{"id":"https://openalex.org/W4415798685","doi":"https://doi.org/10.52202/079017-0252","title":"CiteME: Can Language Models Accurately Cite Scientific Claims?","display_name":"CiteME: Can Language Models Accurately Cite Scientific Claims?","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4415798685","doi":"https://doi.org/10.52202/079017-0252"},"language":"en","primary_location":{"id":"doi:10.52202/079017-0252","doi":"https://doi.org/10.52202/079017-0252","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-0252","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.12861","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ori Press","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ori Press","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107077701","display_name":"Andreas Hochlehnert","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas Hochlehnert","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113274335","display_name":"Ameya Prabhu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ameya Prabhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108719787","display_name":"Vishaal Udandarao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vishaal Udandarao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058555772","display_name":"Ori Press","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ofir Press","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5061457780","display_name":"Matthias Bethge","orcid":"https://orcid.org/0000-0002-6417-7812","observed_orcids":["https://orcid.org/0000-0002-6417-7812","https://orcid.org/0009-0008-5601-6120"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthias Bethge","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1549,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.81904171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7847","last_page":"7877"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5952000021934509,"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":0.5952000021934509,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.05299999937415123,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12648","display_name":"Academic Writing and Publishing","score":0.05290000140666962,"subfield":{"id":"https://openalex.org/subfields/1207","display_name":"History and Philosophy of Science"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/citation-generation","display_name":"citation generation","score":0.6259999871253967},{"id":"https://openalex.org/keywords/language-models","display_name":"language models","score":0.7139999866485596},{"id":"https://openalex.org/keywords/scientific-claims","display_name":"scientific claims","score":0.9610000252723694},{"id":"https://openalex.org/keywords/citation-accuracy","display_name":"citation accuracy","score":0.5329999923706055},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.5450000166893005},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"information retrieval","score":0.33799999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6079000234603882},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4390999972820282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42890000343322754},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3686000108718872},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.29670000076293945},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.25690001249313354},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25110000371932983},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.23309999704360962}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/079017-0252","doi":"https://doi.org/10.52202/079017-0252","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-0252","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2407.12861","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.12861","pdf_url":"https://arxiv.org/pdf/2407.12861","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2407.12861","doi":"https://doi.org/10.48550/arxiv.2407.12861","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2407.12861","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2407.12861","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.12861","pdf_url":"https://arxiv.org/pdf/2407.12861","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1562512020","display_name":null,"funder_award_id":"206/4-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G53513784","display_name":"SFB 1233: Robustheit des Sehens  Prinzipien der Inferenz und neuronale Mechanismen","funder_award_id":"276693517","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7907426250","display_name":"EXC 2064: Maschinelles Lernen: Neue Perspektiven f\u00fcr die Wissenschaft","funder_award_id":"390727645","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G817300853","display_name":null,"funder_award_id":"SFB1233","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320315389","display_name":"Open Philanthropy Project","ror":"https://ror.org/004d1k391"},{"id":"https://openalex.org/F4320317967","display_name":"International Max Planck Research School for Environmental, Cellular and Molecular Microbiology","ror":null},{"id":"https://openalex.org/F4320319740","display_name":"Good Ventures Foundation","ror":"https://ror.org/01t5wp533"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320327553","display_name":"International Max Planck Research School for Advanced Methods in Process and Systems Engineering","ror":"https://ror.org/04hazks31"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415798685.pdf","grobid_xml":"https://content.openalex.org/works/W4415798685.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4396786040","https://openalex.org/W7166824498","https://openalex.org/W7170939351","https://openalex.org/W7160633014","https://openalex.org/W7139011239","https://openalex.org/W7140095479","https://openalex.org/W7133233293","https://openalex.org/W7168249844","https://openalex.org/W4402683414","https://openalex.org/W7128801722"],"abstract_inverted_index":{"Thousands":[0],"of":[1,72,81,142],"new":[2],"scientific":[3],"papers":[4],"are":[5],"published":[6],"each":[7,89],"month.":[8],"Such":[9],"information":[10],"overload":[11],"complicates":[12],"researcher":[13],"efforts":[14,59],"to":[15,24,51,60,179],"stay":[16],"current":[17],"with":[18,107],"the":[19,32,54,70,128,158],"state-of-the-art":[20],"as":[21,23,47,149],"well":[22],"verify":[25],"and":[26,104,113,135,175],"correctly":[27,52],"attribute":[28],"claims.":[29],"We":[30,57,116],"pose":[31],"following":[33],"research":[34,49,159],"question:":[35],"Given":[36],"a":[37,41,48,66,91,98,150,162],"text":[38,82],"excerpt":[39],"referencing":[40,90],"paper,":[42],"could":[43],"an":[44,123,140,169],"LM":[45,130,170],"act":[46],"assistant":[50],"identify":[53],"referenced":[55],"paper?":[56],"advance":[58],"answer":[61],"this":[62,118],"question":[63],"by":[64,120,168],"building":[65],"benchmark":[67],"that":[68,131],"evaluates":[69],"abilities":[71],"LMs":[73,103,108],"in":[74],"citation":[75],"attribution.":[76],"Our":[77],"benchmark,":[78],"CiteME,":[79],"consists":[80],"excerpts":[83],"from":[84],"recent":[85],"machine":[86],"learning":[87],"papers,":[88,137],"single":[92],"other":[93],"paper.":[94],"CiteME":[95,147],"use":[96],"reveals":[97],"large":[99],"gap":[100,119],"between":[101],"frontier":[102],"human":[105],"performance,":[106],"achieving":[109],"only":[110],"4.2-18.5%":[111],"accuracy":[112,141],"humans":[114],"69.7%.":[115],"close":[117],"introducing":[121],"CiteAgent,":[122],"autonomous":[124],"system":[125],"built":[126],"on":[127,144],"GPT-4o":[129],"can":[132,171],"also":[133],"search":[134],"read":[136],"which":[138],"achieves":[139],"35.3\\%":[143],"CiteME.":[145],"Overall,":[146],"serves":[148],"challenging":[151],"testbed":[152],"for":[153],"open-ended":[154],"claim":[155,166],"attribution,":[156],"driving":[157],"community":[160],"towards":[161],"future":[163],"where":[164],"any":[165],"made":[167],"be":[172,180],"automatically":[173],"verified":[174],"discarded":[176],"if":[177],"found":[178],"incorrect.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-10-15T10:00:46.086208","created_date":"2025-11-03T00:00:00"}