{"id":"https://openalex.org/W7166885524","doi":"https://doi.org/10.18653/v1/2026.findings-acl.481","title":"Bayesian Active Learning with Gaussian Processes Guided by LLM Relevance Scoring for Dense Passage Retrieval","display_name":"Bayesian Active Learning with Gaussian Processes Guided by LLM Relevance Scoring for Dense Passage Retrieval","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166885524","doi":"https://doi.org/10.18653/v1/2026.findings-acl.481"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.481","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.481","pdf_url":"https://aclanthology.org/2026.findings-acl.481.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.481.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100383368","display_name":"Junyoung Kim","orcid":"https://orcid.org/0000-0002-9007-7145"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junyoung Kim","raw_affiliation_strings":["Sungkyunkwan University , Republic of Korea ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University , Republic of Korea ,","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007047341","display_name":"Anton Korikov","orcid":"https://orcid.org/0009-0003-4487-9504"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Anton Korikov","raw_affiliation_strings":["University of Toronto , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto , Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139773712","display_name":"Jiazhou Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jiazhou Liang","raw_affiliation_strings":["University of Toronto , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto , Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007072228","display_name":"Justin Cui","orcid":"https://orcid.org/0009-0007-7376-1256"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Justin Cui","raw_affiliation_strings":["University of Toronto , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto , Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127900191","display_name":"Yifan Simon Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yifan Simon Liu","raw_affiliation_strings":["University of Toronto , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto , Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111351135","display_name":"Q. G. Wen","orcid":"https://orcid.org/0000-0002-5556-9419"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Qianfeng Wen","raw_affiliation_strings":["University of Toronto , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto , Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065406046","display_name":"Mark Zhao","orcid":"https://orcid.org/0000-0002-0706-5208"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mark Zhao","raw_affiliation_strings":["University of Toronto , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto , Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139749931","display_name":"Scott Sanner","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Scott Sanner","raw_affiliation_strings":["University of Toronto , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto , Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.85032295,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9884","last_page":"9898"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9046000242233276,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9046000242233276,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.03959999978542328,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.008500000461935997,"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/gaussian-process","display_name":"Gaussian process","score":0.564300000667572},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5593000054359436},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.5194000005722046},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.512499988079071},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.39480000734329224},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.38920000195503235},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37549999356269836}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6557000279426575},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6215999722480774},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.564300000667572},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5593000054359436},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.5194000005722046},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.512499988079071},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46389999985694885},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.39480000734329224},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.38920000195503235},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37549999356269836},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.3125},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.2671000063419342},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.25850000977516174}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.481","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.481","pdf_url":"https://aclanthology.org/2026.findings-acl.481.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2604.17906","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.17906","pdf_url":"https://arxiv.org/pdf/2604.17906","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.481","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.481","pdf_url":"https://aclanthology.org/2026.findings-acl.481.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1248055536","display_name":null,"funder_award_id":"RS-2022-00143911","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G2759505043","display_name":null,"funder_award_id":"RS-202400457882","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G2948537139","display_name":null,"funder_award_id":"RS-2022-00143911","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G5704809196","display_name":null,"funder_award_id":"RS-2024-00457882","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166885524.pdf","grobid_xml":"https://content.openalex.org/works/W7166885524.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"exhibit":[5],"exceptional":[6],"zero-shot":[7],"relevance":[8,51,71,83,96,112,151],"modeling,":[9],"their":[10],"high":[11],"computational":[12],"cost":[13],"necessitates":[14],"framing":[15],"passage":[16],"retrieval":[17],"as":[18],"a":[19,76,104],"budgetconstrained":[20],"global":[21,91],"optimization":[22],"problem.Existing":[23],"approaches":[24],"passively":[25],"rely":[26],"on":[27,110,163],"first-stage":[28],"dense":[29],"retrievers,":[30],"which":[31],"leads":[32],"to":[33,38,49,53,89],"two":[34,140],"limitations:":[35],"(1)":[36],"failing":[37,48],"retrieve":[39],"relevant":[40],"passages":[41,117],"in":[42],"semantically":[43],"distinct":[44],"clusters,":[45],"and":[46,139,148,153],"(2)":[47],"propagate":[50],"signals":[52,84],"the":[54,86,94,99,123,129,159],"broader":[55],"corpus.To":[56],"address":[57],"these":[58],"limitations,":[59],"we":[60],"propose":[61],"Bayesian":[62],"Active":[63],"Learning":[64],"with":[65,103,128],"Gaussian":[66,106],"Processes":[67],"guidEd":[68],"by":[69,120],"LLM":[70,82,111,141,155,161],"scoring":[72,119],"(BAGEL)":[73],"1":[74],",":[75],"novel":[77],"framework":[78],"that":[79,144],"propagates":[80],"sparse":[81],"across":[85,98,135],"embedding":[87,101],"space":[88,102],"guide":[90],"exploration.BAGEL":[92],"models":[93],"multimodal":[95],"distribution":[97],"entire":[100],"query-specific":[105],"Process":[107],"(GP)":[108],"based":[109],"scores.Subsequently,":[113],"it":[114],"iteratively":[115],"selects":[116],"for":[118],"strategically":[121],"balancing":[122],"exploitation":[124],"of":[125,131],"highconfidence":[126],"regions":[127],"exploration":[130],"uncertain":[132],"areas.Extensive":[133],"experiments":[134],"four":[136,165],"benchmark":[137],"datasets":[138],"backbones":[142],"demonstrate":[143],"BAGEL":[145],"effectively":[146],"explores":[147],"captures":[149],"complex":[150],"distributions":[152],"outperforms":[154],"reranking":[156],"methods":[157],"under":[158],"same":[160],"budget":[162],"all":[164],"datasets.":[166]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2026-07-02T00:00:00"}