{"id":"https://openalex.org/W4416034006","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1064","title":"More Documents, Same Length: Isolating the Challenge of Multiple Documents in RAG","display_name":"More Documents, Same Length: Isolating the Challenge of Multiple Documents in RAG","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034006","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1064"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1064","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1064","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1064.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1064.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112702972","display_name":"Shahar Levy","orcid":null},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Shahar Levy","raw_affiliation_strings":["School of Computer Science and Engineering The Hebrew University of Jerusalem , Jerusalem , Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering The Hebrew University of Jerusalem , Jerusalem , Israel","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040587483","display_name":"Nir Mazor","orcid":null},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Nir Mazor","raw_affiliation_strings":["School of Computer Science and Engineering The Hebrew University of Jerusalem , Jerusalem , Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering The Hebrew University of Jerusalem , Jerusalem , Israel","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120308463","display_name":"Lihi Shalmon","orcid":null},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Lihi Shalmon","raw_affiliation_strings":["School of Computer Science and Engineering The Hebrew University of Jerusalem , Jerusalem , Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering The Hebrew University of Jerusalem , Jerusalem , Israel","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120308464","display_name":"Michael Hassid","orcid":null},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Michael Hassid","raw_affiliation_strings":["School of Computer Science and Engineering The Hebrew University of Jerusalem , Jerusalem , Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering The Hebrew University of Jerusalem , Jerusalem , Israel","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082136238","display_name":"Gabriel Stanovsky","orcid":"https://orcid.org/0000-0002-2420-8979"},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Gabriel Stanovsky","raw_affiliation_strings":["School of Computer Science and Engineering The Hebrew University of Jerusalem , Jerusalem , Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering The Hebrew University of Jerusalem , Jerusalem , Israel","institution_ids":["https://openalex.org/I197251160"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197251160"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19539","last_page":"19547"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.0608999989926815,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.0608999989926815,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.049400001764297485,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.03530000150203705,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.24709999561309814},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.24580000340938568},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.22120000422000885},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.21209999918937683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.557699978351593},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.28859999775886536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28700000047683716},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.24709999561309814},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.24580000340938568},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.22120000422000885},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.21209999918937683},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.21199999749660492},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20749999582767487},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.19130000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1064","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1064","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1064.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1064","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1064","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1064.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034006.pdf","grobid_xml":"https://content.openalex.org/works/W4416034006.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Retrieval-Augmented":[0],"Generation":[1],"(RAG)":[2],"enhances":[3],"the":[4,34,59,70,78,126],"accuracy":[5],"of":[6,36,64,72],"Large":[7],"Language":[8],"Model":[9],"(LLM)":[10],"responses":[11],"by":[12,92],"leveraging":[13],"relevant":[14,65],"external":[15],"documents":[16,25,37,115],"during":[17],"generation.Although":[18],"previous":[19],"studies":[20],"noted":[21],"that":[22,76,112],"retrieving":[23],"many":[24],"can":[26],"degrade":[27],"performance,":[28],"they":[29],"did":[30],"not":[31],"isolate":[32],"how":[33],"quantity":[35],"affects":[38],"performance":[39,91],"while":[40,68],"controlling":[41],"for":[42,87],"context":[43,60],"length.We":[44],"evaluate":[45],"various":[46],"language":[47],"models":[48],"on":[49],"custom":[50],"datasets":[51,127],"derived":[52],"from":[53,120],"a":[54,117],"multi-hop":[55],"QA":[56],"task.We":[57],"keep":[58],"length":[61],"and":[62,74,128],"position":[63],"information":[66],"constant":[67],"varying":[69],"number":[71],"documents,":[73],"find":[75],"increasing":[77,101],"document":[79,102],"count":[80],"in":[81,136],"RAG":[82],"settings":[83],"poses":[84],"significant":[85],"challenges":[86],"most":[88],"LLMs,":[89],"reducing":[90],"up":[93],"to":[94,132],"20%.However,":[95],"Qwen2.5":[96],"maintained":[97],"consistent":[98],"results":[99,110],"across":[100],"counts,":[103],"indicating":[104],"better":[105],"multi-document":[106,137],"handling":[107,121],"capability.Finally,":[108],"our":[109],"indicate":[111],"processing":[113],"multiple":[114],"is":[116],"separate":[118],"challenge":[119],"long":[122],"contexts.We":[123],"also":[124],"make":[125],"code":[129],"available":[130],"1":[131],"facilitate":[133],"further":[134],"research":[135],"retrieval.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-11-08T00:00:00"}
