English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Journal Article

Large language models surpass human experts in predicting neuroscience results

MPS-Authors
/persons/resource/persons277194

Yáñez,  Felipe       
Max Planck Research Group In Silico Brain Sciences, Max Planck Institute for Neurobiology of Behavior – caesar, Max Planck Society;

External Resource
Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)

s41562-024-02046-9.pdf
(Publisher version), 4MB

Supplementary Material (public)
There is no public supplementary material available
Citation

Luo, X., Rechardt, A., Sun, G., Nejad, K. K., Yáñez, F., Yilmaz, B., et al. (2024). Large language models surpass human experts in predicting neuroscience results. Nature Human Behaviour, online ahead of print. doi:10.1038/s41562-024-02046-9.


Cite as: https://hdl.handle.net/21.11116/0000-0010-4B7C-0
Abstract
Scientific discoveries often hinge on synthesizing decades of research, a task that potentially outstrips human information processing capacities. Large language models (LLMs) offer a solution. LLMs trained on the vast scientific literature could potentially integrate noisy yet interrelated findings to forecast novel results better than human experts. Here, to evaluate this possibility, we created BrainBench, a forward-looking benchmark for predicting neuroscience results. We find that LLMs surpass experts in predicting experimental outcomes. BrainGPT, an LLM we tuned on the neuroscience literature, performed better yet. Like human experts, when LLMs indicated high confidence in their predictions, their responses were more likely to be correct, which presages a future where LLMs assist humans in making discoveries. Our approach is not neuroscience specific and is transferable to other knowledge-intensive endeavours.