An Information Bottleneck Characterization of the Understanding-Workload Tradeoff in Human-Centered Explainable AI
Name
3630106.3659032.pdf
Size
2.59 MB
Format
Adobe PDF
Checksum (MD5)
12567034b65bc1ff72d0ed5b18a97c3b
Author(s)
Sanneman, Lindsay
Tucker, Mycal
Shah, Julie A.
Date Issued
June 3, 2024
Publisher
ACM|The 2024 ACM Conference on Fairness, Accountability, and Transparency
Citation
Sanneman, Lindsay, Tucker, Mycal and Shah, Julie A. 2024. "An Information Bottleneck Characterization of the Understanding-Workload Tradeoff in Human-Centered Explainable AI."
Version
Final published version
Abstract
Recent advances in artificial intelligence (AI) have underscored the need for explainable AI (XAI) to support human understanding of AI systems. Consideration of human factors that impact explanation efficacy, such as mental workload and human understanding, is central to effective XAI design. Existing work in XAI has demonstrated a tradeoff between understanding and workload induced by different types of explanations. Explaining complex concepts through abstractions (hand-crafted groupings of related problem features) has been shown to effectively address and balance this workload-understanding tradeoff. In this work, we characterize the workload-understanding balance via the Information Bottleneck method: an information-theoretic approach which automatically generates abstractions that maximize informativeness and minimize complexity. In particular, we establish empirical connections between workload and complexity and between understanding and informativeness through human-subject experiments. This empirical link between human factors and information-theoretic concepts provides an important mathematical characterization of the workload-understanding tradeoff which enables user-tailored XAI design.
Description
FAccT ’24, June 03–06, 2024, Rio de Janeiro, Brazil
MIT Department
Massachusetts Institute of Technology. Department of Aeronautics and Astronautics
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3630106.3659032
