{"id":"https://openalex.org/W7104372646","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1339","title":"Equipping Retrieval-Augmented Large Language Models with Document Structure Awareness","display_name":"Equipping Retrieval-Augmented Large Language Models with Document Structure Awareness","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7104372646","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1339"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1339","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1339","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1339.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.1339.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Lingnan Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lingnan Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Chong Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chong Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Kaiyuan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaiyuan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Liu Zhengyong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu Zhengyong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wenqiang Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenqiang Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Fanqing Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fanqing Meng","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":0.57566569,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24608","last_page":"24631"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.30809998512268066,"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":0.30809998512268066,"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":0.18400000035762787,"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":0.17470000684261322,"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/language-model","display_name":"Language model","score":0.3546000123023987},{"id":"https://openalex.org/keywords/information-structure","display_name":"Information structure","score":0.33320000767707825},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3327000141143799},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3059000074863434},{"id":"https://openalex.org/keywords/information-model","display_name":"Information model","score":0.2903999984264374},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.271699994802475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6690000295639038},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4154999852180481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3580999970436096},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C2779954242","wikidata":"https://www.wikidata.org/wiki/Q6031227","display_name":"Information structure","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.33149999380111694},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C21338462","wikidata":"https://www.wikidata.org/wiki/Q1662581","display_name":"Information model","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.26750001311302185},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1339","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1339","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1339.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.1339","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1339","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1339.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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7104372646.pdf","grobid_xml":"https://content.openalex.org/works/W7104372646.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"demonstrate":[5],"impressive":[6],"capabilities,":[7],"their":[8],"reliance":[9],"on":[10,113],"parametric":[11],"knowledge":[12],"often":[13],"leads":[14],"to":[15,70,83,132],"factual":[16],"inaccuracies.Retrieval-Augmented":[17],"Generation":[18],"(RAG)":[19],"mitigates":[20],"this":[21,45],"by":[22,44,107],"leveraging":[23],"external":[24],"documents,":[25],"yet":[26],"existing":[27],"approaches":[28],"treat":[29],"retrieved":[30],"passages":[31],"as":[32,94],"isolated":[33],"chunks,":[34],"ignoring":[35],"valuable":[36],"structure":[37,74],"that":[38,56,123],"is":[39],"crucial":[40],"for":[41],"document":[42,73,92],"organization.Motivated":[43],"gap,":[46],"we":[47],"propose":[48],"Retrieve-DocumentRoute-Read":[49],"(RDR":[50],"2":[51,65,118],"),":[52],"a":[53,95],"novel":[54],"framework":[55],"explicitly":[57],"incorporates":[58],"structural":[59,125],"information":[60],"throughout":[61],"the":[62],"RAG":[63,129],"process.RDR":[64],"employs":[66],"an":[67],"LLM-based":[68],"router":[69],"dynamically":[71],"navigate":[72],"trees,":[75],"jointly":[76],"evaluating":[77],"content":[78],"relevance":[79],"and":[80,102,134],"hierarchical":[81],"relationships":[82],"assemble":[84],"optimal":[85],"evidence.Our":[86],"key":[87],"innovation":[88],"lies":[89],"in":[90,138],"formulating":[91],"routing":[93],"trainable":[96],"task,":[97],"with":[98],"automatic":[99],"action":[100],"curation":[101],"structureaware":[103],"passage":[104],"selection":[105],"inspired":[106],"human":[108],"reading":[109],"strategies.Through":[110],"comprehensive":[111],"evaluation":[112],"five":[114],"challenging":[115],"datasets,":[116],"RDR":[117],"achieves":[119],"state-of-the-art":[120],"performance,":[121],"demonstrating":[122],"explicit":[124],"awareness":[126],"significantly":[127],"enhances":[128],"systems'":[130],"ability":[131],"acquire":[133],"utilize":[135],"knowledge,":[136],"particularly":[137],"complex":[139],"scenarios":[140],"requiring":[141],"multi-document":[142],"synthesis.":[143]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}