Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters
Boshi Wang, Sewon Min, Xiang Deng, Jiaming Shen, You Wu, Luke Zettlemoyer, Huan Sun
Abstract
Chain-of-Thought (CoT) prompting can dramatically improve the multi-step reasoning abilities of large language models (LLMs). CoT explicitly encourages the LLM to generate intermediate rationales for solving a problem, by providing a series of reasoning steps in the demonstrations. Despite its success, there is still little understanding of what makes CoT prompting effective and which aspects of the demonstrated reasoning steps contribute to its performance. In this paper, we show that CoT reasoning is possible even with invalid demonstrations - prompting with invalid reasoning steps can achieve over 80-90% of the performance obtained using CoT under various metrics, while still generating coherent lines of reasoning during inference. Further experiments show that other aspects of the rationales, such as being relevant to the query and correctly ordering the reasoning steps, are much more important for effective CoT reasoning. Overall, these findings both deepen our understanding of CoT prompting, and open up new questions regarding LLMs’ capability to learn to reason in context.- Anthology ID:
- 2023.acl-long.153
- 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:
- 2717–2739
- Language:
- URL:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2023.acl-long.153/
- DOI:
- 10.18653/v1/2023.acl-long.153
- Cite (ACL):
- Boshi Wang, Sewon Min, Xiang Deng, Jiaming Shen, You Wu, Luke Zettlemoyer, and Huan Sun. 2023. Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2717–2739, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters (Wang et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2023.acl-long.153.pdf