This talk explores the intersection of large language models (LLMs) and psychometrics, presenting a pioneering pathway for leveraging AI in developing and validating assessments for human behavior and cognition. By examining how LLMs can be used to in conjunction with psychometrics, we highlight the potential for these technologies to revolutionize psychological assessments, generating the building blocks for a fully-automated assessment development and validation framework.

Hudson Golino’s research focuses on quantitative methods, psychometrics and machine learning applied in the fields of psychology, health and education. He is particularly interested in new ways to assess the number of dimensions (i.e. latent variables) underlying multivariate data using network psychometrics. At University of Virginia, he teaches undergraduate and graduate courses on quantitative methods at the Department of Psychology. His current research focuses on large language models, network psychometrics, information, and quantum information theory. He has several free and open source R packages implementing the techniques developed by his research team. Golino completed his Ph.D. in March 2015 at the Universidade Federal de Minas Gerais (Brazil), where he studied applications of machine learning in Psychology, Education and Health. Golino also holds an M.Sci. in Developmental Psychology with an emphasis on psychometrics (2012), an BS. in Psychology (2011), all from Universidade Federal de Minas Gerais.