{"id":"https://openalex.org/W4412945011","doi":"https://doi.org/10.18653/v1/2025.acl-long.892","title":"The Distracting Effect: Understanding Irrelevant Passages in RAG","display_name":"The Distracting Effect: Understanding Irrelevant Passages in RAG","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945011","doi":"https://doi.org/10.18653/v1/2025.acl-long.892"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.892","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.892","pdf_url":"https://aclanthology.org/2025.acl-long.892.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.892.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119204428","display_name":"Chen Amiraz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Amiraz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092543637","display_name":"Florin Cuconasu","orcid":"https://orcid.org/0009-0008-9768-1047"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Florin Cuconasu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093826503","display_name":"Simone Filice","orcid":"https://orcid.org/0009-0002-6735-9950"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simone Filice","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5048818669","display_name":"Zohar Karnin","orcid":"https://orcid.org/0009-0009-0108-289X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zohar Karnin","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":2.8012,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.91304073,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"18228","last_page":"18258"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.23170000314712524,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.23170000314712524,"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/computer-science","display_name":"Computer science","score":0.6301120519638062},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3386538028717041}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6301120519638062},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3386538028717041}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.892","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.892","pdf_url":"https://aclanthology.org/2025.acl-long.892.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.06914","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.06914","pdf_url":"https://arxiv.org/pdf/2505.06914","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:iris.uniroma1.it:11573/1744062","is_oa":true,"landing_page_url":"https://hdl.handle.net/11573/1744062","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.892","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.892","pdf_url":"https://aclanthology.org/2025.acl-long.892.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.699999988079071}],"awards":[{"id":"https://openalex.org/G8779474850","display_name":null,"funder_award_id":"PE0000013-FAIR","funder_id":"https://openalex.org/F4320322510","funder_display_name":"Sapienza Universit\u00e0 di Roma"}],"funders":[{"id":"https://openalex.org/F4320322510","display_name":"Sapienza Universit\u00e0 di Roma","ror":"https://ror.org/02be6w209"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945011.pdf","grobid_xml":"https://content.openalex.org/works/W4412945011.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"A":[0],"well-known":[1],"issue":[2,38],"with":[3,87],"Retrieval":[4],"Augmented":[5],"Generation":[6],"(RAG)":[7],"is":[8,112],"that":[9,12],"retrieved":[10],"passages":[11,80,124],"are":[13],"irrelevant":[14,123],"to":[15,25,81,96,104],"the":[16,20,41,58,118],"query":[17,49],"sometimes":[18],"distract":[19],"answer-generating":[21],"LLM,":[22],"causing":[23],"it":[24],"provide":[26,53],"an":[27,51],"incorrect":[28],"response.In":[29],"this":[30,36],"paper,":[31],"we":[32,93,115,133],"shed":[33],"light":[34],"on":[35,107],"core":[37],"and":[39,64,76,131,135,157],"formulate":[40],"distracting":[42,59,79,91,142,160],"effect":[43,60],"of":[44,57,61,122],"a":[45,48,54,62,97,152],"passage":[46,63],"w.r.t.":[47],"(and":[50],"LLM).We":[52],"quantifiable":[55],"measure":[56],"demonstrate":[65],"its":[66],"robustness":[67],"across":[68],"LLMs.Our":[69],"research":[70,148],"introduces":[71],"novel":[72],"methods":[73,138],"for":[74,139,155],"identifying":[75,156],"using":[77],"hard":[78,141,159],"improve":[82],"RAG":[83,109],"systems.By":[84],"fine-tuning":[85],"LLMs":[86],"these":[88],"carefully":[89],"selected":[90],"passages,":[92],"achieve":[94],"up":[95],"7.5%":[98],"increase":[99],"in":[100],"answering":[101],"accuracy":[102],"compared":[103],"counterparts":[105],"fine-tuned":[106],"conventional":[108],"datasets.Our":[110],"contribution":[111],"two-fold:":[113],"first,":[114],"move":[116],"beyond":[117],"simple":[119],"binary":[120],"classification":[121],"as":[125],"either":[126],"completely":[127],"unrelated":[128],"vs.":[129],"distracting,":[130],"second,":[132],"develop":[134],"analyze":[136],"multiple":[137],"finding":[140],"passages.To":[143],"our":[144],"knowledge,":[145],"no":[146],"other":[147],"has":[149],"provided":[150],"such":[151],"comprehensive":[153],"framework":[154],"utilizing":[158],"passages.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-11T18:08:03.149640","created_date":"2025-10-10T00:00:00"}