Using AI Uncertainty Quantification to Improve Human Decision-Making

Laura Marusich, Jonathan Bakdash, Yan Zhou, Murat Kantarcioglu
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34949-34960, 2024.

Abstract

AI Uncertainty Quantification (UQ) has the potential to improve human decision-making beyond AI predictions alone by providing additional probabilistic information to users. The majority of past research on AI and human decision-making has concentrated on model explainability and interpretability, with little focus on understanding the potential impact of UQ on human decision-making. We evaluated the impact on human decision-making for instance-level UQ, calibrated using a strict scoring rule, in two online behavioral experiments. In the first experiment, our results showed that UQ was beneficial for decision-making performance compared to only AI predictions. In the second experiment, we found UQ had generalizable benefits for decision-making across a variety of representations for probabilistic information. These results indicate that implementing high quality, instance-level UQ for AI may improve decision-making with real systems compared to AI predictions alone.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-marusich24a, title = {Using {AI} Uncertainty Quantification to Improve Human Decision-Making}, author = {Marusich, Laura and Bakdash, Jonathan and Zhou, Yan and Kantarcioglu, Murat}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {34949--34960}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/marusich24a/marusich24a.pdf}, url = {https://proceedings.mlr.press/v235/marusich24a.html}, abstract = {AI Uncertainty Quantification (UQ) has the potential to improve human decision-making beyond AI predictions alone by providing additional probabilistic information to users. The majority of past research on AI and human decision-making has concentrated on model explainability and interpretability, with little focus on understanding the potential impact of UQ on human decision-making. We evaluated the impact on human decision-making for instance-level UQ, calibrated using a strict scoring rule, in two online behavioral experiments. In the first experiment, our results showed that UQ was beneficial for decision-making performance compared to only AI predictions. In the second experiment, we found UQ had generalizable benefits for decision-making across a variety of representations for probabilistic information. These results indicate that implementing high quality, instance-level UQ for AI may improve decision-making with real systems compared to AI predictions alone.} }
Endnote
%0 Conference Paper %T Using AI Uncertainty Quantification to Improve Human Decision-Making %A Laura Marusich %A Jonathan Bakdash %A Yan Zhou %A Murat Kantarcioglu %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-marusich24a %I PMLR %P 34949--34960 %U https://proceedings.mlr.press/v235/marusich24a.html %V 235 %X AI Uncertainty Quantification (UQ) has the potential to improve human decision-making beyond AI predictions alone by providing additional probabilistic information to users. The majority of past research on AI and human decision-making has concentrated on model explainability and interpretability, with little focus on understanding the potential impact of UQ on human decision-making. We evaluated the impact on human decision-making for instance-level UQ, calibrated using a strict scoring rule, in two online behavioral experiments. In the first experiment, our results showed that UQ was beneficial for decision-making performance compared to only AI predictions. In the second experiment, we found UQ had generalizable benefits for decision-making across a variety of representations for probabilistic information. These results indicate that implementing high quality, instance-level UQ for AI may improve decision-making with real systems compared to AI predictions alone.
APA
Marusich, L., Bakdash, J., Zhou, Y. & Kantarcioglu, M.. (2024). Using AI Uncertainty Quantification to Improve Human Decision-Making. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:34949-34960 Available from https://proceedings.mlr.press/v235/marusich24a.html.

Related Material