{"id":"https://openalex.org/W6979285387","doi":null,"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":"2025-04-19","ids":{"openalex":"https://openalex.org/W6979285387"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2504.14175","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.14175","pdf_url":"https://arxiv.org/pdf/2504.14175","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.14175","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032937776","display_name":"Yejun Yoon","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoon, Yejun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114337163","display_name":"Jaeyoon Jung","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jung, Jaeyoon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yoon, Seunghyun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoon, Seunghyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Park, Kunwoo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Park, Kunwoo","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":true,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.82669997215271,"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"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.82669997215271,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.16019999980926514,"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/T11147","display_name":"Misinformation and Its Impacts","score":0.004100000020116568,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/query-expansion","display_name":"query expansion","score":0.8169999718666077},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9710000157356262},{"id":"https://openalex.org/keywords/knowledge-leakage","display_name":"knowledge leakage","score":0.8330000042915344},{"id":"https://openalex.org/keywords/fact-checking","display_name":"fact-checking","score":0.7120000123977661},{"id":"https://openalex.org/keywords/zero-shot-retrieval","display_name":"zero-shot retrieval","score":0.8550000190734863},{"id":"https://openalex.org/keywords/logical-consequence","display_name":"logical consequence","score":0.8339999914169312},{"id":"https://openalex.org/keywords/evidence-retrieval","display_name":"evidence retrieval","score":0.31700000166893005}],"concepts":[{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.809499979019165},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7196000218391418},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5920000076293945},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.536300003528595},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.4429999887943268},{"id":"https://openalex.org/C96956885","wikidata":"https://www.wikidata.org/wiki/Q6138701","display_name":"RDF query language","level":5,"score":0.4122999906539917},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.3959999978542328},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.31060001254081726},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3086000084877014},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.3068000078201294},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.30390000343322754},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2800999879837036},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2745000123977661}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2504.14175","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.14175","pdf_url":"https://arxiv.org/pdf/2504.14175","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.14175","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.14175","pdf_url":"https://arxiv.org/pdf/2504.14175","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Query":[0],"expansion":[1,120],"methods":[2,17],"powered":[3],"by":[4,43,71,98],"large":[5],"language":[6],"models":[7],"(LLMs)":[8],"have":[9],"demonstrated":[10],"effectiveness":[11],"in":[12,48,109],"zero-shot":[13],"retrieval":[14,34],"tasks.":[15],"These":[16],"assume":[18],"that":[19,103],"LLMs":[20],"can":[21],"generate":[22],"hypothetical":[23],"documents":[24,67,94],"that,":[25,83],"when":[26],"incorporated":[27],"into":[28],"a":[29,60],"query":[30,119],"vector,":[31],"enhance":[32],"the":[33,52,65,114],"of":[35,117],"real":[36],"evidence.":[37,100],"However,":[38],"we":[39,62],"challenge":[40],"this":[41],"assumption":[42],"investigating":[44],"whether":[45,64],"knowledge":[46,104],"leakage":[47,105],"benchmarks":[49],"contributes":[50],"to":[51],"observed":[53],"performance":[54,86,116],"gains.":[55],"Using":[56],"fact":[57],"verification":[58],"as":[59],"testbed,":[61],"analyze":[63],"generated":[66,93],"contain":[68],"information":[69],"entailed":[70,97],"ground-truth":[72],"evidence":[73],"and":[74],"assess":[75],"their":[76],"impact":[77],"on":[78,84],"performance.":[79],"Our":[80],"findings":[81],"indicate":[82],"average,":[85],"improvements":[87],"consistently":[88],"occurred":[89],"for":[90],"claims":[91],"whose":[92],"included":[95],"sentences":[96],"gold":[99],"This":[101],"suggests":[102],"may":[106],"be":[107],"present":[108],"fact-verification":[110],"benchmarks,":[111],"potentially":[112],"inflating":[113],"perceived":[115],"LLM-based":[118],"methods.":[121]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}