Optimal Explanations: A Quantitative Model of Human Error in Causal Graph Interpretation

Proceedings of the 31st International Conference on Intelligent User Interfaces 2026 Open access

Read full text
Authors: Paul-David Zuercher, Thomas Bohné, Per Ola Kristensson
DOI: 10.1145/3742413.3789226
Cited by: 1
References: 22

Abstract

When Artificial Intelligence (AI) reasoning is explained via causal graphs for human oversight, the human-computer interface is the performance bottleneck for decision-supported actions. As explanations grow more complex, humans’ interpretation ability degrades, resulting in ineffective oversight. This paper contributes a quantitative model of human causal reasoning bounds and demonstrates their utility for interpretable AI explanations.

Fields of Study & Subjects

Bayesian Modeling and Causal Inference Explainable Artificial Intelligence (XAI) Decision-Making and Behavioral Economics

Publication details

Journal / source
Proceedings of the 31st International Conference on Intelligent User Interfaces
Publisher
ACM
Pages
474–488
Publication date
3 March 2026
Language
EN