{"id":"https://openalex.org/W4412887968","doi":"https://doi.org/10.18653/v1/2025.findings-acl.980","title":"Hypothetical Documents or Knowledge Leakage? Rethinking LLM-based Query Expansion","display_name":"Hypothetical Documents or Knowledge Leakage? Rethinking LLM-based Query Expansion","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887968","doi":"https://doi.org/10.18653/v1/2025.findings-acl.980"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.980","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.980","pdf_url":"https://aclanthology.org/2025.findings-acl.980.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 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.980.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032937776","display_name":"Yejun Yoon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yejun Yoon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048369297","display_name":"Jae\u2010Yoon Jung","orcid":"https://orcid.org/0000-0002-4850-6284"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaeyoon Jung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101424021","display_name":"Seunghyun Yoon","orcid":"https://orcid.org/0000-0002-7262-3579"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seunghyun Yoon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5069120214","display_name":"Kunwoo Park","orcid":"https://orcid.org/0000-0003-2913-9711"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kunwoo Park","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":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19170","last_page":"19187"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.8824999928474426,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.8824999928474426,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.8420000076293945,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.8382999897003174,"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/computer-science","display_name":"Computer science","score":0.6580304503440857},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.6513009071350098},{"id":"https://openalex.org/keywords/leakage","display_name":"Leakage (economics)","score":0.6277896761894226},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.5047780275344849},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5024397373199463}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6580304503440857},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.6513009071350098},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.6277896761894226},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.5047780275344849},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5024397373199463},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.980","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.980","pdf_url":"https://aclanthology.org/2025.findings-acl.980.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 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.980","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.980","pdf_url":"https://aclanthology.org/2025.findings-acl.980.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 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"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/G8748030351","display_name":null,"funder_award_id":"IITP-2025-RS-2022-00156360","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"},{"id":"https://openalex.org/F4320337407","display_name":"Division of Human Resource Development","ror":"https://ror.org/03mamvh39"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887968.pdf","grobid_xml":"https://content.openalex.org/works/W4412887968.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2096359267","https://openalex.org/W2006459955","https://openalex.org/W4256058599","https://openalex.org/W2146885082","https://openalex.org/W2066605394","https://openalex.org/W1982237068","https://openalex.org/W2572349046","https://openalex.org/W2538384344","https://openalex.org/W4386051213","https://openalex.org/W185198413"],"abstract_inverted_index":{"Query":[0],"expansion":[1,115],"methods":[2,16],"powered":[3],"by":[4,41,68,94],"large":[5],"language":[6],"models":[7],"(LLMs)":[8],"have":[9],"demonstrated":[10],"effectiveness":[11],"in":[12,46,104],"zero-shot":[13],"retrieval":[14,33],"tasks.These":[15],"assume":[17],"that":[18,98],"LLMs":[19],"can":[20],"generate":[21],"hypothetical":[22],"documents":[23,64,90],"that,":[24,79],"when":[25],"incorporated":[26],"into":[27],"a":[28,57],"query":[29,114],"vector,":[30],"enhance":[31],"the":[32,50,62,109],"of":[34,112],"real":[35],"evidence.However,":[36],"we":[37,59],"challenge":[38],"this":[39],"assumption":[40],"investigating":[42],"whether":[43,61],"knowledge":[44,99],"leakage":[45,100],"benchmarks":[47],"contributes":[48],"to":[49],"observed":[51],"performance":[52,82,111],"gains.Using":[53],"fact":[54],"verification":[55],"as":[56],"testbed,":[58],"analyze":[60],"generated":[63,89],"contain":[65],"information":[66],"entailed":[67,93],"ground-truth":[69],"evidence":[70],"and":[71],"assess":[72],"their":[73],"impact":[74],"on":[75,80],"performance.Our":[76],"findings":[77],"indicate":[78],"average,":[81],"improvements":[83],"consistently":[84],"occurred":[85],"for":[86],"claims":[87],"whose":[88],"included":[91],"sentences":[92],"gold":[95],"evidence.This":[96],"suggests":[97],"may":[101],"be":[102],"present":[103],"fact-verification":[105],"benchmarks,":[106],"potentially":[107],"inflating":[108],"perceived":[110],"LLM-based":[113],"methods.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
