Calibrating Expressions of Certainty
Peiqi Wang, Barbara D. Lam, Yingcheng Liu, Ameneh Asgari-Targhi, Rameswar Panda, William M Wells, Tina Kapur, Polina Golland
Abstract
We present a novel approach to calibrating linguistic expressions of certainty, e.g., "Maybe" and "Likely". Unlike prior work that assigns a single score to each certainty phrase, we model uncertainty as distributions over the simplex to capture their semantics more accurately. To accommodate this new representation of certainty, we generalize existing measures of miscalibration and introduce a novel post-hoc calibration method. Leveraging these tools, we analyze the calibration of both humans (e.g., radiologists) and computational models (e.g., language models) and provide interpretable suggestions to improve their calibration.
BibTeX
@inproceedings{
wang2025calibrating,
title={Calibrating Expressions of Certainty},
author={Peiqi Wang and Barbara D. Lam and Yingcheng Liu and Ameneh Asgari-Targhi and Rameswar Panda and William M Wells and Tina Kapur and Polina Golland},
booktitle={The Thirteenth International Conference on Learning Representations},
year={2025},
url={https://openreview.net/forum?id=dNunnVB4W6}
}