Calc-X and Calcformers: Empowering Arithmetical Chain-of-Thought through Interaction with Symbolic Systems
Marek Kadlčík, Michal Štefánik, Ondrej Sotolar, Vlastimil Martinek
Abstract
Despite outstanding performance in many tasks, language models are notoriously inclined to make factual errors in tasks requiring arithmetic computation. We address this deficiency by creating Calc-X, a collection of datasets that demonstrates the appropriate use of a calculator in reasoning chains. Calc-X is suitable for teaching language models to offload computations to a symbolic system. We survey and unify several existing chain-of-thought datasets into a proposed format, resulting in a standard collection of over 300,000 samples requiring arithmetic reasoning. Finally, we use the new Calc-X collection to train open-source calculator-using models and show that these models approximately double the accuracy of generating correct results compared to vanilla language model baselines.- Anthology ID:
- 2023.emnlp-main.742
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 12101–12108
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.742
- DOI:
- 10.18653/v1/2023.emnlp-main.742
- Cite (ACL):
- Marek Kadlčík, Michal Štefánik, Ondrej Sotolar, and Vlastimil Martinek. 2023. Calc-X and Calcformers: Empowering Arithmetical Chain-of-Thought through Interaction with Symbolic Systems. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 12101–12108, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Calc-X and Calcformers: Empowering Arithmetical Chain-of-Thought through Interaction with Symbolic Systems (Kadlčík et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/corrections-2024-05/2023.emnlp-main.742.pdf