{"id":"https://openalex.org/W7124887930","doi":"https://doi.org/10.1109/access.2026.3655813","title":"Enhancing Technical Question Answering Quality Through Multimodal Document Segmentation","display_name":"Enhancing Technical Question Answering Quality Through Multimodal Document Segmentation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7124887930","doi":"https://doi.org/10.1109/access.2026.3655813"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3655813","doi":"https://doi.org/10.1109/access.2026.3655813","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3655813","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","oarl","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3655813","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115708280","display_name":"Dmitry Lvov","orcid":"https://orcid.org/0009-0008-3211-5853","observed_orcids":["https://orcid.org/0009-0008-3211-5853"]},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Dmitry Lvov","raw_affiliation_strings":["Department of Artificial Intelligence, ITMO University, Saint Petersburg, Russia"],"raw_orcid":"https://orcid.org/0009-0008-3211-5853","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, ITMO University, Saint Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069488147","display_name":"Ivan Smirnov","orcid":"https://orcid.org/0009-0002-3690-4733","observed_orcids":["https://orcid.org/0009-0002-3690-4733"]},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Ivan Smirnov","raw_affiliation_strings":["Department of Artificial Intelligence, ITMO University, Saint Petersburg, Russia"],"raw_orcid":"https://orcid.org/0009-0002-3690-4733","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, ITMO University, Saint Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069498907","display_name":"Valeria Volokha","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Valeria Volokha","raw_affiliation_strings":["Department of Artificial Intelligence, ITMO University, Saint Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, ITMO University, Saint Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134020680","display_name":"Anastasia Laushkina","orcid":"https://orcid.org/0000-0001-7887-3299","observed_orcids":["https://orcid.org/0000-0001-7887-3299"]},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Anastasia Laushkina","raw_affiliation_strings":["Department of Artificial Intelligence, ITMO University, Saint Petersburg, Russia"],"raw_orcid":"https://orcid.org/0000-0001-7887-3299","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, ITMO University, Saint Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121300864","display_name":"A. V. Boukhanovsky","orcid":"https://orcid.org/0000-0003-1588-8164","observed_orcids":["https://orcid.org/0000-0003-1588-8164"]},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Alexander Boukhanovsky","raw_affiliation_strings":["Department of Artificial Intelligence, ITMO University, Saint Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, ITMO University, Saint Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I173089394"],"apc_list":{"value":2075,"currency":"USD","value_usd":2075},"apc_paid":{"value":2075,"currency":"USD","value_usd":2075},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"12733","last_page":"12743"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9653000235557556,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9653000235557556,"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/T10028","display_name":"Topic Modeling","score":0.015699999406933784,"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":0.004999999888241291,"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/technical-question-answering","display_name":"technical question answering","score":0.9580000042915344},{"id":"https://openalex.org/keywords/document-segmentation","display_name":"document segmentation","score":0.847000002861023},{"id":"https://openalex.org/keywords/multimodal-document-understanding","display_name":"multimodal document understanding","score":0.7599999904632568},{"id":"https://openalex.org/keywords/multimodal-annotation","display_name":"multimodal annotation","score":0.7590000033378601},{"id":"https://openalex.org/keywords/regulatory-compliance","display_name":"regulatory compliance","score":0.7350000143051147},{"id":"https://openalex.org/keywords/scienceqa","display_name":"ScienceQA","score":0.8360000252723694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8579999804496765},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5878000259399414},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5275999903678894},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5228000283241272},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5169000029563904},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.4880000054836273},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.48660001158714294},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4512999951839447},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.37869998812675476},{"id":"https://openalex.org/C25688753","wikidata":"https://www.wikidata.org/wiki/Q1413406","display_name":"Technical documentation","level":3,"score":0.3617999851703644},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33079999685287476},{"id":"https://openalex.org/C58655809","wikidata":"https://www.wikidata.org/wiki/Q7936186","display_name":"Vision document","level":5,"score":0.3183000087738037},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2994999885559082},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.295199990272522},{"id":"https://openalex.org/C2776235265","wikidata":"https://www.wikidata.org/wiki/Q18392052","display_name":"Fragment (logic)","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27549999952316284},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.2572000026702881},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2572000026702881},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C145644426","wikidata":"https://www.wikidata.org/wiki/Q169411","display_name":"Unified Modeling Language","level":3,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3655813","doi":"https://doi.org/10.1109/access.2026.3655813","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3655813","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","oarl","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2037902bded94d0ab265a310c6b585b3","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/2037902bded94d0ab265a310c6b585b3","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"IEEE Access, Vol 14, Pp 12733-12743 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3655813","doi":"https://doi.org/10.1109/access.2026.3655813","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3655813","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","oarl","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5378999710083008,"display_name":"Industry, innovation and infrastructure"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1483870316","https://openalex.org/W2626778328","https://openalex.org/W2947697927","https://openalex.org/W2997154779","https://openalex.org/W3003484198","https://openalex.org/W3003711898","https://openalex.org/W3047032303","https://openalex.org/W3120043490","https://openalex.org/W3185341429","https://openalex.org/W4290927927","https://openalex.org/W4304013646","https://openalex.org/W4390874575","https://openalex.org/W4399566004","https://openalex.org/W4402422296","https://openalex.org/W4402702988","https://openalex.org/W4402716477","https://openalex.org/W4405064339","https://openalex.org/W4410600332","https://openalex.org/W4412888476","https://openalex.org/W4413145313","https://openalex.org/W4416034444"],"related_works":["https://openalex.org/W4412867399","https://openalex.org/W7131890771","https://openalex.org/W7160540146","https://openalex.org/W4405064339","https://openalex.org/W7169721598","https://openalex.org/W7162136677","https://openalex.org/W4404315596","https://openalex.org/W7196994968","https://openalex.org/W4405468271","https://openalex.org/W4416036143"],"abstract_inverted_index":{"Technical":[0],"documents":[1,52],"present":[2],"unique":[3],"multimodal":[4,44],"understanding":[5],"challenges":[6],"due":[7],"to":[8],"their":[9],"heterogeneous":[10],"information":[11],"elements":[12,64],"requiring":[13],"both":[14],"localized":[15],"visual":[16,60],"interpretation":[17,132],"and":[18,43,101,116,125,136,152],"global":[19,73],"contextual":[20],"reasoning.":[21],"We":[22],"introduce":[23],"a":[24,67],"novel":[25],"two-tiered":[26],"augmentation":[27],"strategy":[28],"that":[29,50,71],"uniquely":[30],"bridges":[31],"this":[32],"gap":[33],"by":[34,114],"generating":[35],"semantically":[36],"enriched":[37],"document":[38,93],"fragments":[39],"through":[40],"layout-aware":[41],"segmentation":[42],"annotation.":[45],"Unlike":[46],"conventional":[47],"RAG":[48],"approaches":[49],"process":[51],"as":[53],"atomic":[54],"text":[55],"units,":[56],"our":[57,143],"methodology":[58],"preserves":[59],"integrity":[61],"of":[62,133],"technical":[63,141],"while":[65],"creating":[66],"hierarchical":[68],"evidence":[69,81],"structure":[70],"balances":[72],"context":[74],"(via":[75,82],"Page-Augmented":[76],"Retrieval)":[77],"with":[78],"precise":[79],"local":[80],"Localized":[83],"Fragment":[84],"Augmentation).":[85],"This":[86],"approach":[87],"addresses":[88],"the":[89,95],"fundamental":[90],"limitation":[91],"in":[92],"AI:":[94],"trade-off":[96],"between":[97],"preserving":[98],"spatial":[99],"relationships":[100],"providing":[102],"task-relevant":[103],"context.":[104],"Our":[105],"method":[106],"achieves":[107],"state-of-the-art":[108],"results,":[109],"improving":[110],"GPT-4\u2019s":[111],"DesignQA":[112],"performance":[113],"22.4%":[115],"demonstrating":[117],"strong":[118],"generalizability":[119],"on":[120],"ScienceQA":[121],"(85.3%":[122],"MC":[123],"accuracy)":[124],"MMMU":[126],"(66.7%":[127],"overall).":[128],"By":[129],"enabling":[130],"accurate":[131],"design":[134,150],"constraints":[135],"functional":[137],"requirements":[138],"directly":[139],"from":[140],"documentation,":[142],"framework":[144],"advances":[145],"AI":[146],"systems":[147],"for":[148],"engineering":[149],"verification":[151],"regulatory":[153],"compliance.":[154],"Code":[155],"will":[156],"be":[157],"available":[158],"at":[159],"https://github.com/LvovDmitro/mmqa-segmentation.":[160]},"counts_by_year":[],"updated_date":"2026-11-13T13:42:25.865203","created_date":"2026-01-21T00:00:00"}