Davin Nabizadeh

This article presents normative information for the Defining Issue Test Version 2 (DIT2) schema scores and most common summary scores based on secondary data from the last 10 years DIT2 database (N = 73740, Mage = 23.11, SD = 7.87, the age range in year = 12–95) maintained by the University of Alabama’s Center for the Study of Ethical Development from 2011 to 2020. More specifically, the study provides (1) norms by education; (2) norms by gender and education; and (3) norms by gender and age for the DIT2. The norms indicate a general but not consistent trend that moral reasoning scores increase by education level. Additionally, the Personal Interest and Maintain Norms scores are higher for males than females for all education levels and age groups while Postconventional, N2, and Type indicator scores are higher for females than males for all education levels and age groups.

This study investigates how various large language models (LLMs) generate responses to moral reasoning dilemmas. It specifically examines LLM-generated responses using the Defining Issues Test (DIT-2), which measures abstract moral reasoning schemas, and the Intermediate Concepts Measure (ICM Educational leaders’ version), which assesses domain-specific professional moral reasoning. For DIT-2, Claude prioritizes the highest post-conventional moral reasoning, followed by Gemini Advanced and Gemini. For the ICM Educational Leaders version, Gemini Advanced had the highest total ICM score, followed by Claude 3.5 Sonnet and Gemini. The findings indicate that some LLMs can generate responses consistent with sophisticated moral reasoning patterns, producing scores comparable to or exceeding graduate-level human participants; however, no direct comparisons with human participants were made in this study. This study provides a methodological framework for guiding larger-scale research into AI-generated and human moral reasoning patterns.