Streamlining ABET Direct Assessment: The Potential of ChatGPT Integration in Open and Distance Engineering Education

Abstract

Open and distance engineering education (ODEE) presents unique challenges for program evaluation and accreditation. Traditional ABET accreditation processes, often reliant on in-person observation and resource-intensive assessments, struggle to effectively assess the diverse learning experiences and outcomes inherent to ODEE environments. This paper proposes an LLM-enhanced framework for ABET accreditation, specifically designed to address the complexities of ODEE. The framework integrates Large Language Models (LLMs) like ChatGPT throughout key assessment stages, from curriculum mapping and CLO weighting to examination design, attainment level setting, and student outcome reporting. This paper details how LLMs can analyze learning data, personalize assessments, provide scalable yet tailored feedback, and automate reporting, thereby enhancing the robustness, efficiency, and transparency of ABET accreditation for ODEE programs. The ethical considerations and potential limitations of LLM integration are also critically examined, highlighting the need for human oversight, data privacy safeguards, and ongoing evaluation. By embracing the capabilities of LLMs responsibly, this framework empowers ODEE programs, particularly those within a European context seeking international recognition, to demonstrate program quality, continuous improvement, and alignment with globally recognized standards in engineering education.