Calibrating Large Language Models Using Their Generations Only

Dennis Ulmer, Martin Gubri, Hwaran Lee, Sangdoo Yun, Seong Oh


Abstract
As large language models (LLMs) are increasingly deployed in user-facing applications, building trust and maintaining safety by accurately quantifying a model’s confidence in its prediction becomes even more important. However, finding effective ways to calibrate LLMs—especially when the only interface to the models is their generated text—remains a challenge. We propose APRICOT (Auxiliary prediction of confidence targets): A method to set confidence targets and train an additional model that predicts an LLM’s confidence based on its textual input and output alone. This approach has several advantages: It is conceptually simple, does not require access to the target model beyond its output, does not interfere with the language generation, and has a multitude of potential usages, for instance by verbalizing the predicted confidence or using it to re-prompting the LLM to accurately reflecting its uncertainty. We show how our approach performs competitively in terms of calibration error for white-box and black-box LLMs on closed-book question-answering to detect incorrect LLM answers.
Anthology ID:
2024.acl-long.824
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
15440–15459
Language:
URL:
https://aclanthology.org/2024.acl-long.824
DOI:
10.18653/v1/2024.acl-long.824
Bibkey:
Cite (ACL):
Dennis Ulmer, Martin Gubri, Hwaran Lee, Sangdoo Yun, and Seong Oh. 2024. Calibrating Large Language Models Using Their Generations Only. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15440–15459, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Calibrating Large Language Models Using Their Generations Only (Ulmer et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.824.pdf