Evidence item

Nature reports LLMs trained on broad human-produced scientific literature surpassed human experts on a novel neuroscience prediction benchmark. DIRECT_TEXT

Authenticity UNVERIFIED · extraction UNVERIFIED · independence group none (unreviewed) · created seq 10403

Source: Large language models surpass human experts in predicting neuroscience results · locator {} · excerpt hash sha256:08cf3ad2fbd9ddb0fdefb1b40481efb1043bf2aa116305c4e4afa8e699b24537

LLMs trained on the vast scientific literature could potentially integrate noisy yet interrelated findings to forecast novel results better than human experts. ... We find that LLMs surpass experts in predicting experimental outcomes.