{"id":"https://openalex.org/W4402827393","doi":"https://doi.org/10.1038/s41586-024-07930-y","title":"Larger and more instructable language models become less reliable","display_name":"Larger and more instructable language models become less reliable","publication_year":2024,"publication_date":"2024-09-25","ids":{"openalex":"https://openalex.org/W4402827393","doi":"https://doi.org/10.1038/s41586-024-07930-y","pmid":"https://pubmed.ncbi.nlm.nih.gov/39322679"},"language":"en","primary_location":{"id":"doi:10.1038/s41586-024-07930-y","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41586-024-07930-y","pdf_url":"https://www.nature.com/articles/s41586-024-07930-y.pdf","source":{"id":"https://openalex.org/S137773608","display_name":"Nature","issn_l":"0028-0836","issn":["0028-0836","1476-4687"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.nature.com/articles/s41586-024-07930-y.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034619858","display_name":"Lexin Zhou","orcid":"https://orcid.org/0000-0003-1161-4270"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I4210131846","display_name":"Artificial Intelligence Research Institute","ror":"https://ror.org/03c0ach84","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210131846"]},{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES","GB"],"is_corresponding":false,"raw_author_name":"Lexin Zhou","raw_affiliation_strings":["University of Cambridge, Cambridge, UK","Valencian Research Institute for Artificial Intelligence (VRAIN), Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain"],"raw_orcid":"https://orcid.org/0000-0003-1161-4270","affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Valencian Research Institute for Artificial Intelligence (VRAIN), Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain","institution_ids":["https://openalex.org/I4210131846","https://openalex.org/I60053951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054592192","display_name":"Wout Schellaert","orcid":"https://orcid.org/0000-0002-9182-4747"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I2802641067","display_name":"Leverhulme Trust","ror":"https://ror.org/012mzw131","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802641067"]},{"id":"https://openalex.org/I4210131846","display_name":"Artificial Intelligence Research Institute","ror":"https://ror.org/03c0ach84","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210131846"]},{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES","GB"],"is_corresponding":false,"raw_author_name":"Wout Schellaert","raw_affiliation_strings":["Leverhulme Centre for the Future of Intelligence, University of Cambridge, Cambridge, UK","Valencian Research Institute for Artificial Intelligence (VRAIN), Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain"],"raw_orcid":"https://orcid.org/0000-0002-9182-4747","affiliations":[{"raw_affiliation_string":"Leverhulme Centre for the Future of Intelligence, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749","https://openalex.org/I2802641067"]},{"raw_affiliation_string":"Valencian Research Institute for Artificial Intelligence (VRAIN), Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain","institution_ids":["https://openalex.org/I4210131846","https://openalex.org/I60053951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051725651","display_name":"Fernando Mart\u00ednez\u2010Plumed","orcid":"https://orcid.org/0000-0003-2902-6477"},"institutions":[{"id":"https://openalex.org/I4210131846","display_name":"Artificial Intelligence Research Institute","ror":"https://ror.org/03c0ach84","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210131846"]},{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Fernando Mart\u00ednez-Plumed","raw_affiliation_strings":["ValGRAI, Valencia, Spain","Valencian Research Institute for Artificial Intelligence (VRAIN), Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain"],"raw_orcid":"https://orcid.org/0000-0003-2902-6477","affiliations":[{"raw_affiliation_string":"ValGRAI, Valencia, Spain","institution_ids":[]},{"raw_affiliation_string":"Valencian Research Institute for Artificial Intelligence (VRAIN), Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain","institution_ids":["https://openalex.org/I4210131846","https://openalex.org/I60053951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093047845","display_name":"Yael Moros-Daval","orcid":"https://orcid.org/0000-0001-5442-2055"},"institutions":[{"id":"https://openalex.org/I4210131846","display_name":"Artificial Intelligence Research Institute","ror":"https://ror.org/03c0ach84","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210131846"]},{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Yael Moros-Daval","raw_affiliation_strings":["Valencian Research Institute for Artificial Intelligence (VRAIN), Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain"],"raw_orcid":"https://orcid.org/0000-0001-5442-2055","affiliations":[{"raw_affiliation_string":"Valencian Research Institute for Artificial Intelligence (VRAIN), Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain","institution_ids":["https://openalex.org/I4210131846","https://openalex.org/I60053951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050804466","display_name":"C\u00e8sar Ferri","orcid":"https://orcid.org/0000-0002-8975-1120"},"institutions":[{"id":"https://openalex.org/I4210131846","display_name":"Artificial Intelligence Research Institute","ror":"https://ror.org/03c0ach84","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210131846"]},{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"C\u00e8sar Ferri","raw_affiliation_strings":["ValGRAI, Valencia, Spain","Valencian Research Institute for Artificial Intelligence (VRAIN), Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain"],"raw_orcid":"https://orcid.org/0000-0002-8975-1120","affiliations":[{"raw_affiliation_string":"ValGRAI, Valencia, Spain","institution_ids":[]},{"raw_affiliation_string":"Valencian Research Institute for Artificial Intelligence (VRAIN), Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain","institution_ids":["https://openalex.org/I4210131846","https://openalex.org/I60053951"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029864546","display_name":"Jos\u00e9 Hern\u00e1ndez\u2010Orallo","orcid":"https://orcid.org/0000-0001-9746-7632"},"institutions":[{"id":"https://openalex.org/I1317635190","display_name":"Valve (United States)","ror":"https://ror.org/020esap58","country_code":"US","type":"company","lineage":["https://openalex.org/I1317635190"]},{"id":"https://openalex.org/I2802641067","display_name":"Leverhulme Trust","ror":"https://ror.org/012mzw131","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802641067"]},{"id":"https://openalex.org/I4210131846","display_name":"Artificial Intelligence Research Institute","ror":"https://ror.org/03c0ach84","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210131846"]},{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES","GB","US"],"is_corresponding":true,"raw_author_name":"Jos\u00e9 Hern\u00e1ndez-Orallo","raw_affiliation_strings":["Leverhulme Centre for the Future of Intelligence, University of Cambridge, Cambridge, UK. jorallo@upv.es","ValGRAI, Valencia, Spain. jorallo@upv.es","Valencian Research Institute for Artificial Intelligence (VRAIN), Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain. jorallo@upv.es"],"raw_orcid":"https://orcid.org/0000-0001-9746-7632","affiliations":[{"raw_affiliation_string":"Leverhulme Centre for the Future of Intelligence, University of Cambridge, Cambridge, UK. jorallo@upv.es","institution_ids":["https://openalex.org/I2802641067"]},{"raw_affiliation_string":"ValGRAI, Valencia, Spain. jorallo@upv.es","institution_ids":["https://openalex.org/I1317635190"]},{"raw_affiliation_string":"Valencian Research Institute for Artificial Intelligence (VRAIN), Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain. jorallo@upv.es","institution_ids":["https://openalex.org/I4210131846","https://openalex.org/I60053951"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5029864546"],"corresponding_institution_ids":["https://openalex.org/I1317635190","https://openalex.org/I2802641067","https://openalex.org/I4210131846","https://openalex.org/I60053951"],"apc_list":{"value":11690,"currency":"USD","value_usd":11690},"apc_paid":{"value":11690,"currency":"USD","value_usd":11690},"fwci":41.92,"has_fulltext":true,"cited_by_count":173,"citation_normalized_percentile":{"value":0.99875004,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"634","issue":"8032","first_page":"61","last_page":"68"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9789000153541565,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bespoke","display_name":"Bespoke","score":0.7973753213882446},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7591477632522583},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6209096312522888},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6041749715805054},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5717422962188721},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5425527691841125},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.47828420996665955},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.43635815382003784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43466588854789734},{"id":"https://openalex.org/keywords/human-language","display_name":"Human language","score":0.41906070709228516},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35382407903671265},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3449524939060211},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2065485715866089},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11846810579299927},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07737287878990173}],"concepts":[{"id":"https://openalex.org/C44210515","wikidata":"https://www.wikidata.org/wiki/Q16968978","display_name":"Bespoke","level":2,"score":0.7973753213882446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7591477632522583},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6209096312522888},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6041749715805054},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5717422962188721},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5425527691841125},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.47828420996665955},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.43635815382003784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43466588854789734},{"id":"https://openalex.org/C2993724205","wikidata":"https://www.wikidata.org/wiki/Q315","display_name":"Human language","level":2,"score":0.41906070709228516},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35382407903671265},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3449524939060211},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2065485715866089},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11846810579299927},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07737287878990173},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005246","descriptor_name":"Feedback","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005246","descriptor_name":"Feedback","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005246","descriptor_name":"Feedback","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005246","descriptor_name":"Feedback","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005246","descriptor_name":"Feedback","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005246","descriptor_name":"Feedback","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008962","descriptor_name":"Models, Theoretical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012107","descriptor_name":"Research Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012107","descriptor_name":"Research Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012107","descriptor_name":"Research Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012107","descriptor_name":"Research Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012107","descriptor_name":"Research Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012107","descriptor_name":"Research Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.1038/s41586-024-07930-y","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41586-024-07930-y","pdf_url":"https://www.nature.com/articles/s41586-024-07930-y.pdf","source":{"id":"https://openalex.org/S137773608","display_name":"Nature","issn_l":"0028-0836","issn":["0028-0836","1476-4687"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature","raw_type":"journal-article"},{"id":"pmid:39322679","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39322679","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature","raw_type":null},{"id":"pmh:oai:riunet.upv.es:10251/214533","is_oa":true,"landing_page_url":"http://hdl.handle.net/10251/214533","pdf_url":null,"source":{"id":"https://openalex.org/S4306401500","display_name":"RiuNet (Politechnical University of Valencia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60053951","host_organization_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","host_organization_lineage":["https://openalex.org/I60053951"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pubmedcentral.nih.gov:11446866","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11446866","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11446866/pdf/41586_2024_Article_7930.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Nature","raw_type":"Text"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/374426","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/374426","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/10c5a402-8c32-4200-8ee7-c9bd6bc98cf3/download","source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:RePEc:nat:nature:v:634:y:2024:i:8032:d:10.1038_s41586-024-07930-y","is_oa":false,"landing_page_url":"https://www.nature.com/articles/s41586-024-07930-y","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1038/s41586-024-07930-y","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41586-024-07930-y","pdf_url":"https://www.nature.com/articles/s41586-024-07930-y.pdf","source":{"id":"https://openalex.org/S137773608","display_name":"Nature","issn_l":"0028-0836","issn":["0028-0836","1476-4687"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1411269697","display_name":null,"funder_award_id":"CIPROM/2022/6","funder_id":"https://openalex.org/F4320321864","funder_display_name":"Generalitat Valenciana"},{"id":"https://openalex.org/G1622782223","display_name":null,"funder_award_id":"MCIN/AEI/10","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G2628364946","display_name":null,"funder_award_id":"H2020","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G265104915","display_name":null,"funder_award_id":"EC H2020","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G3480869486","display_name":null,"funder_award_id":"13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G3492592289","display_name":null,"funder_award_id":"PID2021-122830OB-C42","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G3827193553","display_name":null,"funder_award_id":"952215","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G4909719005","display_name":null,"funder_award_id":"PID2021-122830OB-C42","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G5080475149","display_name":null,"funder_award_id":"10.13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G6033112984","display_name":null,"funder_award_id":"MICIU/AEI/10","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G683931746","display_name":null,"funder_award_id":"H2020","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7084143925","display_name":null,"funder_award_id":"AEI/10","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7535663061","display_name":null,"funder_award_id":"AEI/10.","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320315389","display_name":"Open Philanthropy Project","ror":"https://ror.org/004d1k391"},{"id":"https://openalex.org/F4320321864","display_name":"Generalitat Valenciana","ror":"https://ror.org/0097mvx21"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402827393.pdf","grobid_xml":"https://content.openalex.org/works/W4402827393.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W1580108238","https://openalex.org/W1988272543","https://openalex.org/W2007563658","https://openalex.org/W2085302711","https://openalex.org/W2171843165","https://openalex.org/W2890894339","https://openalex.org/W2981852735","https://openalex.org/W2984353433","https://openalex.org/W3128442340","https://openalex.org/W3185341429","https://openalex.org/W3196731672","https://openalex.org/W3205068155","https://openalex.org/W3217791123","https://openalex.org/W4224275713","https://openalex.org/W4225591000","https://openalex.org/W4226278401","https://openalex.org/W4294235612","https://openalex.org/W4300027192","https://openalex.org/W4308244210","https://openalex.org/W4308760226","https://openalex.org/W4310529830","https://openalex.org/W4318464200","https://openalex.org/W4320710261","https://openalex.org/W4322718191","https://openalex.org/W4323655724","https://openalex.org/W4365445794","https://openalex.org/W4367188881","https://openalex.org/W4367365458","https://openalex.org/W4380355772","https://openalex.org/W4381889417","https://openalex.org/W4382318449","https://openalex.org/W4384561707","https://openalex.org/W4384918448","https://openalex.org/W4385571124","https://openalex.org/W4385572845","https://openalex.org/W4386977707","https://openalex.org/W4388787841","https://openalex.org/W4389991792","https://openalex.org/W4392504765","https://openalex.org/W4392681182","https://openalex.org/W4392929783","https://openalex.org/W4399576866","https://openalex.org/W6778883912","https://openalex.org/W6839548382","https://openalex.org/W6847076894","https://openalex.org/W6847753483","https://openalex.org/W6851711695","https://openalex.org/W6851775633","https://openalex.org/W6854308750","https://openalex.org/W6893024061","https://openalex.org/W7073593060"],"related_works":["https://openalex.org/W2181465263","https://openalex.org/W3093969907","https://openalex.org/W3202725889","https://openalex.org/W2232750048","https://openalex.org/W2212726445","https://openalex.org/W4244794230","https://openalex.org/W4389712339","https://openalex.org/W2806540758","https://openalex.org/W2494533090","https://openalex.org/W3082526343"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"prevailing":[2],"methods":[3],"to":[4,135,161],"make":[5],"large":[6,54],"language":[7,55,76],"models":[8,56,97,125,133],"more":[9,52,144],"powerful":[10],"and":[11,27,32,51,71,173,196],"amenable":[12],"have":[13,58],"been":[14],"based":[15],"on":[16,148],"continuous":[17],"scaling":[18],"up":[19,35],"(that":[20],"is,":[21],"increasing":[22],"their":[23],"size,":[24],"data":[25],"volume":[26],"computational":[28],"resources":[29],"1":[30],")":[31],"bespoke":[33],"shaping":[34],"(including":[36],"post-filtering":[37],"2,3":[38],",":[39],"fine":[40],"tuning":[41],"or":[42,113],"use":[43],"of":[44,74,102,165,178,198,211],"human":[45,86,114,152],"feedback":[46],"4,5":[47],").":[48],"However,":[49],"larger":[50],"instructable":[53],"may":[57],"become":[59],"less":[60],"reliable.":[61],"By":[62],"studying":[63],"the":[64,92,108,118,166,187,194],"relationship":[65],"between":[66],"difficulty":[67,104,182],"concordance,":[68],"task":[69],"avoidance":[70],"prompting":[72],"stability":[73,160],"several":[75],"model":[77,109],"families,":[78],"here":[79],"we":[80,157],"show":[81],"that":[82,123,151,159],"easy":[83,90],"instances":[84],"for":[85,91,189,206],"participants":[87],"are":[88],"also":[89,121],"models,":[93],"but":[94,130,176],"scaled-up,":[95,131],"shaped-up":[96,132],"do":[98],"not":[99,111],"secure":[100],"areas":[101,205],"low":[103],"in":[105,193,203],"which":[106,207],"either":[107],"does":[110],"err":[112],"supervision":[115],"can":[116],"spot":[117],"errors.":[119],"We":[120],"find":[122],"early":[124],"often":[126],"avoid":[127],"user":[128],"questions":[129,150],"tend":[134],"give":[136],"an":[137],"apparently":[138],"sensible":[139],"yet":[140],"wrong":[141],"answer":[142],"much":[143],"often,":[145],"including":[146],"errors":[147,212],"difficult":[149],"supervisors":[153],"frequently":[154],"overlook.":[155],"Moreover,":[156],"observe":[158],"different":[162],"natural":[163],"phrasings":[164],"same":[167],"question":[168],"is":[169,213],"improved":[170],"by":[171],"scaling-up":[172],"shaping-up":[174],"interventions,":[175],"pockets":[177],"variability":[179],"persist":[180],"across":[181],"levels.":[183],"These":[184],"findings":[185],"highlight":[186],"need":[188],"a":[190,208],"fundamental":[191],"shift":[192],"design":[195],"development":[197],"general-purpose":[199],"artificial":[200],"intelligence,":[201],"particularly":[202],"high-stakes":[204],"predictable":[209],"distribution":[210],"paramount.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":65},{"year":2025,"cited_by_count":98},{"year":2024,"cited_by_count":10}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-10-10T00:00:00"}
