Abstract
For users to trust model predictions, they need to understand model outputs, particularly their confidence — calibration aims to adjust (calibrate) models’ confidence to match expected accuracy. We argue that the traditional calibration evaluation does not promote effective calibrations: for example, it can encourage always assigning a mediocre confidence score to all predictions, which does not help users distinguish correct predictions from wrong ones. Building on those observations, we propose a new calibration metric, MacroCE, that better captures whether the model assigns low confidence to wrong predictions and high confidence to correct predictions. Focusing on the practical application of open-domain question answering, we examine conventional calibration methods applied on the widely-used retriever-reader pipeline, all of which do not bring significant gains under our new MacroCE metric. Toward better calibration, we propose a new calibration method (ConsCal) that uses not just final model predictions but whether multiple model checkpoints make consistent predictions. Altogether, we provide an alternative view of calibration along with a new metric, re-evaluation of existing calibration methods on our metric, and proposal of a more effective calibration method.- Anthology ID:
- 2022.findings-emnlp.204
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2022
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Editors:
- Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2814–2829
- Language:
- URL:
- https://aclanthology.org/2022.findings-emnlp.204
- DOI:
- 10.18653/v1/2022.findings-emnlp.204
- Cite (ACL):
- Chenglei Si, Chen Zhao, Sewon Min, and Jordan Boyd-Graber. 2022. Re-Examining Calibration: The Case of Question Answering. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 2814–2829, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Re-Examining Calibration: The Case of Question Answering (Si et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2022.findings-emnlp.204.pdf