Revisiting Automated Prompting: Are We Actually Doing Better?
Yulin Zhou, Yiren Zhao, Ilia Shumailov, Robert Mullins, Yarin Gal
Abstract
Current literature demonstrates that Large Language Models (LLMs) are great few-shot learners, and prompting significantly increases their performance on a range of downstream tasks in a few-shot learning setting. An attempt to automate human-led prompting followed, with some progress achieved. In particular, subsequent work demonstrates that automation can outperform fine-tuning in certain K-shot learning scenarios. In this paper, we revisit techniques for automated prompting on six different downstream tasks and a larger range of K-shot learning settings. We find that automated prompting does not consistently outperform simple manual prompting. Our work suggests that, in addition to fine-tuning, manual prompting should be used as a baseline in this line of research.- Anthology ID:
- 2023.acl-short.155
- 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:
- 1822–1832
- Language:
- URL:
- https://aclanthology.org/2023.acl-short.155
- DOI:
- 10.18653/v1/2023.acl-short.155
- Cite (ACL):
- Yulin Zhou, Yiren Zhao, Ilia Shumailov, Robert Mullins, and Yarin Gal. 2023. Revisiting Automated Prompting: Are We Actually Doing Better?. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1822–1832, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Revisiting Automated Prompting: Are We Actually Doing Better? (Zhou et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2023.acl-short.155.pdf