Do GPT Language Models Suffer From Split Personality Disorder? The Advent Of Substrate-Free Psychometrics
Autor: | Romero, Peter, Fitz, Stephen, Nakatsuma, Teruo |
---|---|
Rok vydání: | 2024 |
Předmět: | |
Druh dokumentu: | Working Paper |
DOI: | 10.21203/rs.3.rs-2717108/v1 |
Popis: | Previous research on emergence in large language models shows these display apparent human-like abilities and psychological latent traits. However, results are partly contradicting in expression and magnitude of these latent traits, yet agree on the worrisome tendencies to score high on the Dark Triad of narcissism, psychopathy, and Machiavellianism, which, together with a track record of derailments, demands more rigorous research on safety of these models. We provided a state of the art language model with the same personality questionnaire in nine languages, and performed Bayesian analysis of Gaussian Mixture Model, finding evidence for a deeper-rooted issue. Our results suggest both interlingual and intralingual instabilities, which indicate that current language models do not develop a consistent core personality. This can lead to unsafe behaviour of artificial intelligence systems that are based on these foundation models, and are increasingly integrated in human life. We subsequently discuss the shortcomings of modern psychometrics, abstract it, and provide a framework for its species-neutral, substrate-free formulation. Comment: 37 pages, 7 figures, 3 tables, date v1: Mar 26 2023; replaced with new version; reason: removed journal logo from older version of article that is no longer valid |
Databáze: | arXiv |
Externí odkaz: |