Understanding the brain with AI-driven explanations and experiments

Microsoft Research · 3 weeks ago

Microsoft Research and collaborators developed generative causal testing (GCT), a method that distills opaque language model predictions of brain activity into readable explanations by having LLMs generate targeted stories to confirm which concepts specific brain regions respond to. The approach was published in Nature Neuroscience and successfully identified known selectivity patterns, separated three place-processing regions previously thought similar, and discovered unmapped prefrontal micro-regions tuned to specific concepts like dialogue and clock times. GCT demonstrates that black-box predictive models can be converted into testable scientific hypotheses that can be verified through real experiments.