Small Foundation Models of Human Cognition and Behaviour
Large language models fine-tuned on human behavioural data have emerged as general-purpose cognitive proxies, but the scale this requires, and whether these models process task structure or exploit statistical shortcuts, remain open questions. We train fourteen models from 135M t...
ArXiv CS.AI
Source
Generated insight by OnAirToday AI
This research suggests that smaller, cognitively fine-tuned AI models can effectively proxy human behavior and cognition, potentially reducing the need for massive datasets and computational resources. Understanding how these models generalize and what information they utilize is crucial for their reliable application in cognitive science research.
Get the day's AI news in one short email. Free.
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.