Surface Form Competition: Why the Highest Probability Answer Isn’t Always Right

Ari Holtzman, Peter West, Vered Shwartz, Yejin Choi, Luke Zettlemoyer


Abstract
Large language models have shown promising results in zero-shot settings. For example, they can perform multiple choice tasks simply by conditioning on a question and selecting the answer with the highest probability. However, ranking by string probability can be problematic due to surface form competition—wherein different surface forms compete for probability mass, even if they represent the same underlying concept in a given context, e.g. “computer” and “PC.” Since probability mass is finite, this lowers the probability of the correct answer, due to competition from other strings that are valid answers (but not one of the multiple choice options). We introduce Domain Conditional Pointwise Mutual Information, an alternative scoring function that directly compensates for surface form competition by simply reweighing each option according to its a priori likelihood within the context of a specific task. It achieves consistent gains in zero-shot performance over both calibrated and uncalibrated scoring functions on all GPT-2 and GPT-3 models on a variety of multiple choice datasets.
Anthology ID:
2021.emnlp-main.564
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7038–7051
Language:
URL:
https://aclanthology.org/2021.emnlp-main.564
DOI:
10.18653/v1/2021.emnlp-main.564
Bibkey:
Cite (ACL):
Ari Holtzman, Peter West, Vered Shwartz, Yejin Choi, and Luke Zettlemoyer. 2021. Surface Form Competition: Why the Highest Probability Answer Isn’t Always Right. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7038–7051, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Surface Form Competition: Why the Highest Probability Answer Isn’t Always Right (Holtzman et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.564.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.564.mp4
Data
ARCBoolQCOPACommonsenseQAHellaSwagSST