Teaching Small Language Models to Reason

Lucie Charlotte Magister, Jonathan Mallinson, Jakub Adamek, Eric Malmi, Aliaksei Severyn


Abstract
Chain of thought prompting successfully improves the reasoning capabilities of large language models, achieving state of the art results on a range of datasets. However, these reasoning capabilities only appear to emerge in models with at least tens of billions of parameters. In this paper, we explore the transfer of such reasoning capabilities to smaller models via knowledge distillation, also investigating model and dataset size trade-off. Specifically, we finetune a student model on the chain of thought outputs generated by a larger teacher model. Our experiments show that the proposed method improves task performance across arithmetic, commonsense and symbolic reasoning datasets. For example, the accuracy of T5 XXL on GSM8K improves from 8.11% to 21.99% and 18.42% when finetuned on PaLM 540B and GPT-3 175B generated chains of thought, respectively.
Anthology ID:
2023.acl-short.151
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short 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:
1773–1781
Language:
URL:
https://aclanthology.org/2023.acl-short.151
DOI:
10.18653/v1/2023.acl-short.151
Bibkey:
Cite (ACL):
Lucie Charlotte Magister, Jonathan Mallinson, Jakub Adamek, Eric Malmi, and Aliaksei Severyn. 2023. Teaching Small Language Models to Reason. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1773–1781, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Teaching Small Language Models to Reason (Magister et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-short.151.pdf
Video:
 https://aclanthology.org/2023.acl-short.151.mp4