Scientific discoveries often hinge on synthesizing decades of research, a task that potentially outstrips human information processing capacities. Lar

Large language models surpass human experts in predicting neuroscience results

submited by

Style Pass

2024-11-27 14:30:10

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.

Keeping up with the exponentially increasing1 scientific literature is a superhuman challenge. Potentially disruptive findings go unnoticed in the deluge of articles2. Processing and integrating the myriad of relevant findings may already surpass humans’ abilities.