{"id":"https://openalex.org/W4416017619","doi":"https://doi.org/10.1145/3746252.3761382","title":"A Comparative Analysis of Linguistic and Retrieval Diversity in LLM-Generated Search Queries","display_name":"A Comparative Analysis of Linguistic and Retrieval Diversity in LLM-Generated Search Queries","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4416017619","doi":"https://doi.org/10.1145/3746252.3761382"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3761382","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761382","pdf_url":null,"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 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746252.3761382","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052168069","display_name":"Oleg Zendel","orcid":"https://orcid.org/0000-0003-1535-0989"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Oleg Zendel","raw_affiliation_strings":["RMIT University, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103309188","display_name":"Sara Fahad Dawood Al Lawati","orcid":"https://orcid.org/0009-0000-7513-014X"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sara Fahad Dawood Al Lawati","raw_affiliation_strings":["RMIT University, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031434805","display_name":"Lida Rashidi","orcid":"https://orcid.org/0000-0002-6189-3274"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lida Rashidi","raw_affiliation_strings":["RMIT University, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085925326","display_name":"Falk Scholer","orcid":"https://orcid.org/0000-0001-9094-0810"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Falk Scholer","raw_affiliation_strings":["RMIT University, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072614956","display_name":"Mark Sanderson","orcid":"https://orcid.org/0000-0003-0487-9609"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mark Sanderson","raw_affiliation_strings":["RMIT University, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5052168069"],"corresponding_institution_ids":["https://openalex.org/I82951845"],"apc_list":null,"apc_paid":null,"fwci":3.1528,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.94137498,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4014","last_page":"4023"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9483000040054321,"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":0.9483000040054321,"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/T13274","display_name":"Expert finding and Q&A systems","score":0.007400000002235174,"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/T14347","display_name":"Big Data and Digital Economy","score":0.0026000000070780516,"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/diversity","display_name":"Diversity (politics)","score":0.5015000104904175},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.44130000472068787},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4050999879837036},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.39879998564720154},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.33149999380111694},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.3059999942779541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7077000141143799},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6068000197410583},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.5015000104904175},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44130000472068787},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42489999532699585},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40459999442100525},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.39879998564720154},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26489999890327454},{"id":"https://openalex.org/C2993724205","wikidata":"https://www.wikidata.org/wiki/Q315","display_name":"Human language","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2581000030040741}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746252.3761382","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761382","pdf_url":null,"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 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/30843344","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"Conference contribution"}],"best_oa_location":{"id":"doi:10.1145/3746252.3761382","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761382","pdf_url":null,"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 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1968927634","https://openalex.org/W1977437814","https://openalex.org/W1981065051","https://openalex.org/W2035569891","https://openalex.org/W2053154970","https://openalex.org/W2090035194","https://openalex.org/W2096946253","https://openalex.org/W2740121459","https://openalex.org/W2899154813","https://openalex.org/W3153610952","https://openalex.org/W3198734960","https://openalex.org/W4220841658","https://openalex.org/W4284664032","https://openalex.org/W4284899329","https://openalex.org/W4367190690","https://openalex.org/W4384652592","https://openalex.org/W4384662964","https://openalex.org/W4391876619","https://openalex.org/W4392581042","https://openalex.org/W4396802124","https://openalex.org/W4400525800","https://openalex.org/W4400526284","https://openalex.org/W4400526908","https://openalex.org/W4401335995","https://openalex.org/W4402951142","https://openalex.org/W4403582649","https://openalex.org/W4405143965","https://openalex.org/W4406779230","https://openalex.org/W4407687648","https://openalex.org/W4410637007","https://openalex.org/W4412377054","https://openalex.org/W4412673258"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4],"increasingly":[5],"used":[6,180],"to":[7,26],"generate":[8,89],"search":[9],"queries":[10,24,50,64,74,102,132],"for":[11,160],"various":[12],"Information":[13],"Retrieval":[14],"(IR)":[15],"tasks.":[16],"However,":[17],"it":[18],"remains":[19],"unclear":[20],"how":[21],"these":[22,158],"machine-generated":[23],"compare":[25,70],"human-written":[27],"ones,":[28],"particularly":[29],"in":[30,98,148,168],"terms":[31],"of":[32,46,145,157],"diversity":[33],"and":[34,48,59,69,114,164],"alignment":[35],"with":[36,72,181],"real":[37,137],"user":[38,138,165],"behavior.":[39,100,152],"This":[40],"paper":[41],"presents":[42],"an":[43],"empirical":[44],"comparison":[45],"LLM-":[47],"human-generated":[49],"across":[51],"multiple":[52],"dimensions,":[53],"including":[54],"lexical":[55],"diversity,":[56],"linguistic":[57],"variation,":[58],"retrieval":[60,122],"effectiveness.":[61],"We":[62,153,170],"analyze":[63],"produced":[65],"by":[66],"several":[67],"LLMs":[68,87,147,174],"them":[71],"human":[73,99,127],"from":[75,95],"two":[76],"datasets":[77],"collected":[78],"five":[79],"years":[80],"apart.":[81],"Our":[82],"findings":[83,159],"show":[84],"that":[85,130,172],"while":[86,173],"can":[88],"diverse":[90],"queries,":[91,128],"their":[92],"patterns":[93],"differ":[94],"those":[96],"observed":[97],"LLM":[101],"typically":[103],"exhibit":[104],"higher":[105],"surface-level":[106],"uniqueness":[107],"but":[108],"rely":[109],"less":[110],"on":[111],"stopword":[112],"use":[113],"word":[115],"form":[116],"variation.":[117],"They":[118],"also":[119],"achieve":[120],"lower":[121],"effectiveness":[123],"when":[124],"judged":[125],"against":[126],"suggesting":[129],"LLM-generated":[131],"may":[133],"not":[134],"always":[135],"reflect":[136],"intent.":[139],"These":[140],"differences":[141],"highlight":[142],"the":[143,155],"limitations":[144],"current":[146],"replicating":[149],"natural":[150],"querying":[151],"discuss":[154],"implications":[156],"LLM-based":[161],"query":[162],"generation":[163],"behavior":[166],"simulation":[167],"IR.":[169],"conclude":[171],"hold":[175],"potential,":[176],"they":[177],"should":[178],"be":[179],"caution.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-11-08T00:00:00"}
