On the use of foundation models in cognitive science

2026-08-07

AI Summary

This study addresses the lack of a rigorous evaluation framework for assessing whether foundation models can serve as explanatory models of human cognition and development, noting that behavioral alignment alone is insufficient to establish cognitive validity. The authors propose a four-stage inferential framework—task adaptation, construction of linking hypotheses, evaluation of behavioral correspondence, and systematic model comparison—that emphasizes the central role of linking hypotheses in mapping model outputs to human behavior. They argue that mere behavioral fit is inadequate; instead, cognitive plausibility requires integration of theoretical commitments, diagnostic tasks, and comparative experiments. By providing a methodological foundation for applying foundation models in cognitive and developmental science, this work substantially enhances their scientific validity as explanatory tools.

Abstract

A host of recent studies have evaluated the cognitive and developmental alignment of Foundation Models (FMs). These investigations include evaluations of their correspondence to adult performance across a range of cognitive domains, as well as whether aspects of model training track children's cognitive development. However, using FMs as candidate cognitive models poses significant methodological and conceptual challenges. A key question underlies this effort: under what conditions does behavioral alignment justify treating FMs as explanatory models of cognition? In this paper, we articulate a four-stage inferential framework for evaluating FMs as cognitive and developmental models: adapting human experimental tasks to model-compatible formats, specifying linking hypotheses that map model outputs to human measures, evaluating behavioral correspondence, and comparing across candidate models or manipulations. We clarify the role of linking hypotheses in mapping model outputs to human behavioral measures, identify challenges that constrain alignment claims, and propose principles for theory-driven and comparative evaluation. Throughout, we argue that behavioral fit alone is insufficient. Alignment becomes scientifically meaningful only when embedded within explicit theoretical commitments, theory-diagnostic tasks, and systematic contrastive evaluation across candidate models.

Problem

• Foundation Models
• cognitive modeling
• behavioral alignment
• linking hypotheses
• developmental cognition

Innovation

• foundation models
• cognitive modeling
• linking hypotheses
• behavioral alignment
• inferential framework