001041321 001__ 1041321
001041321 005__ 20250512115732.0
001041321 0247_ $$2doi$$a10.1038/s41562-024-02046-9
001041321 0247_ $$2datacite_doi$$a10.34734/FZJ-2025-02220
001041321 0247_ $$2pmid$$a39604572
001041321 0247_ $$2WOS$$aWOS:001365146700001
001041321 037__ $$aFZJ-2025-02220
001041321 082__ $$a150
001041321 1001_ $$0P:(DE-HGF)0$$aLuo, Xiaoliang$$b0$$eCorresponding author
001041321 245__ $$aLarge language models surpass human experts in predicting neuroscience results
001041321 260__ $$aLondon$$bNature Research$$c2025
001041321 3367_ $$2DRIVER$$aarticle
001041321 3367_ $$2DataCite$$aOutput Types/Journal article
001041321 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1744792024_17200
001041321 3367_ $$2BibTeX$$aARTICLE
001041321 3367_ $$2ORCID$$aJOURNAL_ARTICLE
001041321 3367_ $$00$$2EndNote$$aJournal Article
001041321 520__ $$acientific 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.
001041321 536__ $$0G:(DE-HGF)POF4-5254$$a5254 - Neuroscientific Data Analytics and AI (POF4-525)$$cPOF4-525$$fPOF IV$$x0
001041321 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
001041321 7001_ $$0P:(DE-HGF)0$$aRechardt, Akilles$$b1
001041321 7001_ $$0P:(DE-HGF)0$$aSun, Guangzhi$$b2
001041321 7001_ $$0P:(DE-HGF)0$$aNejad, Kevin K.$$b3
001041321 7001_ $$0P:(DE-HGF)0$$aYáñez, Felipe$$b4
001041321 7001_ $$0P:(DE-HGF)0$$aYilmaz, Bati$$b5
001041321 7001_ $$0P:(DE-HGF)0$$aLee, Kangjoo$$b6
001041321 7001_ $$0P:(DE-HGF)0$$aCohen, Alexandra O.$$b7
001041321 7001_ $$0P:(DE-HGF)0$$aBorghesani, Valentina$$b8
001041321 7001_ $$0P:(DE-HGF)0$$aPashkov, Anton$$b9
001041321 7001_ $$0P:(DE-HGF)0$$aMarinazzo, Daniele$$b10
001041321 7001_ $$0P:(DE-HGF)0$$aNicholas, Jonathan$$b11
001041321 7001_ $$0P:(DE-HGF)0$$aSalatiello, Alessandro$$b12
001041321 7001_ $$0P:(DE-HGF)0$$aSucholutsky, Ilia$$b13
001041321 7001_ $$0P:(DE-HGF)0$$aMinervini, Pasquale$$b14
001041321 7001_ $$0P:(DE-HGF)0$$aRazavi, Sepehr$$b15
001041321 7001_ $$0P:(DE-HGF)0$$aRocca, Roberta$$b16
001041321 7001_ $$0P:(DE-HGF)0$$aYusifov, Elkhan$$b17
001041321 7001_ $$0P:(DE-HGF)0$$aOkalova, Tereza$$b18
001041321 7001_ $$0P:(DE-HGF)0$$aGu, Nianlong$$b19
001041321 7001_ $$0P:(DE-HGF)0$$aFerianc, Martin$$b20
001041321 7001_ $$0P:(DE-HGF)0$$aKhona, Mikail$$b21
001041321 7001_ $$0P:(DE-Juel1)172843$$aPatil, Kaustubh R.$$b22
001041321 7001_ $$0P:(DE-HGF)0$$aLee, Pui-Shee$$b23
001041321 7001_ $$0P:(DE-HGF)0$$aMata, Rui$$b24
001041321 7001_ $$0P:(DE-HGF)0$$aMyers, Nicholas E.$$b25
001041321 7001_ $$0P:(DE-HGF)0$$aBizley, Jennifer K.$$b26
001041321 7001_ $$0P:(DE-HGF)0$$aMusslick, Sebastian$$b27
001041321 7001_ $$0P:(DE-HGF)0$$aBilgin, Isil Poyraz$$b28
001041321 7001_ $$0P:(DE-HGF)0$$aNiso, Guiomar$$b29
001041321 7001_ $$0P:(DE-HGF)0$$aAles, Justin M.$$b30
001041321 7001_ $$0P:(DE-HGF)0$$aGaebler, Michael$$b31
001041321 7001_ $$0P:(DE-HGF)0$$aRatan Murty, N. Apurva$$b32
001041321 7001_ $$0P:(DE-HGF)0$$aLoued-Khenissi, Leyla$$b33
001041321 7001_ $$0P:(DE-HGF)0$$aBehler, Anna$$b34
001041321 7001_ $$0P:(DE-HGF)0$$aHall, Chloe M.$$b35
001041321 7001_ $$0P:(DE-HGF)0$$aDafflon, Jessica$$b36
001041321 7001_ $$0P:(DE-HGF)0$$aBao, Sherry Dongqi$$b37
001041321 7001_ $$0P:(DE-HGF)0$$aLove, Bradley C.$$b38
001041321 773__ $$0PERI:(DE-600)2885046-4$$a10.1038/s41562-024-02046-9$$gVol. 9, no. 2, p. 305 - 315$$n2$$p305 - 315$$tNature human behaviour$$v9$$x2397-3374$$y2025
001041321 8564_ $$uhttps://juser.fz-juelich.de/record/1041321/files/s41562-024-02046-9.pdf$$yOpenAccess
001041321 909CO $$ooai:juser.fz-juelich.de:1041321$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
001041321 9101_ $$0I:(DE-HGF)0$$6P:(DE-HGF)0$$a Department of Experimental Psychology, University College London$$b0
001041321 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)172843$$aForschungszentrum Jülich$$b22$$kFZJ
001041321 9131_ $$0G:(DE-HGF)POF4-525$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5254$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vDecoding Brain Organization and Dysfunction$$x0
001041321 9141_ $$y2025
001041321 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2024-12-05
001041321 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2024-12-05
001041321 915__ $$0StatID:(DE-HGF)0130$$2StatID$$aDBCoverage$$bSocial Sciences Citation Index$$d2024-12-05
001041321 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
001041321 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bNAT HUM BEHAV : 2022$$d2024-12-05
001041321 915__ $$0StatID:(DE-HGF)1180$$2StatID$$aDBCoverage$$bCurrent Contents - Social and Behavioral Sciences$$d2024-12-05
001041321 915__ $$0StatID:(DE-HGF)1030$$2StatID$$aDBCoverage$$bCurrent Contents - Life Sciences$$d2024-12-05
001041321 915__ $$0StatID:(DE-HGF)3003$$2StatID$$aDEAL Nature$$d2024-12-05$$wger
001041321 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2024-12-05
001041321 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2024-12-05
001041321 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001041321 915__ $$0StatID:(DE-HGF)9925$$2StatID$$aIF >= 25$$bNAT HUM BEHAV : 2022$$d2024-12-05
001041321 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2024-12-05
001041321 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2024-12-05
001041321 9201_ $$0I:(DE-Juel1)INM-7-20090406$$kINM-7$$lGehirn & Verhalten$$x0
001041321 980__ $$ajournal
001041321 980__ $$aVDB
001041321 980__ $$aUNRESTRICTED
001041321 980__ $$aI:(DE-Juel1)INM-7-20090406
001041321 9801_ $$aFullTexts