🔴 Language models, like humans, show content effects on reasoning tasks

“Language models also perform imperfectly on logical reasoning tasks and more often fail in situations where humans fail—when stimuli become too abstract or conflict with prior expectations.”

Andrew K Lampinen, Ishita Dasgupta, Stephanie C Y Chan, Hannah R Sheahan, Antonia Creswell, Dharshan Kumaran, James L McClelland, Felix Hill, Language models, like humans, show content effects on reasoning tasks, PNAS Nexus, Volume 3, Issue 7, July 2024, pgae233, https://doi.org/10.1093/pnasnexus/pgae233

#OpenAccess #OA #Research #Article #DOI #LanguageModels #Reasoning #Logic #ComputerScience #AI #ArtificialIntelligence #Academia #Academic #Academics @ai