{"id":"https://openalex.org/W7130549509","doi":"https://doi.org/10.1145/3774904.3792955","title":"Retrieval Collapses When AI Pollutes the Web","display_name":"Retrieval Collapses When AI Pollutes the Web","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7130549509","doi":"https://doi.org/10.1145/3774904.3792955"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792955","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792955","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 ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792955","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126385126","display_name":"Hongyeon Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I174135032","display_name":"Bellevue College","ror":"https://ror.org/05gr4yv49","country_code":"US","type":"education","lineage":["https://openalex.org/I174135032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongyeon Yu","raw_affiliation_strings":["NAVER Corp., Bellevue, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-4325-5332","affiliations":[{"raw_affiliation_string":"NAVER Corp., Bellevue, WA, USA","institution_ids":["https://openalex.org/I174135032"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126371176","display_name":"Dongchan Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I174135032","display_name":"Bellevue College","ror":"https://ror.org/05gr4yv49","country_code":"US","type":"education","lineage":["https://openalex.org/I174135032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongchan Kim","raw_affiliation_strings":["NAVER Corp., Bellevue, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-9803-9311","affiliations":[{"raw_affiliation_string":"NAVER Corp., Bellevue, WA, USA","institution_ids":["https://openalex.org/I174135032"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126397893","display_name":"Young-Bum Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I174135032","display_name":"Bellevue College","ror":"https://ror.org/05gr4yv49","country_code":"US","type":"education","lineage":["https://openalex.org/I174135032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Young-Bum Kim","raw_affiliation_strings":["NAVER Corp., Bellevue, WA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1304-5446","affiliations":[{"raw_affiliation_string":"NAVER Corp., Bellevue, WA, USA","institution_ids":["https://openalex.org/I174135032"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I174135032"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13464944,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8745","last_page":"8748"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.131400004029274,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.131400004029274,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.12700000405311584,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.07209999859333038,"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/adversarial-system","display_name":"Adversarial system","score":0.6255999803543091},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5411999821662903},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.491100013256073},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.37130001187324524},{"id":"https://openalex.org/keywords/adversarial-information-retrieval","display_name":"Adversarial information retrieval","score":0.34279999136924744},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3176000118255615}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6255999803543091},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5982000231742859},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5411999821662903},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.491100013256073},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42170000076293945},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C116425068","wikidata":"https://www.wikidata.org/wiki/Q4686695","display_name":"Adversarial information retrieval","level":5,"score":0.34279999136924744},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3246999979019165},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2599000036716461},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.259799987077713},{"id":"https://openalex.org/C2779756789","wikidata":"https://www.wikidata.org/wiki/Q28549308","display_name":"Fake news","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3774904.3792955","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792955","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 ACM Web Conference 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2602.16136","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.16136","pdf_url":"https://arxiv.org/pdf/2602.16136","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,"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"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792955","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792955","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 ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","score":0.5123810768127441,"display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"proliferation":[2],"of":[3,123,138,157],"AI-generated":[4,48],"content":[5,49,61,77],"on":[6,111],"the":[7,29,63,83,109,136,147],"Web":[8],"presents":[9],"a":[10,43,86,97,154],"structural":[11],"risk":[12,137],"to":[13,91,152],"information":[14],"retrieval,":[15],"as":[16,40],"search":[17,51],"engines":[18],"and":[19,56,78,146],"Retrieval-Augmented":[20],"Generation":[21],"(RAG)":[22],"systems":[23],"increasingly":[24],"consume":[25],"evidence":[26,145],"produced":[27],"by":[28],"Large":[30],"Language":[31],"Models":[32],"(LLMs).":[33],"We":[34,66],"characterize":[35],"this":[36,68],"ecosystem-level":[37],"failure":[38],"mode":[39],"Retrieval":[41],"Collapse,":[42],"two-stage":[44],"process":[45],"where":[46,103],"(1)":[47],"dominates":[50],"results,":[52],"eroding":[53],"source":[54],"diversity,":[55],"(2)":[57],"low-quality":[58],"or":[59],"adversarial":[60,116],"infiltrates":[62],"retrieval":[64,139],"pipeline.":[65],"analyzed":[67],"dynamic":[69],"through":[70],"controlled":[71],"experiments":[72],"involving":[73],"both":[74],"high-quality":[75],"SEO-style":[76],"adversarially":[79],"crafted":[80],"content.":[81],"In":[82],"SEO":[84],"scenario,":[85],"67\\%":[87],"pool":[88],"contamination":[89],"led":[90],"over":[92],"80\\%":[93],"exposure":[94],"contamination,":[95,117],"creating":[96],"homogenized":[98],"yet":[99],"deceptively":[100],"healthy":[101],"state":[102],"answer":[104],"accuracy":[105],"remains":[106],"stable":[107],"despite":[108],"reliance":[110],"synthetic":[112,144],"sources.":[113],"Conversely,":[114],"under":[115],"baselines":[118],"like":[119],"BM25":[120],"exposed":[121],"$\\sim$19\\%":[122],"harmful":[124],"content,":[125],"whereas":[126],"LLM-based":[127],"rankers":[128],"demonstrated":[129],"stronger":[130],"suppression":[131],"capabilities.":[132],"These":[133],"findings":[134],"highlight":[135],"pipelines":[140],"quietly":[141],"shifting":[142],"toward":[143],"need":[148],"for":[149],"retrieval-aware":[150],"strategies":[151],"prevent":[153],"self-reinforcing":[155],"cycle":[156],"quality":[158],"decline":[159],"in":[160],"Web-grounded":[161],"systems.":[162]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2026-02-20T00:00:00"}