{"id":"https://openalex.org/W7129069124","doi":"https://doi.org/10.1145/3773966.3777988","title":"How Do LLM-Generated Texts Impact Term-Based Retrieval Models?","display_name":"How Do LLM-Generated Texts Impact Term-Based Retrieval Models?","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W7129069124","doi":"https://doi.org/10.1145/3773966.3777988"},"language":null,"primary_location":{"id":"doi:10.1145/3773966.3777988","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3777988","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 Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3773966.3777988","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126143502","display_name":"Wei Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Huang","raw_affiliation_strings":["State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126099080","display_name":"Keping Bi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keping Bi","raw_affiliation_strings":["State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084642830","display_name":"Yinqiong Cai","orcid":"https://orcid.org/0000-0002-7869-8213"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinqiong Cai","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126131107","display_name":"Wei Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Chen","raw_affiliation_strings":["State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109736354","display_name":"Jiafeng Guo","orcid":"https://orcid.org/0000-0002-2793-3893"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiafeng Guo","raw_affiliation_strings":["State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110849771","display_name":"Xueqi Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqi Cheng","raw_affiliation_strings":["State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5126143502"],"corresponding_institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87763149,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"238","last_page":"248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.6633999943733215,"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":0.6633999943733215,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.07339999824762344,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.05820000171661377,"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/generalization","display_name":"Generalization","score":0.642799973487854},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5407999753952026},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4611000120639801},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4350999891757965},{"id":"https://openalex.org/keywords/zipfs-law","display_name":"Zipf's law","score":0.40779998898506165},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.40450000762939453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6780999898910522},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.642799973487854},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5504000186920166},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5407999753952026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49790000915527344},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4611000120639801},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4350999891757965},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4205000102519989},{"id":"https://openalex.org/C125932096","wikidata":"https://www.wikidata.org/wiki/Q205472","display_name":"Zipf's law","level":2,"score":0.40779998898506165},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.27129998803138733},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.263700008392334}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3773966.3777988","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3777988","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 Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3773966.3777988","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3777988","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 Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7296939492225647,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1999822363","https://openalex.org/W2009047999","https://openalex.org/W2081580037","https://openalex.org/W2090618725","https://openalex.org/W2105157020","https://openalex.org/W2134557008","https://openalex.org/W2144211451","https://openalex.org/W2165612380","https://openalex.org/W2317666317","https://openalex.org/W2798658104","https://openalex.org/W2889787757","https://openalex.org/W2912924812","https://openalex.org/W2951534261","https://openalex.org/W2963961878","https://openalex.org/W3017330897","https://openalex.org/W3035324702","https://openalex.org/W4206765718","https://openalex.org/W4252076394","https://openalex.org/W4295601746","https://openalex.org/W4317553041","https://openalex.org/W4379958473","https://openalex.org/W4384918448","https://openalex.org/W4390347092","https://openalex.org/W4391164144","https://openalex.org/W4400267287","https://openalex.org/W4400529824","https://openalex.org/W4401306886","https://openalex.org/W4401798709","https://openalex.org/W4401863498","https://openalex.org/W4402669968","https://openalex.org/W4404534210","https://openalex.org/W4412888775"],"related_works":[],"abstract_inverted_index":{"As":[0],"more":[1],"content":[2,64],"generated":[3],"by":[4],"large":[5],"language":[6],"models":[7,126,133],"(LLMs)":[8],"floods":[9],"into":[10],"the":[11,19,60,144],"Internet,":[12],"information":[13],"retrieval":[14,67,125],"(IR)":[15],"systems":[16,167],"now":[17],"face":[18],"challenge":[20],"of":[21,27,62,143],"distinguishing":[22],"and":[23,29,75,90,98,116,160,172],"handling":[24],"a":[25,40,156],"blend":[26],"human-authored":[28],"machine-generated":[30],"texts.":[31],"Recent":[32],"studies":[33],"suggest":[34],"that":[35,84,131],"neural":[36],"retrievers":[37,49],"may":[38],"exhibit":[39,87],"preferential":[41],"inclination":[42],"toward":[43],"LLM-generated":[44,63,85],"content,":[45],"while":[46],"classic":[47],"term-based":[48,66,124,165],"like":[50],"BM25":[51],"tend":[52],"to":[53,110,141],"favor":[54],"human-written":[55],"documents.":[56],"This":[57,153],"paper":[58],"investigates":[59],"influence":[61],"on":[65],"models,":[68],"which":[69],"are":[70,104,175],"valued":[71],"for":[72,158],"their":[73],"efficiency":[74],"robust":[76],"generalization":[77],"across":[78],"domains.":[79],"Our":[80,119],"linguistic":[81],"analysis":[82],"reveals":[83],"texts":[86],"smoother":[88],"high-frequency":[89],"steeper":[91],"low-frequency":[92],"Zipf":[93],"slopes,":[94],"higher":[95],"term":[96,137],"specificity,":[97],"greater":[99],"document-level":[100],"diversity.":[101],"These":[102],"traits":[103],"aligned":[105],"with":[106],"LLMs":[107],"being":[108],"trained":[109],"optimize":[111],"reader":[112],"experience":[113],"through":[114],"diverse":[115],"precise":[117],"expressions.":[118],"study":[120],"further":[121],"explores":[122],"whether":[123],"demonstrate":[127],"source":[128,151],"bias,":[129],"concluding":[130],"these":[132],"prioritize":[134],"documents":[135],"whose":[136],"distributions":[138],"closely":[139],"correspond":[140],"those":[142],"queries,":[145],"rather":[146],"than":[147],"displaying":[148],"an":[149],"inherent":[150],"bias.":[152],"work":[154],"provides":[155],"foundation":[157],"understanding":[159],"addressing":[161],"potential":[162],"biases":[163],"in":[164],"IR":[166],"managing":[168],"mixed-source":[169],"content.":[170],"Code":[171],"supplementary":[173],"material":[174],"available":[176],"at":[177],"https://github.com/Trustworthy-Information-Access/LLM-Impact-Term-Retrieval.":[178]},"counts_by_year":[],"updated_date":"2026-02-23T20:09:44.859080","created_date":"2026-02-17T00:00:00"}