{"id":"https://openalex.org/W7204107397","doi":"https://doi.org/10.48550/arxiv.2608.21252","title":"EnSI-RAG: Entity-Structure-Indexed Retrieval-Augmented Generation for Long-Document Question Answering","display_name":"EnSI-RAG: Entity-Structure-Indexed Retrieval-Augmented Generation for Long-Document Question Answering","publication_year":2026,"publication_date":"2026-08-21","ids":{"openalex":"https://openalex.org/W7204107397","doi":"https://doi.org/10.48550/arxiv.2608.21252"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.21252","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21252","pdf_url":"https://arxiv.org/pdf/2608.21252","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.21252","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136719242","display_name":"Xuanyu Meng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Xuanyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125077824","display_name":"Jiashuo Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sun, Jiashuo","raw_affiliation_strings":["University of Illinois Urbana-Champaign Urbana , Illinois , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign Urbana , Illinois , USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120572342","display_name":"Jash Rajesh Parekh","orcid":"https://orcid.org/0000-0003-3310-4634","observed_orcids":["https://orcid.org/0000-0003-3310-4634"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Parekh, Jash Rajesh","raw_affiliation_strings":["University of Illinois Urbana-Champaign Urbana , Illinois , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign Urbana , Illinois , USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126590770","display_name":"Jiawei Han","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han, Jiawei","raw_affiliation_strings":["University of Illinois Urbana-Champaign Urbana , Illinois , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign Urbana , Illinois , USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9750999808311462,"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":0.9750999808311462,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.01759999990463257,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0032999999821186066,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9760000109672546},{"id":"https://openalex.org/keywords/multi-hop-reasoning","display_name":"multi-hop reasoning","score":0.8659999966621399},{"id":"https://openalex.org/keywords/entity-relationships","display_name":"entity relationships","score":0.4620000123977661}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7872999906539917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7797999978065491},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6809999942779541},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4781000018119812},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.45660001039505005},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3953999876976013},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.3804999887943268},{"id":"https://openalex.org/C105888452","wikidata":"https://www.wikidata.org/wiki/Q7565148","display_name":"Source document","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3472999930381775},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C2778753569","wikidata":"https://www.wikidata.org/wiki/Q1960395","display_name":"Span (engineering)","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C2993776861","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Open domain","level":3,"score":0.2775999903678894},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.27250000834465027},{"id":"https://openalex.org/C2777299769","wikidata":"https://www.wikidata.org/wiki/Q3707858","display_name":"Type (biology)","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.21252","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21252","pdf_url":"https://arxiv.org/pdf/2608.21252","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,"listed_in":[],"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":"doi:10.48550/arxiv.2608.21252","doi":"https://doi.org/10.48550/arxiv.2608.21252","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.21252","pdf_url":null,"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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.21252","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21252","pdf_url":"https://arxiv.org/pdf/2608.21252","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,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204107397.pdf","grobid_xml":"https://content.openalex.org/works/W7204107397.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7210262355","https://openalex.org/W7213230773","https://openalex.org/W4417537698","https://openalex.org/W7152330892","https://openalex.org/W7223136084","https://openalex.org/W7147143482","https://openalex.org/W7164147455","https://openalex.org/W7134836697","https://openalex.org/W7160301386","https://openalex.org/W7166816498"],"abstract_inverted_index":{"Question":[0],"answering":[1],"(QA)":[2],"over":[3],"long,":[4],"connected":[5],"documents":[6,26],"remains":[7],"challenging":[8],"because":[9],"relevant":[10],"evidence":[11,46,127],"may":[12],"span":[13],"multiple":[14],"entities":[15,43],"and":[16,30,92,113,139],"their":[17],"relationships.":[18],"Existing":[19],"retrieval-augmented":[20],"generation":[21],"(RAG)":[22],"methods":[23],"typically":[24],"index":[25],"as":[27,110,155],"raw":[28],"chunks":[29],"retrieve":[31],"them":[32],"through":[33],"embedding":[34],"similarity.":[35],"Their":[36],"performance":[37],"degrades":[38],"when":[39,48],"chunk":[40],"boundaries":[41],"separate":[42],"from":[44,129],"supporting":[45],"or":[47],"a":[49,63,67,84,93],"question":[50],"requires":[51],"multi-hop":[52],"reasoning":[53],"across":[54,165],"the":[55,100,117,121,150],"corpus.":[56],"We":[57],"propose":[58],"EnSI-RAG":[59,141],"(Entity-Structure-Indexed":[60],"Retrieval-Augmented":[61],"Generation),":[62],"framework":[64],"that":[65],"constructs":[66],"query-independent,":[68],"entity-centered":[69],"index.":[70],"Each":[71],"record":[72],"(e,":[73],"t,":[74,83],"k,":[75],"v)":[76],"represents":[77],"an":[78,114,143],"entity":[79],"e,":[80],"its":[81,163],"type":[82],"semantic":[85],"category":[86],"k":[87],"in":[88],"{property,":[89],"relation,":[90],"aspect},":[91],"value":[94],"v,":[95],"while":[96,132],"retaining":[97],"links":[98],"to":[99,149],"original":[101],"source":[102,135],"passages.":[103],"At":[104],"query":[105],"time,":[106],"these":[107,166],"records":[108],"serve":[109],"retrieval":[111],"handles,":[112],"LLM":[115],"synthesizes":[116],"retrieved":[118],"passages":[119],"into":[120],"final":[122],"answer.":[123],"This":[124],"design":[125],"separates":[126],"localization":[128],"answer":[130],"synthesis":[131],"preserving":[133],"traceable":[134],"evidence.":[136],"Across":[137],"Loong":[138],"Oolong,":[140],"achieves":[142],"average":[144],"accuracy":[145],"of":[146],"78.24.":[147],"Relative":[148],"published":[151],"baseline":[152],"scores":[153],"used":[154],"references,":[156],"this":[157],"is":[158,170],"6.62":[159],"points":[160],"higher,":[161],"suggesting":[162],"effectiveness":[164],"settings.":[167],"The":[168],"code":[169],"available":[171],"at":[172],"https://github.com/RamonMeng/EnSI-RAG.":[173]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-25T00:00:00"}
