{"id":"https://openalex.org/W7166809139","doi":"https://doi.org/10.18653/v1/2026.acl-long.1475","title":"LLM-Generated Text May Harm Your Retrieval! A Robust Detection Strategy for Retrieval-Augmented Generation","display_name":"LLM-Generated Text May Harm Your Retrieval! A Robust Detection Strategy for Retrieval-Augmented Generation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166809139","doi":"https://doi.org/10.18653/v1/2026.acl-long.1475"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1475","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1475","pdf_url":"https://aclanthology.org/2026.acl-long.1475.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1475.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139726231","display_name":"Zhaoheng Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaoheng Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139821406","display_name":"Yutao Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yutao Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139737149","display_name":"Ji-Rong Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji-Rong Wen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139805341","display_name":"Zhicheng Dou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhicheng Dou","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.84206818,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"31973","last_page":"31988"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.517300009727478,"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":0.517300009727478,"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":0.2476000040769577,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.06109999865293503,"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/harm","display_name":"Harm","score":0.44859999418258667},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.35690000653266907},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2678999900817871},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.2563999891281128}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.566100001335144},{"id":"https://openalex.org/C2777363581","wikidata":"https://www.wikidata.org/wiki/Q15098235","display_name":"Harm","level":2,"score":0.44859999418258667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38850000500679016},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3441999852657318},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2976999878883362},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2678999900817871},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25949999690055847},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2563999891281128},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1475","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1475","pdf_url":"https://aclanthology.org/2026.acl-long.1475.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1475","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1475","pdf_url":"https://aclanthology.org/2026.acl-long.1475.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G228125052","display_name":null,"funder_award_id":"62272467","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166809139.pdf","grobid_xml":"https://content.openalex.org/works/W7166809139.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1,154],"(RAG)":[2],"effectively":[3],"enhances":[4],"the":[5,23,43,62,69,83,92,106,165],"accuracy":[6],"and":[7,45,58,68,115,149,163],"timeliness":[8],"of":[9,26,47,65,71,109,119,168],"large":[10],"language":[11],"models":[12],"(LLMs)":[13],"by":[14,32],"incorporating":[15],"external":[16,20,29],"knowledge":[17],"retrieved":[18,48,93],"from":[19,91,146],"sources.However,":[21],"with":[22,38,138],"increasing":[24],"prevalence":[25],"LLM-generated":[27,39,89],"content,":[28],"corpora":[30],"used":[31],"RAG":[33,56,84,99,114,169],"systems":[34],"may":[35],"become":[36],"contaminated":[37],"texts.Such":[40],"contamination":[41,140],"compromises":[42],"reliability":[44],"quality":[46],"results,":[49],"ultimately":[50],"leading":[51],"to":[52,77,86],"a":[53,129],"degradation":[54,162],"in":[55,98],"performance,":[57],"raises":[59],"concerns":[60],"about":[61],"diminishing":[63],"presence":[64],"human":[66,150],"texts":[67,90,151],"\"Spiral":[70],"Silence\"":[72],"effect.A":[73],"natural":[74],"solution":[75],"is":[76],"incorporate":[78],"LLM":[79,110,148],"text":[80,111],"detectors":[81,112],"into":[82],"pipeline":[85],"filter":[87],"out":[88],"results.However,":[94],"their":[95],"effective":[96],"use":[97],"remains":[100],"under-explored.In":[101],"this":[102,125],"paper,":[103],"we":[104,127],"explore":[105],"usage":[107],"paradigms":[108],"for":[113],"highlight":[116],"key":[117],"limitations":[118],"off-the-shelf":[120],"or":[121],"directly":[122],"fine-tuned":[123],"detectors.To":[124],"end,":[126],"propose":[128],"RAG-aware":[130],"data":[131,145],"augmentation":[132],"strategy":[133],"that":[134,157],"aligns":[135],"detector":[136],"training":[137,144],"realistic":[139],"patterns.Our":[141],"approach":[142],"synthesizes":[143],"both":[147],"under":[152],"diverse":[153],"modes.Experiments":[155],"show":[156],"our":[158],"method":[159],"mitigates":[160],"performance":[161],"improves":[164],"long-term":[166],"stability":[167],"systems.":[170]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}