Abstract
Quantitative and numerical comprehension in language is an important task in many fields like education and finance, but still remains a challenging task for language models. While tool and calculator usage has shown to be helpful to improve mathematical reasoning in large pretrained decoder-only language models, this remains unexplored for smaller language models with encoders. In this paper, we propose Pre-Calc, a simple pre-finetuning objective of learning to use the calculator for both encoder-only and encoder-decoder architectures, formulated as a discriminative and generative task respectively. We pre-train BERT and RoBERTa for discriminative calculator use and Flan-T5 for generative calculator use on the MAWPS, SVAMP, and AsDiv-A datasets, which improves performance on downstream tasks that require numerical understanding. Our code and data are available at https://github.com/calc-cmu/pre-calc.- Anthology ID:
- 2024.semeval-1.211
- Volume:
- Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
- Month:
- June
- Year:
- 2024
- Address:
- Mexico City, Mexico
- Editors:
- Atul Kr. Ojha, A. Seza Doğruöz, Harish Tayyar Madabushi, Giovanni Da San Martino, Sara Rosenthal, Aiala Rosá
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1468–1475
- Language:
- URL:
- https://aclanthology.org/2024.semeval-1.211
- DOI:
- Cite (ACL):
- Vishruth Veerendranath, Vishwa Shah, and Kshitish Ghate. 2024. Calc-CMU at SemEval-2024 Task 7: Pre-Calc - Learning to Use the Calculator Improves Numeracy in Language Models. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 1468–1475, Mexico City, Mexico. Association for Computational Linguistics.
- Cite (Informal):
- Calc-CMU at SemEval-2024 Task 7: Pre-Calc - Learning to Use the Calculator Improves Numeracy in Language Models (Veerendranath et al., SemEval 2024)
- PDF:
- https://preview.aclanthology.org/jeptaln-2024-ingestion/2024.semeval-1.211.pdf