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

Ritwik Vashistha, Arya Farahi
Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, PMLR 258:4726-4734, 2025.

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 conditional 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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v258-vashistha25a, title = {I-trustworthy Models. A framework for trustworthiness evaluation of probabilistic classifiers}, author = {Vashistha, Ritwik and Farahi, Arya}, booktitle = {Proceedings of The 28th International Conference on Artificial Intelligence and Statistics}, pages = {4726--4734}, year = {2025}, editor = {Li, Yingzhen and Mandt, Stephan and Agrawal, Shipra and Khan, Emtiyaz}, volume = {258}, series = {Proceedings of Machine Learning Research}, month = {03--05 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v258/main/assets/vashistha25a/vashistha25a.pdf}, url = {https://proceedings.mlr.press/v258/vashistha25a.html}, 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 conditional 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.} }
Endnote
%0 Conference Paper %T I-trustworthy Models. A framework for trustworthiness evaluation of probabilistic classifiers %A Ritwik Vashistha %A Arya Farahi %B Proceedings of The 28th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2025 %E Yingzhen Li %E Stephan Mandt %E Shipra Agrawal %E Emtiyaz Khan %F pmlr-v258-vashistha25a %I PMLR %P 4726--4734 %U https://proceedings.mlr.press/v258/vashistha25a.html %V 258 %X 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 conditional 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.
APA
Vashistha, R. & Farahi, A.. (2025). I-trustworthy Models. A framework for trustworthiness evaluation of probabilistic classifiers. Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 258:4726-4734 Available from https://proceedings.mlr.press/v258/vashistha25a.html.

Related Material