superior performance (average gain of 3.4 % on each task) when a model is jointly trained on all the tasks as opposed to task-specific modeling. Finally, we hope that NumGLUE will encourage systems that perform robust and general arithmetic reasoning within language, a first step towards being able to perform more complex mathematical reasoning.
Anthology ID:
2022.acl-long.246
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3505–3523
Language:
URL:
https://aclanthology.org/2022.acl-long.246
DOI:
10.18653/v1/2022.acl-long.246
Bibkey:
Cite (ACL):
Swaroop Mishra, Arindam Mitra, Neeraj Varshney, Bhavdeep Sachdeva, Peter Clark, Chitta Baral, and Ashwin Kalyan. 2022. NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3505–3523, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks (Mishra et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.246.pdf
Data
GLUEMATHSuperGLUE