{"id":"https://openalex.org/W7135240633","doi":"https://doi.org/10.48550/arxiv.2603.11838","title":"DatedGPT: Preventing Lookahead Bias in Large Language Models with Time-Aware Pretraining","display_name":"DatedGPT: Preventing Lookahead Bias in Large Language Models with Time-Aware Pretraining","publication_year":2026,"publication_date":"2026-03-12","ids":{"openalex":"https://openalex.org/W7135240633","doi":"https://doi.org/10.48550/arxiv.2603.11838"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.11838","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11838","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.11838","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128923070","display_name":"Yutong Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Yutong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101066425","display_name":"Raphael Tang","orcid":"https://orcid.org/0009-0007-2873-892X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Raphael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128957660","display_name":"Zhenyu Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Zhenyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129047630","display_name":"Wenxi Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Wenxi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128949523","display_name":"Yao Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Yao","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.22450000047683716,"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":0.22450000047683716,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.11460000276565552,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0828000009059906,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.659500002861023},{"id":"https://openalex.org/keywords/cutoff","display_name":"Cutoff","score":0.5133000016212463},{"id":"https://openalex.org/keywords/outcome","display_name":"Outcome (game theory)","score":0.5023000240325928},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.46549999713897705},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.39149999618530273},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.3305000066757202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7746000289916992},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.659500002861023},{"id":"https://openalex.org/C2778217198","wikidata":"https://www.wikidata.org/wiki/Q556977","display_name":"Cutoff","level":2,"score":0.5133000016212463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5062999725341797},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.5023000240325928},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.46549999713897705},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4474000036716461},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4009999930858612},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C101454708","wikidata":"https://www.wikidata.org/wiki/Q17106019","display_name":"Standard Model (mathematical formulation)","level":3,"score":0.3181000053882599},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28859999775886536},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.11838","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11838","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.11838","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11838","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1,35],"models":[2,36,72,77,167],"pretrained":[3],"on":[4,40],"internet-scale":[5],"data":[6,49,120],"risk":[7],"lookahead":[8,127,147],"bias":[9,148],"in":[10,62,149],"forecasting":[11],"tasks,":[12],"as":[13],"they":[14],"may":[15],"have":[16],"already":[17],"seen":[18],"the":[19,113,122,137],"true":[20],"outcome":[21,123],"during":[22,69],"training.":[23],"To":[24],"address":[25],"this,":[26],"we":[27],"present":[28],"DatedGPT,":[29],"a":[30,126],"family":[31],"of":[32,78,110,129,146],"twelve":[33],"1.3B-parameter":[34],"trained":[37],"from":[38,166],"scratch":[39],"approximately":[41],"100":[42],"billion":[43],"tokens":[44],"each":[45,63,86],"with":[46,56,75],"strict":[47],"annual":[48],"cutoffs":[50],"spanning":[51],"2013":[52],"to":[53,66,161],"2024,":[54],"together":[55],"DatedInstruct,":[57],"an":[58,106,154],"instruction":[59],"dataset":[60],"grounded":[61],"year's":[64],"documents":[65],"prevent":[67],"leakage":[68],"post-training.":[70],"The":[71,140],"are":[73],"competitive":[74],"open":[76],"similar":[79],"scale,":[80],"and":[81,163],"perplexity-based":[82],"probing":[83],"confirms":[84],"that":[85,158],"model's":[87],"knowledge":[88],"is":[89],"bounded":[90],"by":[91],"its":[92],"cutoff":[93,170],"year.":[94],"On":[95],"stock":[96],"return":[97],"prediction":[98],"over":[99],"61,000":[100],"firm-day":[101],"news":[102],"headlines,":[103],"DatedGPT-instruct":[104],"achieves":[105],"annualised":[107],"Sharpe":[108],"ratio":[109],"$3.20$":[111],"under":[112],"lookahead-bias-free":[114],"setup.":[115],"Lookahead-biased":[116],"models,":[117],"whose":[118],"training":[119],"covers":[121],"period,":[124],"add":[125],"premium":[128],"$26.4$":[130],"b.p.":[131],"per":[132],"standard":[133],"deviation,":[134],"significant":[135],"at":[136,173],"1%":[138],"level.":[139],"series":[141],"thus":[142],"enables":[143],"direct":[144],"analysis":[145],"financial":[150],"forecasting.":[151],"We":[152],"provide":[153],"interactive":[155],"web":[156],"demo":[157],"allows":[159],"users":[160],"query":[162],"compare":[164],"responses":[165],"across":[168],"different":[169],"years,":[171],"available":[172],"www.datedgpt.com.":[174]},"counts_by_year":[],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2026-03-14T00:00:00"}