{"id":"https://openalex.org/W4385565351","doi":"https://doi.org/10.18653/v1/2023.acl-long.99","title":"Precise Zero-Shot Dense Retrieval without Relevance Labels","display_name":"Precise Zero-Shot Dense Retrieval without Relevance Labels","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385565351","doi":"https://doi.org/10.18653/v1/2023.acl-long.99"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.acl-long.99","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-long.99","pdf_url":"https://aclanthology.org/2023.acl-long.99.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":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2023.acl-long.99.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060885692","display_name":"Luyu Gao","orcid":"https://orcid.org/0009-0006-5806-3022"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luyu Gao","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021623012","display_name":"Xueguang Ma","orcid":"https://orcid.org/0000-0003-3430-4910"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xueguang Ma","raw_affiliation_strings":["School of Computer Science, University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082997975","display_name":"Jimmy Lin","orcid":"https://orcid.org/0000-0002-0661-7189"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jimmy Lin","raw_affiliation_strings":["School of Computer Science, University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009879041","display_name":"Jamie Callan","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jamie Callan","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":61.5606,"has_fulltext":true,"cited_by_count":295,"citation_normalized_percentile":{"value":0.99947396,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1762","last_page":"1777"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.998199999332428,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9980000257492065,"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/relevance","display_name":"Relevance (law)","score":0.814260721206665},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7555469870567322},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6476069092750549},{"id":"https://openalex.org/keywords/relevance-feedback","display_name":"Relevance feedback","score":0.6228581666946411},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6176925897598267},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.5900630950927734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5730956792831421},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5654224753379822},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5309125185012817},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5214661359786987},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5196603536605835},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.4736270308494568},{"id":"https://openalex.org/keywords/vector-space","display_name":"Vector space","score":0.4453596770763397},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4180775284767151},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4102504253387451},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.3505192995071411},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33027058839797974},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12684544920921326},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10574930906295776}],"concepts":[{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.814260721206665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7555469870567322},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6476069092750549},{"id":"https://openalex.org/C2779532271","wikidata":"https://www.wikidata.org/wiki/Q445558","display_name":"Relevance feedback","level":4,"score":0.6228581666946411},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6176925897598267},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.5900630950927734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5730956792831421},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5654224753379822},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5309125185012817},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5214661359786987},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5196603536605835},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.4736270308494568},{"id":"https://openalex.org/C13336665","wikidata":"https://www.wikidata.org/wiki/Q125977","display_name":"Vector space","level":2,"score":0.4453596770763397},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4180775284767151},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4102504253387451},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.3505192995071411},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33027058839797974},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12684544920921326},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10574930906295776},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.acl-long.99","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-long.99","pdf_url":"https://aclanthology.org/2023.acl-long.99.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":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.acl-long.99","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-long.99","pdf_url":"https://aclanthology.org/2023.acl-long.99.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":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.75}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385565351.pdf","grobid_xml":"https://content.openalex.org/works/W4385565351.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W2740492458","https://openalex.org/W2798329376","https://openalex.org/W2798658104","https://openalex.org/W2896457183","https://openalex.org/W2912924812","https://openalex.org/W2951434086","https://openalex.org/W2951534261","https://openalex.org/W2998702515","https://openalex.org/W3013710630","https://openalex.org/W3035390927","https://openalex.org/W3099700870","https://openalex.org/W3099977667","https://openalex.org/W3118668786","https://openalex.org/W3154670582","https://openalex.org/W3156636935","https://openalex.org/W3156836409","https://openalex.org/W3168875417","https://openalex.org/W3175111331","https://openalex.org/W3177813494","https://openalex.org/W3180230246","https://openalex.org/W3184918446","https://openalex.org/W3185146124","https://openalex.org/W3188983256","https://openalex.org/W3194157311","https://openalex.org/W3205068155","https://openalex.org/W3207095490","https://openalex.org/W3210277894","https://openalex.org/W3212725701","https://openalex.org/W4200635123","https://openalex.org/W4206121183","https://openalex.org/W4221166196","https://openalex.org/W4224308101","https://openalex.org/W4224438163","https://openalex.org/W4225591000","https://openalex.org/W4226146865","https://openalex.org/W4226278401","https://openalex.org/W4226399820","https://openalex.org/W4281562781","https://openalex.org/W4284669679","https://openalex.org/W4286987939","https://openalex.org/W4287780085","https://openalex.org/W4287827771","https://openalex.org/W4292779060","https://openalex.org/W4295601746","https://openalex.org/W4297162632","https://openalex.org/W4320813768","https://openalex.org/W4378189609","https://openalex.org/W4385570569","https://openalex.org/W4385570594","https://openalex.org/W4385573057","https://openalex.org/W4385573082","https://openalex.org/W4385573358","https://openalex.org/W4385573970"],"related_works":["https://openalex.org/W2156506451","https://openalex.org/W199666437","https://openalex.org/W2153892331","https://openalex.org/W193554","https://openalex.org/W2364053392","https://openalex.org/W373949808","https://openalex.org/W2369483736","https://openalex.org/W2063134459","https://openalex.org/W2109141752","https://openalex.org/W1493413336"],"abstract_inverted_index":{"While":[0],"dense":[1,23,135,151],"retrieval":[2,24],"has":[3],"been":[4],"shown":[5],"to":[6,18,48,68,128,159],"be":[7],"effective":[8,20],"and":[9,13,42,81,154,171],"efficient":[10],"across":[11,162],"tasks":[12,164],"languages,":[14],"it":[15],"remains":[16],"difficult":[17],"create":[19],"fully":[21],"zero-shot":[22,40,60],"systems":[25],"when":[26],"no":[27],"relevance":[28,76],"labels":[29],"are":[30,115],"available.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35,46],"recognize":[36],"the":[37,94,106,125,129,133,139,148],"difficulty":[38],"of":[39],"learning":[41],"encoding":[43],"relevance.":[44],"Instead,":[45],"propose":[47],"pivot":[49],"through":[50],"Hypothetical":[51],"Document":[52],"Embeddings":[53],"(HyDE).":[54],"Given":[55],"a":[56,70,103],"query,":[57],"HyDE":[58,145],"first":[59],"prompts":[61],"an":[62,86,97],"instruction-following":[63],"language":[64],"model":[65],"(e.g.,":[66,91,175],"InstructGPT)":[67],"generate":[69],"hypothetical":[71],"document.":[72],"The":[73],"document":[74,95,127],"captures":[75],"patterns":[77],"but":[78],"is":[79],"\"fake\"":[80],"may":[82],"contain":[83],"hallucinations.":[84,140],"Then,":[85],"unsupervised":[87,150],"contrastively":[88],"learned":[89],"encoder":[90],"Contriever)":[92],"encodes":[93],"into":[96],"embedding":[98,108],"vector.":[99],"This":[100,121],"vector":[101,119],"identifies":[102],"neighborhood":[104],"in":[105,172],"corpus":[107],"space,":[109],"from":[110],"which":[111],"similar":[112],"real":[113],"documents":[114],"retrieved":[116],"based":[117],"on":[118],"similarity.":[120],"second":[122],"step":[123],"grounds":[124],"generated":[126],"actual":[130],"corpus,":[131],"with":[132],"encoder's":[134],"bottleneck":[136],"filtering":[137],"out":[138],"Our":[141],"experiments":[142],"show":[143],"that":[144],"significantly":[146],"outperforms":[147],"state-ofthe-art":[149],"retriever":[152],"Contriever":[153],"shows":[155],"strong":[156],"performance":[157],"comparable":[158],"fine-tuned":[160],"retrievers":[161],"various":[163],"(e.g.":[165],"web":[166],"search,":[167],"QA,":[168],"fact":[169],"verification)":[170],"non-English":[173],"languages":[174],"sw,":[176],"ko,":[177],"ja,":[178],"bn).":[179]},"counts_by_year":[{"year":2026,"cited_by_count":115},{"year":2025,"cited_by_count":120},{"year":2024,"cited_by_count":45},{"year":2023,"cited_by_count":15}],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2025-10-10T00:00:00"}