English

I-trustworthy Models. A framework for trustworthiness evaluation of probabilistic classifiers

Machine Learning 2025-05-05 v2 Machine Learning Methodology

Abstract

As probabilistic models continue to permeate various facets of our society and contribute to scientific advancements, it becomes a necessity to go beyond traditional metrics such as predictive accuracy and error rates and assess their trustworthiness. Grounded in the competence-based theory of trust, this work formalizes I-trustworthy framework -- a novel framework for assessing the trustworthiness of probabilistic classifiers for inference tasks by linking local calibration to trustworthiness. To assess I-trustworthiness, we use the local calibration error (LCE) and develop a method of hypothesis-testing. This method utilizes a kernel-based test statistic, Kernel Local Calibration Error (KLCE), to test local calibration of a probabilistic classifier. This study provides theoretical guarantees by offering convergence bounds for an unbiased estimator of KLCE. Additionally, we present a diagnostic tool designed to identify and measure biases in cases of miscalibration. The effectiveness of the proposed test statistic is demonstrated through its application to both simulated and real-world datasets. Finally, LCE of related recalibration methods is studied, and we provide evidence of insufficiency of existing methods to achieve I-trustworthiness.

Keywords

Cite

@article{arxiv.2501.15617,
  title  = {I-trustworthy Models. A framework for trustworthiness evaluation of probabilistic classifiers},
  author = {Ritwik Vashistha and Arya Farahi},
  journal= {arXiv preprint arXiv:2501.15617},
  year   = {2025}
}

Comments

Accepted at AISTATS 2025 Conference

R2 v1 2026-06-28T21:18:31.303Z