Abstract
Language models generate text based on successively sampling the next word. A decoding procedure based on nucleus (top-p) sampling chooses from the smallest possible set of words whose cumulative probability exceeds the probability p. In this work, we assess whether a top-p set is indeed aligned with its probabilistic meaning in various linguistic contexts.We employ conformal prediction, a calibration procedure that focuses on the construction of minimal prediction sets according to a desired confidence level, to calibrate the parameter p as a function of the entropy of the next word distribution. We find that OPT models are overconfident, and that calibration shows a moderate inverse scaling with model size.- Anthology ID:
- 2023.findings-acl.3
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2023
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 27–34
- Language:
- URL:
- https://aclanthology.org/2023.findings-acl.3
- DOI:
- 10.18653/v1/2023.findings-acl.3
- Cite (ACL):
- Shauli Ravfogel, Yoav Goldberg, and Jacob Goldberger. 2023. Conformal Nucleus Sampling. In Findings of the Association for Computational Linguistics: ACL 2023, pages 27–34, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Conformal Nucleus Sampling (Ravfogel et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/2023.findings-acl.3.pdf