Large language models surpass human experts in predicting neuroscience results

Xiaoliang Luo (), Akilles Rechardt, Guangzhi Sun, Kevin K. Nejad, Felipe Yáñez, Bati Yilmaz, Kangjoo Lee, Alexandra O. Cohen, Valentina Borghesani, Anton Pashkov, Daniele Marinazzo, Jonathan Nicholas, Alessandro Salatiello, Ilia Sucholutsky, Pasquale Minervini, Sepehr Razavi, Roberta Rocca, Elkhan Yusifov, Tereza Okalova, Nianlong Gu, Martin Ferianc, Mikail Khona, Kaustubh R. Patil, Pui-Shee Lee, Rui Mata, Nicholas E. Myers, Jennifer K. Bizley, Sebastian Musslick, Isil Poyraz Bilgin, Guiomar Niso, Justin M. Ales, Michael Gaebler, N. Apurva Ratan Murty, Leyla Loued-Khenissi, Anna Behler, Chloe M. Hall, Jessica Dafflon, Sherry Dongqi Bao and Bradley C. Love ()
Additional contact information
Xiaoliang Luo: University College London
Akilles Rechardt: University College London
Guangzhi Sun: University of Cambridge
Kevin K. Nejad: University of Oxford
Felipe Yáñez: Max Planck Institute for Neurobiology of Behavior – caesar
Bati Yilmaz: Bilkent University
Kangjoo Lee: Yale University School of Medicine
Alexandra O. Cohen: Emory University
Valentina Borghesani: Université de Genève
Anton Pashkov: Novosibirsk State Medical University
Daniele Marinazzo: Ghent University
Jonathan Nicholas: New York University
Alessandro Salatiello: University of Tübingen
Ilia Sucholutsky: Princeton University
Pasquale Minervini: University of Edinburgh
Sepehr Razavi: The University of Edinburgh
Roberta Rocca: Aarhus University
Elkhan Yusifov: University of Zurich
Tereza Okalova: University of Pennsylvania
Nianlong Gu: University of Zurich
Martin Ferianc: University College London
Mikail Khona: Massachusetts Institute of Technology
Kaustubh R. Patil: Research Centre Jülich
Pui-Shee Lee: Ludwig-Maximilians-University Munich
Rui Mata: University of Basel
Nicholas E. Myers: University of Nottingham
Jennifer K. Bizley: University College London
Sebastian Musslick: University of Osnabrück
Isil Poyraz Bilgin: Centre de recherche de l’Institut universitaire de gériatrie de Montréal
Guiomar Niso: CSIC
Justin M. Ales: University of St Andrews
Michael Gaebler: Max Planck Institute for Human Cognitive and Brain Sciences
N. Apurva Ratan Murty: Georgia Institute of Technology
Leyla Loued-Khenissi: Lausanne University Hospital
Anna Behler: The University of Newcastle
Chloe M. Hall: University Medical Center of the Johannes Gutenberg University
Jessica Dafflon: National Institute of Mental Health
Sherry Dongqi Bao: University of Zurich
Bradley C. Love: University College London

Nature Human Behaviour, 2025, vol. 9, issue 2, 305-315

Abstract: 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.

Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41562-024-02046-9 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:nathum:v:9:y:2025:i:2:d:10.1038_s41562-024-02046-9

Ordering information: This journal article can be ordered from
https://www.nature.com/nathumbehav/

DOI: 10.1038/s41562-024-02046-9

Access Statistics for this article

Nature Human Behaviour is currently edited by Stavroula Kousta

More articles in Nature Human Behaviour from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().