Abstract
The rapid advancement of technology, including artificial intelligence (AI), is creating new challenges for judicial review under the Administrative Procedure Act (APA). In late 2023, federal administrative agencies publicly disclosed over 700 use cases of AI that employ sophisticated techniques like machine learning and natural language processing. While the APA's flexible judicial review framework certainly allows agencies to utilize new technologies, the APA also requires explainability of agency decisions; thus, agencies must be able to articulate the reasoning and methodology behind AI-enabled decisions for the purpose of judicial review. This Article examines APA judicial review as it applies to agency adoption of AI by examining how courts have previously assessed agency predictive and computer models. It summarizes current federal agency AI use cases and techniques and proposes an Lil report card." This report card is designed to direct judicial review towards essential attributes of AI implementations, ensuring courts focus on evaluating the training data, model design, intended uses, validation practices, and performance metrics of AI models. Through this lens, the Article seeks to offer a structured approach for courts in assessing the rationality of agency decisions informed by AI models under the arbitrary and capricious review standard.
Recommended Citation
Zoe E. Niesel,
An Artificial Intelligence Report Card for Judicial Review,
14
Mich. J. Env't. & Admin. L.
143
(2024).
Available at:
https://repository.law.umich.edu/mjeal/vol14/iss1/4
Included in
Administrative Law Commons, Artificial Intelligence and Robotics Commons, Environmental Law Commons
