Bridging Psychometric and Content Development Practices with AI: A Community-Based Workflow for Augmenting Hawaiian Language Assessments

This paper presents the design and evaluation of a community-based artificial intelligence (AI)workflow developed for the Kaiapuni Assessment of Educational Outcomes (KĀʻEO) program, theonly native language assessment used for federal accountability in the United States. The projectexplored whether document-grounded language models could ethically and effectively augmenthuman analysis of item performance while preserving the cultural and linguistic integrity of theHawaiian language.Operating under the KĀʻEO AI Policy Framework, the workflow used NotebookLM for crossdocumentsynthesis of psychometric data and Claude 3.5 Sonnet for developer-facing interpretation,with human oversight at every stage. Fifty-eight flagged items across Hawaiian LanguageArts, Mathematics, and Science were reviewed during Round 2 of the AI Lab, producing six interpretivebriefs that identified systemic design issues such as linguistic ambiguity, Depth-of-Knowledge(DOK) misalignment, and structural overload.The findings demonstrate that AI can serve as an ethically bounded amplifier of human expertise,accelerating analysis while simultaneously prioritizing fairness, human expertise, and cultural authority.This work offers a replicable model for responsible AI integration in Indigenous-languageeducational measurement.