{"id":"https://openalex.org/W4416036143","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1062","title":"MultiDocFusion : Hierarchical and Multimodal Chunking Pipeline for Enhanced RAG on Long Industrial Documents","display_name":"MultiDocFusion : Hierarchical and Multimodal Chunking Pipeline for Enhanced RAG on Long Industrial Documents","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036143","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1062"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1062","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1062","pdf_url":"https://aclanthology.org/2025.emnlp-main.1062.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.1062.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101382380","display_name":"JoongMin Shin","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Joongmin Shin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003145618","display_name":"Chanjun Park","orcid":"https://orcid.org/0000-0002-7200-9632"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chanjun Park","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066098676","display_name":"Jeongbae Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeongbae Park","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014883878","display_name":"Jaehyung Seo","orcid":"https://orcid.org/0000-0002-4761-9818"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaehyung Seo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5111217720","display_name":"Heuiseok Lim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heuiseok Lim","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101382380"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32419657,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20996","last_page":"21015"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.12290000170469284,"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"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.12290000170469284,"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"}},{"id":"https://openalex.org/T11609","display_name":"Geophysical Methods and Applications","score":0.06859999895095825,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.06400000303983688,"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/pipeline","display_name":"Pipeline (software)","score":0.608299970626831},{"id":"https://openalex.org/keywords/chunking","display_name":"Chunking (psychology)","score":0.3472999930381775},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.2590999901294708},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2371000051498413}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6852999925613403},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.608299970626831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3986000120639801},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33090001344680786},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2619999945163727},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2410999983549118},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2371000051498413},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.2240999937057495}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1062","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1062","pdf_url":"https://aclanthology.org/2025.emnlp-main.1062.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2604.12352","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.12352","pdf_url":"https://arxiv.org/pdf/2604.12352","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2604.12352","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.12352","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1062","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1062","pdf_url":"https://aclanthology.org/2025.emnlp-main.1062.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1225283220","display_name":null,"funder_award_id":"NRF-2021R","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G2511627992","display_name":null,"funder_award_id":"2024-003","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G3034753964","display_name":null,"funder_award_id":"grant","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G3071639259","display_name":null,"funder_award_id":"2021R1","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G342704958","display_name":null,"funder_award_id":"funded","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G3914271861","display_name":null,"funder_award_id":"2021R1A6A1A030","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G5463329283","display_name":null,"funder_award_id":"COMPA","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G6072120315","display_name":null,"funder_award_id":"funded","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G6181273566","display_name":null,"funder_award_id":"NRF-2021R1A6A1A03045425","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G7102533171","display_name":null,"funder_award_id":"RS-2024-00398115","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G961453132","display_name":null,"funder_award_id":"98115","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G982292920","display_name":null,"funder_award_id":"NRF-20","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320332128","display_name":"Commercializations Promotion Agency for R and D Outcomes","ror":null},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036143.pdf","grobid_xml":"https://content.openalex.org/works/W4416036143.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"RAG-based":[0,137],"QA":[1,103,138],"has":[2],"emerged":[3],"as":[4],"a":[5,38,67],"powerful":[6],"method":[7],"for":[8,119],"processing":[9],"long":[10,23],"industrial":[11,24,91],"documents.However,":[12],"conventional":[13],"text":[14,54],"chunking":[15,40,131],"approaches":[16],"often":[17],"neglect":[18],"the":[19,111,127,134],"complex":[20],"structures":[21],"of":[22,46,63,83,114,129,136],"documents,":[25],"causing":[26],"information":[27],"loss":[28],"and":[29,80,101],"reduced":[30],"answer":[31],"quality.To":[32],"address":[33],"this,":[34],"we":[35],"introduce":[36],"MultiDocFusion,":[37],"multimodal":[39,120],"pipeline":[41],"that":[42,94],"integrates:":[43],"(i)":[44],"detection":[45],"document":[47,51,64,75,117],"regions":[48,58],"using":[49,70],"visionbased":[50],"parsing,":[52],"(ii)":[53],"extraction":[55],"from":[56],"these":[57],"via":[59],"OCR,":[60],"(iii)":[61],"reconstruction":[62],"structure":[65],"into":[66],"hierarchical":[68,77,84],"tree":[69],"large":[71],"language":[72],"model":[73],"(LLM)based":[74],"section":[76],"parsing":[78],"(DSHP-LLM),":[79],"(iv)":[81],"construction":[82],"chunks":[85],"through":[86],"DFS-based":[87],"Grouping.Extensive":[88],"experiments":[89],"across":[90],"benchmarks":[92],"demonstrate":[93],"MultiDocFusion":[95],"improves":[96],"retrieval":[97],"precision":[98],"by":[99,105],"8-15%":[100],"ANLS":[102],"scores":[104],"2-3%":[106],"compared":[107],"to":[108],"baselines,":[109],"emphasizing":[110],"critical":[112],"role":[113],"explicitly":[115],"leveraging":[116],"hierarchy":[118],"document-based":[121],"QA.These":[122],"significant":[123],"performance":[124],"gains":[125],"underscore":[126],"necessity":[128],"structure-aware":[130],"in":[132],"enhancing":[133],"fidelity":[135],"systems.":[139]},"counts_by_year":[],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-11-08T00:00:00"}