Measuring Pointwise π±-Usable Information In-Context-ly
Sheng Lu, Shan Chen, Yingya Li, Danielle Bitterman, Guergana Savova, Iryna Gurevych
Abstract
In-context learning (ICL) is a new learning paradigm that has gained popularity along with the development of large language models. In this work, we adapt a recently proposed hardness metric, pointwise π±-usable information (PVI), to an in-context version (in-context PVI). Compared to the original PVI, in-context PVI is more efficient in that it requires only a few exemplars and does not require fine-tuning. We conducted a comprehensive empirical analysis to evaluate the reliability of in-context PVI. Our findings indicate that in-context PVI estimates exhibit similar characteristics to the original PVI. Specific to the in-context setting, we show that in-context PVI estimates remain consistent across different exemplar selections and numbers of shots. The variance of in-context PVI estimates across different exemplar selections is insignificant, which suggests that in-context PVI estimates are stable. Furthermore, we demonstrate how in-context PVI can be employed to identify challenging instances. Our work highlights the potential of in-context PVI and provides new insights into the capabilities of ICL.- Anthology ID:
- 2023.findings-emnlp.1054
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 15739β15756
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.1054
- DOI:
- 10.18653/v1/2023.findings-emnlp.1054
- Cite (ACL):
- Sheng Lu, Shan Chen, Yingya Li, Danielle Bitterman, Guergana Savova, and Iryna Gurevych. 2023. Measuring Pointwise π±-Usable Information In-Context-ly. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 15739β15756, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Measuring Pointwise π±-Usable Information In-Context-ly (Lu et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2023.findings-emnlp.1054.pdf