{"id":"https://openalex.org/W4396843604","doi":"https://doi.org/10.1145/3589335.3651945","title":"A Case Study of Enhancing Sparse Retrieval using LLMs","display_name":"A Case Study of Enhancing Sparse Retrieval using LLMs","publication_year":2024,"publication_date":"2024-05-12","ids":{"openalex":"https://openalex.org/W4396843604","doi":"https://doi.org/10.1145/3589335.3651945"},"language":"en","primary_location":{"id":"doi:10.1145/3589335.3651945","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3651945","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651945","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651945","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5097740927","display_name":"Michael Antonios Kruse Ayoub","orcid":"https://orcid.org/0009-0008-6160-0508"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Michael Antonios Kruse Ayoub","raw_affiliation_strings":["University of Copenhagen, Copenhagen, Denmark"],"raw_orcid":"https://orcid.org/0009-0008-6160-0508","affiliations":[{"raw_affiliation_string":"University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101809111","display_name":"Zhan Su","orcid":"https://orcid.org/0000-0001-5189-9165"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Zhan Su","raw_affiliation_strings":["University of Copenhagen, Copenhagen, Denmark"],"raw_orcid":"https://orcid.org/0000-0001-5189-9165","affiliations":[{"raw_affiliation_string":"University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026465666","display_name":"Qiuchi Li","orcid":"https://orcid.org/0000-0002-8219-0869"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Qiuchi Li","raw_affiliation_strings":["University of Copenhagen, Copenhagen, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-8219-0869","affiliations":[{"raw_affiliation_string":"University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I124055696"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9164,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7781681,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1609","last_page":"1615"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9944999814033508,"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":0.9944999814033508,"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/T11719","display_name":"Data Quality and Management","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9925000071525574,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5846181511878967},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36034440994262695}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5846181511878967},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36034440994262695}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3589335.3651945","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3651945","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651945","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/937b5677-4a91-4849-873d-b9bd67e4ac8d","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/937b5677-4a91-4849-873d-b9bd67e4ac8d","pdf_url":"https://curis.ku.dk/ws/files/414751349/A_Case_Study_of_Enhancing.pdf","source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"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":"Ayoub , M A K , Su , Z & Li , Q 2024 , A Case Study of Enhancing Sparse Retrieval using LLMs . in WWW 2024 Companion - Companion Proceedings of the ACM Web Conference . Association for Computing Machinery, Inc. , pp. 1609-1615 , 33rd ACM Web Conference, WWW 2024 , Singapore , Singapore , 13/05/2024 . https://doi.org/10.1145/3589335.3651945","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.1145/3589335.3651945","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3651945","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651945","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4396843604.pdf"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W173119166","https://openalex.org/W1548930048","https://openalex.org/W1776265914","https://openalex.org/W1987996059","https://openalex.org/W1993692165","https://openalex.org/W2043909051","https://openalex.org/W2065096648","https://openalex.org/W2105157020","https://openalex.org/W2117473841","https://openalex.org/W2963680465","https://openalex.org/W2981852735","https://openalex.org/W3154280800","https://openalex.org/W3176182290","https://openalex.org/W4225496273","https://openalex.org/W4236329806","https://openalex.org/W4252076394","https://openalex.org/W4288089799","https://openalex.org/W4367189613"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"While":[0],"dense":[1],"retrieval":[2,9,27,52,75,84,128],"methods":[3,147],"have":[4],"made":[5],"significant":[6],"advancements,":[7],"sparse":[8,26,51,83,146],"techniques":[10],"continue":[11],"to":[12,67,81,110],"offer":[13],"advantages":[14],"in":[15,25,169,200],"terms":[16,168],"of":[17,56,125,165,184],"interpretability":[18],"and":[19,88,172],"generalizability.":[20],"However,":[21],"query-document":[22],"term":[23,163],"mismatch":[24],"persists,":[28],"rendering":[29],"it":[30],"infeasible":[31],"for":[32,73,145],"many":[33],"practical":[34],"applications.":[35],"Recent":[36],"research":[37],"has":[38],"shown":[39],"that":[40,48,140,181,189],"Large":[41],"Language":[42],"Models":[43],"(LLMs)":[44],"hold":[45],"relevant":[46,174],"information":[47,74,127,151],"can":[49,142,156],"enhance":[50,82],"through":[53],"the":[54,94,116,149,154,159,162,166,173,182],"application":[55],"prompt":[57],"engineering.":[58],"In":[59,91,176],"this":[60,65],"paper,":[61],"we":[62,78,179],"build":[63],"upon":[64],"concept":[66],"explore":[68],"various":[69],"strategies":[70],"employing":[71],"LLMs":[72,80,107,141,155,185],"purposes.":[76],"Specifically,":[77],"utilize":[79],"by":[85,99,153],"query":[86,89,92,96,105,171],"rewriting":[87],"expansion.":[90],"rewriting,":[93],"original":[95,117],"is":[97,186],"refined":[98],"creating":[100],"several":[101],"new":[102],"queries.":[103],"For":[104],"expansion,":[106],"are":[108],"employed":[109],"generate":[111],"extra":[112],"terms,":[113],"thereby":[114],"enriching":[115],"query.":[118],"We":[119],"conduct":[120],"experiments":[121,138],"on":[122],"a":[123,170],"range":[124],"well-known":[126],"datasets,":[129],"including":[130],"MSMARCO-passage,":[131],"TREC2019,":[132],"TREC2020,":[133],"Natural":[134],"Questions,":[135],"SCIFACT.":[136],"The":[137],"show":[139],"be":[143,198],"beneficial":[144],"since":[148],"added":[150],"provided":[152],"help":[157],"diminish":[158],"discrepancy":[160],"between":[161],"frequencies":[164],"important":[167],"document.":[175],"certain":[177],"domains,":[178],"demonstrate":[180],"effectiveness":[183],"constrained,":[187],"indicating":[188],"they":[190],"may":[191],"not":[192],"consistently":[193],"perform":[194],"optimally,":[195],"which":[196],"will":[197],"explored":[199],"future":[201],"research.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}