Integrating Large Language Model Applications in Graduate Applied Behavior Analysis Education

As artificial intelligence (AI) based applications rapidly expand in capability and accessibility, graduate programs in applied behavior analysis (ABA) must adapt their pedagogical models to harness their benefits while mitigating risks. This article examines the integration of large language models (LLMs) in ABA education, highlighting how faculty can support student learning while preserving academic integrity. The article examines practical strategies for integrating AI into conceptual and performance-based assessments, emphasizing approaches that maintain strong instructional standards, promote ethical use, and require authentic demonstration of competence. Examples drawn from ABA coursework demonstrate how LLM applications can be thoughtfully incorporated, and recommendations are offered for clarifying appropriate LLM application use, prompt engineering, and rubric-based grading. In addition, the article discusses the importance of proactive policy development, including behavioral contracts and assessment tools, to set clear expectations. Future directions include adaptive learning platforms, virtual clients powered by LLMs, and competency-mapping dashboards that track progress across a student's academic trajectory.