NIST - National Institute of Standards and Technology

09/18/2026 | Press release | Distributed by Public on 09/19/2026 03:13

ARIA Evaluation Planning Manual: Elements of ARIA-Style AI Evaluations

Published
September 18, 2026

Author(s)

Theodore Jensen, Mark Przybocki, Monica Kodwani, Kristen Greene, Patrick Hall, Razvan Amironesei, Craig Greenberg

Abstract

This document outlines the components for evaluating an AI application using the NIST Assessing Risks and Impacts of AI (ARIA) approach. The ARIA Evaluation Planning Manual is designed to illustrate the various elements of conducting a holistic AI evaluation and can be used as a first step in developing new, customized AI evaluations. The ARIA approach assesses an AI system's trustworthiness by combining data from three types of testing: Model Testing, Red Teaming, and User Testing. This manual lists the necessary evaluation elements and provides links to available resources for developing materials and infrastructure.
Citation
NIST Trustworthy and Responsible AI - 200-3
Report Number
200-3
Pub Type
NIST Pubs

Keywords

AI Evaluation, AI Measurement, Model Testing, Red Teaming, User Testing, Trustworthiness.

Citation

Jensen, T. , Przybocki, M. , Kodwani, M. , Greene, K. , Hall, P. , Amironesei, R. and Greenberg, C. (2026), ARIA Evaluation Planning Manual: Elements of ARIA-Style AI Evaluations, NIST Trustworthy and Responsible AI, National Institute of Standards and Technology, Gaithersburg, MD, [online], https://doi.org/10.6028/NIST.AI.200-3, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=962584 (Accessed September 19, 2026)
Additional citation formats

Issues

If you have any questions about this publication or are having problems accessing it, please contact [email protected].

NIST - National Institute of Standards and Technology published this content on September 18, 2026, and is solely responsible for the information contained herein. Distributed via Public Technologies (PUBT), unedited and unaltered, on September 19, 2026 at 09:13 UTC. If you believe the information included in the content is inaccurate or outdated and requires editing or removal, please contact us at [email protected]