AI-Augmented Content Validation in Behavioral Research: Development and Evaluation of the RATER System

, which leverage psychometric scales from 2,443 journal articles spanning eight disciplines and two state-of-the-art large language model architectures (i.e., BERT and GPT). A set of six complementary studies confirms the RATER system's accuracy, reliability, and usefulness. We find RATER can augment the scale development and validation process, increasing the validity of findings in behavioral research.