{"id":"https://openalex.org/W7163391394","doi":"https://doi.org/10.48550/arxiv.2606.03080","title":"Regret Pre-training: Bridging Prior and Posterior Views for Enhanced Knowledge Grounding","display_name":"Regret Pre-training: Bridging Prior and Posterior Views for Enhanced Knowledge Grounding","publication_year":2026,"publication_date":"2026-06-02","ids":{"openalex":"https://openalex.org/W7163391394","doi":"https://doi.org/10.48550/arxiv.2606.03080"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.03080","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03080","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,"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":null,"license_id":null,"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.2606.03080","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137763088","display_name":"Mingkuan Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Mingkuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137636657","display_name":"Xiayu Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Xiayu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137785399","display_name":"Wentao Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Wentao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137693638","display_name":"Suquan Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Suquan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137735775","display_name":"Jiaxuan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jiaxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137719527","display_name":"Xiaoyan Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Xiaoyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137765575","display_name":"Xin Lai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lai, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137764094","display_name":"Jiayin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jiayin","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3840999901294708,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3840999901294708,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10028","display_name":"Topic Modeling","score":0.11559999734163284,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.10970000177621841,"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/regret","display_name":"Regret","score":0.8907999992370605},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.6384000182151794},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5098000168800354},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.4984999895095825},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.4878999888896942},{"id":"https://openalex.org/keywords/causal-chain","display_name":"Causal chain","score":0.4812999963760376},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.42969998717308044},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4034000039100647}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8907999992370605},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6384000182151794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6284999847412109},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5332000255584717},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5098000168800354},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.4984999895095825},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4878999888896942},{"id":"https://openalex.org/C79897977","wikidata":"https://www.wikidata.org/wiki/Q5054568","display_name":"Causal chain","level":2,"score":0.4812999963760376},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43290001153945923},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4034000039100647},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3124000132083893},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31060001254081726},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2630999982357025},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C3020402766","wikidata":"https://www.wikidata.org/wiki/Q104376712","display_name":"Prior information","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2572999894618988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.03080","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03080","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,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.03080","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03080","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,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8565616607666016,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Causal":[0],"language":[1,67],"models":[2],"factorize":[3],"sequence":[4],"probabilities":[5],"using":[6],"only":[7,168],"preceding":[8],"context,":[9],"leaving":[10],"future":[11,103],"information":[12],"unexploited":[13],"during":[14],"training":[15,21,63,126,175],"despite":[16],"its":[17],"availability":[18],"in":[19,32,46],"the":[20,33,75,86,95,112,133,145],"data.":[22],"This":[23],"paper":[24],"introduces":[25,162],"Regret":[26],"Pre-training,":[27],"a":[28,43,48,53,58,70],"self-supervised":[29],"framework":[30,41,161],"grounded":[31],"Learning":[34],"Using":[35],"Privileged":[36],"Information":[37],"(LUPI)":[38],"paradigm.":[39],"The":[40,62,160],"employs":[42],"dual-view":[44],"architecture":[45],"which":[47,98,106],"single":[49],"model":[50],"generates":[51],"both":[52,129],"causal":[54,87],"Student":[55],"distribution":[56],"and":[57,140,166],"future-conditioned":[59],"Teacher":[60],"distribution.":[61],"objective":[64],"augments":[65],"standard":[66],"modeling":[68],"with":[69,111],"regret":[71],"loss":[72],"that":[73,128],"minimizes":[74],"KL":[76],"divergence":[77],"from":[78],"teacher":[79,92],"to":[80,85],"student,":[81],"transferring":[82],"future-aware":[83],"signals":[84],"representations.":[88],"We":[89],"investigate":[90],"two":[91],"configurations":[93,130],"on":[94,108,117],"OLMoE-1B-7B":[96],"architecture:LocalRegret,":[97],"extends":[99],"attention":[100],"by":[101,153],"one":[102,169],"token,":[104],"andGlobalRegret,":[105],"conditions":[107],"bidirectional":[109],"context":[110],"target":[113],"position":[114],"masked.":[115],"Experiments":[116],"nine":[118],"downstream":[119],"tasks":[120],"following":[121],"4":[122],"billion":[123],"tokens":[124],"of":[125],"demonstrate":[127],"consistently":[131],"outperform":[132],"baseline.":[134],"On":[135],"average,GlobalRegret":[136],"andLocalRegret":[137],"achieve":[138],"33.9%":[139],"32.2%":[141],"accuracy":[142],"respectively,":[143],"surpassing":[144],"baseline's":[146],"30.2%.":[147],"Most":[148],"notably,GlobalRegret":[149],"improves":[150],"BoolQ":[151],"performance":[152],"18.1":[154],"percentage":[155],"points":[156],"(61.0%":[157],"vs":[158],"42.9%).":[159],"no":[163],"additional":[164],"parameters":[165],"requires":[167],"extra":[170],"inference-mode":[171],"forward":[172],"pass":[173],"per":[174],"step.":[176]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-04T00:00:00"}