{"id":"https://openalex.org/W4412377958","doi":"https://doi.org/10.1145/3726302.3730222","title":"LLM-based Query Expansion Fails for Unfamiliar and Ambiguous Queries","display_name":"LLM-based Query Expansion Fails for Unfamiliar and Ambiguous Queries","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412377958","doi":"https://doi.org/10.1145/3726302.3730222"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730222","doi":"https://doi.org/10.1145/3726302.3730222","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730222","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730222","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730222","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Kenya Abe","orcid":"https://orcid.org/0009-0007-5413-3158","observed_orcids":["https://orcid.org/0009-0007-5413-3158"]},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenya Abe","raw_affiliation_strings":["University of Tsukuba, Tsukuba, Japan"],"raw_orcid":"https://orcid.org/0009-0007-5413-3158","affiliations":[{"raw_affiliation_string":"University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060037914","display_name":"Kunihiro Takeoka","orcid":"https://orcid.org/0009-0000-9653-8523","observed_orcids":["https://orcid.org/0009-0000-9653-8523"]},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kunihiro Takeoka","raw_affiliation_strings":["NEC Corporation, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0000-9653-8523","affiliations":[{"raw_affiliation_string":"NEC Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015183832","display_name":"Makoto P. Kato","orcid":"https://orcid.org/0000-0002-9351-0901","observed_orcids":["https://orcid.org/0000-0002-9351-0901"]},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Makoto P. Kato","raw_affiliation_strings":["University of Tsukuba, Tsukuba, Japan"],"raw_orcid":"https://orcid.org/0000-0002-9351-0901","affiliations":[{"raw_affiliation_string":"University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044722101","display_name":"Masafumi Oyamada","orcid":"https://orcid.org/0000-0002-4045-7350","observed_orcids":["https://orcid.org/0000-0002-4045-7350"]},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masafumi Oyamada","raw_affiliation_strings":["NEC Corporation, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4045-7350","affiliations":[{"raw_affiliation_string":"NEC Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I118347220"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.7177,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.96407971,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3035","last_page":"3039"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9976000189781189,"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":0.9976000189781189,"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":0.0017000000225380063,"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/T10203","display_name":"Recommender Systems and Techniques","score":9.999999747378752e-05,"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/query-expansion","display_name":"query expansion","score":0.9729999899864197},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9160000085830688},{"id":"https://openalex.org/keywords/retrieval-augmentation","display_name":"retrieval augmentation","score":0.847000002861023},{"id":"https://openalex.org/keywords/query-ambiguity","display_name":"query ambiguity","score":0.6830000281333923},{"id":"https://openalex.org/keywords/retrieval-performance","display_name":"retrieval effectiveness","score":0.4410000145435333},{"id":"https://openalex.org/keywords/sparse-retrieval","display_name":"sparse retrieval","score":0.6650000214576721},{"id":"https://openalex.org/keywords/dense-retrieval","display_name":"dense retrieval","score":0.996999979019165},{"id":"https://openalex.org/keywords/search-coverage","display_name":"search coverage","score":0.49000000953674316},{"id":"https://openalex.org/keywords/hallucinations","display_name":"hallucinations","score":0.38600000739097595}],"concepts":[{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.7626737356185913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.758003830909729},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.6699601411819458},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.5864943861961365},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5215349197387695},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.48324355483055115},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.47342923283576965},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.4482932388782501},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.321882426738739},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.17570003867149353}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3726302.3730222","doi":"https://doi.org/10.1145/3726302.3730222","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730222","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730222","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.12694","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.12694","pdf_url":"https://arxiv.org/pdf/2505.12694","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.12694","doi":"https://doi.org/10.48550/arxiv.2505.12694","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.12694","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3726302.3730222","doi":"https://doi.org/10.1145/3726302.3730222","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730222","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730222","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3813547358","display_name":null,"funder_award_id":"JP23K28090, JP23K25159","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G6421696978","display_name":"Acquisition, Retrieval and Generation of  Meaning Information by Machine Learning","funder_award_id":"23K25159","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6992693322","display_name":"\u6c4e\u7528\u691c\u7d22\u30e2\u30c7\u30eb\u306b\u57fa\u3065\u304f\u4f4e\u8cc7\u6e90\u4e0b\u306b\u304a\u3051\u308b\u60c5\u5831\u691c\u7d22\u30b7\u30b9\u30c6\u30e0\u69cb\u7bc9\u6280\u8853\u306e\u958b\u767a","funder_award_id":"23K28090","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412377958.pdf","grobid_xml":"https://content.openalex.org/works/W4412377958.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1485661919","https://openalex.org/W1981208470","https://openalex.org/W1993692165","https://openalex.org/W2043909051","https://openalex.org/W2068098598","https://openalex.org/W2104049510","https://openalex.org/W2113347069","https://openalex.org/W2912924812","https://openalex.org/W2990138404","https://openalex.org/W4327644083","https://openalex.org/W4367189613","https://openalex.org/W4386081001","https://openalex.org/W4386566590","https://openalex.org/W4387847693","https://openalex.org/W4394947904","https://openalex.org/W4400526126","https://openalex.org/W4403577943","https://openalex.org/W4404534210","https://openalex.org/W4410636420"],"related_works":["https://openalex.org/W4401209596","https://openalex.org/W4409764260","https://openalex.org/W4404782160","https://openalex.org/W4411638747","https://openalex.org/W7126387168","https://openalex.org/W4416068048","https://openalex.org/W4413145989","https://openalex.org/W4375870261","https://openalex.org/W4389520758","https://openalex.org/W7140173909"],"abstract_inverted_index":{"Query":[0],"expansion":[1],"(QE)":[2],"enhances":[3],"retrieval":[4,106,112,124,155],"by":[5],"incorporating":[6],"relevant":[7,37],"terms,":[8],"with":[9],"large":[10],"language":[11],"models":[12],"(LLMs)":[13],"offering":[14],"an":[15],"effective":[16],"alternative":[17],"to":[18,35,73],"traditional":[19],"rule-based":[20],"and":[21,76,102,110],"statistical":[22],"methods.":[23],"However,":[24],"LLM-based":[25,63,118,154],"QE":[26,119,144],"suffers":[27],"from":[28],"a":[29,140],"fundamental":[30],"limitation:":[31],"it":[32],"often":[33],"fails":[34],"generate":[36],"knowledge,":[38,71],"degrading":[39],"search":[40,88],"performance.":[41],"Prior":[42],"studies":[43],"have":[44],"focused":[45],"on":[46,105],"hallucination,":[47],"yet":[48],"its":[49],"underlying":[50],"cause-LLM":[51],"knowledge":[52,101,127],"deficiencies-remains":[53],"underexplored.":[54],"This":[55],"paper":[56],"systematically":[57],"examines":[58],"two":[59],"failure":[60],"cases":[61],"in":[62,128],"QE:":[64],"(1)":[65],"when":[66,78,126],"the":[67,79,98,123,129,151],"LLM":[68,130],"lacks":[69],"query":[70,80,103,134],"leading":[72],"incorrect":[74],"expansions,":[75],"(2)":[77],"is":[81,131,136],"ambiguous,":[82],"causing":[83],"biased":[84],"refinements":[85],"that":[86,117],"narrow":[87],"coverage.":[89],"We":[90,138],"conduct":[91],"controlled":[92],"experiments":[93],"across":[94],"multiple":[95],"datasets,":[96],"evaluating":[97,143],"effects":[99],"of":[100,153],"ambiguity":[104,135],"performance":[107],"using":[108],"sparse":[109],"dense":[111],"models.":[113],"Our":[114],"results":[115],"reveal":[116],"can":[120],"significantly":[121],"degrade":[122],"effectiveness":[125],"insufficient":[132],"or":[133],"high.":[137],"introduce":[139],"framework":[141],"for":[142],"under":[145],"these":[146],"conditions,":[147],"providing":[148],"insights":[149],"into":[150],"limitations":[152],"augmentation.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}