{"id":"https://openalex.org/W4415428138","doi":"https://doi.org/10.3233/faia251212","title":"Reframing Multimodal Complex Document Layout Understanding: A Layout-Aware Multi-Source Reasoning Decision Framework","display_name":"Reframing Multimodal Complex Document Layout Understanding: A Layout-Aware Multi-Source Reasoning Decision Framework","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428138","doi":"https://doi.org/10.3233/faia251212"},"language":null,"primary_location":{"id":"doi:10.3233/faia251212","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251212","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia251212","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100400797","display_name":"Ran Chen","orcid":"https://orcid.org/0000-0001-9875-4588"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ran Chen","raw_affiliation_strings":["Department of Information and Computational Sciences, School of Mathematical Sciences, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Information and Computational Sciences, School of Mathematical Sciences, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101526646","display_name":"Yuyang Zhou","orcid":"https://orcid.org/0000-0002-4915-0486"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuyang Zhou","raw_affiliation_strings":["Department of Information and Computational Sciences, School of Mathematical Sciences, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Information and Computational Sciences, School of Mathematical Sciences, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102565860","display_name":"Jingyang Deng","orcid":"https://orcid.org/0009-0008-3487-225X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyang Deng","raw_affiliation_strings":["Department of Information and Computational Sciences, School of Mathematical Sciences, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Information and Computational Sciences, School of Mathematical Sciences, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055103553","display_name":"Zeren Zhang","orcid":"https://orcid.org/0000-0003-0573-0339"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeren Zhang","raw_affiliation_strings":["Department of Information and Computational Sciences, School of Mathematical Sciences, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Information and Computational Sciences, School of Mathematical Sciences, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110967348","display_name":"Xuefei Tong","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefei Tong","raw_affiliation_strings":["Department of Information and Computational Sciences, School of Mathematical Sciences, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Information and Computational Sciences, School of Mathematical Sciences, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067164993","display_name":"Jinwen Ma","orcid":"https://orcid.org/0000-0002-7388-4295"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinwen Ma","raw_affiliation_strings":["Department of Information and Computational Sciences, School of Mathematical Sciences, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Information and Computational Sciences, School of Mathematical Sciences, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109344908","display_name":"Qinglei Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qinghui Shi","raw_affiliation_strings":["Tongfang Knowledge Network Digital Technology Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Tongfang Knowledge Network Digital Technology Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101898621","display_name":"Qian Xu","orcid":"https://orcid.org/0000-0002-9818-7664"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian Xu","raw_affiliation_strings":["Tongfang Knowledge Network Digital Technology Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Tongfang Knowledge Network Digital Technology Co., Ltd","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020977029","display_name":"Yuanjun Li","orcid":"https://orcid.org/0000-0003-4433-6297"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanjun Li","raw_affiliation_strings":["Tongfang Knowledge Network Digital Technology Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Tongfang Knowledge Network Digital Technology Co., Ltd","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5100400797"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50468608,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9718000292778015,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9718000292778015,"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/T12031","display_name":"Speech and dialogue systems","score":0.939300000667572,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9275000095367432,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.492000013589859},{"id":"https://openalex.org/keywords/reasoning-system","display_name":"Reasoning system","score":0.48660001158714294},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.46129998564720154},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4578000009059906},{"id":"https://openalex.org/keywords/analytic-reasoning","display_name":"Analytic reasoning","score":0.44929999113082886},{"id":"https://openalex.org/keywords/cognitive-reframing","display_name":"Cognitive reframing","score":0.43880000710487366},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.4316999912261963},{"id":"https://openalex.org/keywords/qualitative-reasoning","display_name":"Qualitative reasoning","score":0.39730000495910645},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.38920000195503235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7587000131607056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5182999968528748},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.492000013589859},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.48660001158714294},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.46129998564720154},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4578000009059906},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.44929999113082886},{"id":"https://openalex.org/C187029079","wikidata":"https://www.wikidata.org/wiki/Q958679","display_name":"Cognitive reframing","level":2,"score":0.43880000710487366},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.4316999912261963},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.39730000495910645},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.38920000195503235},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.36309999227523804},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.3490000069141388},{"id":"https://openalex.org/C43971567","wikidata":"https://www.wikidata.org/wiki/Q3142865","display_name":"Logical reasoning","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C156201811","wikidata":"https://www.wikidata.org/wiki/Q5418360","display_name":"Evidential reasoning approach","level":4,"score":0.32580000162124634},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32109999656677246},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2872999906539917},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28139999508857727},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C21847791","wikidata":"https://www.wikidata.org/wiki/Q191081","display_name":"Logical conjunction","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.26840001344680786},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2628999948501587}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia251212","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251212","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia251212","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251212","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"large":[1],"language":[2],"models":[3,62],"(MLLMs)":[4],"have":[5],"achieved":[6],"significant":[7],"progress":[8],"in":[9,189],"document":[10,196],"understanding.":[11,198],"However,":[12],"complex":[13,71,88,195],"layout":[14,72,89,173,197],"reasoning,":[15],"characterized":[16],"by":[17,110],"concise":[18],"answers":[19],"and":[20,40,53,68,115,130,178],"cross-page":[21],"integration,":[22],"remains":[23],"a":[24,92,150],"challenge.":[25],"Unlike":[26],"conventional":[27],"semantics-oriented":[28],"tasks,":[29],"this":[30],"task":[31,94],"demands":[32],"accurate":[33],"visual":[34,113],"perception":[35],"of":[36,59],"fine-grained":[37],"structural":[38],"elements":[39],"logical":[41,179],"reasoning":[42,66,90,97,101,108,137],"across":[43],"multi-page":[44],"documents.":[45],"Existing":[46],"approaches":[47],"primarily":[48],"focus":[49],"on":[50,159,168],"information":[51,176],"extraction":[52],"semantic":[54],"understanding,":[55,175],"limiting":[56],"the":[57,79,100,136,155,169],"capacity":[58],"fine-tuned":[60],"autoregressive":[61],"to":[63,70,148],"capture":[64],"short-answer":[65],"signals":[67],"generalize":[69],"structures.":[73],"To":[74],"address":[75],"this,":[76],"we":[77,141],"propose":[78],"Layout-Aware":[80],"Multi-Source":[81],"Reasoning":[82,127],"Decision":[83],"Framework":[84],"(LAMRD),":[85],"which":[86],"reframes":[87],"as":[91],"decision-making":[93],"over":[95],"multi-source":[96],"paths.":[98,161],"In":[99,135],"path":[102,138],"construction":[103],"stage,":[104,140],"LAMRD":[105,185],"generates":[106],"layout-aware":[107],"paths":[109],"integrating":[111],"internal":[112],"cues":[114],"external":[116],"knowledge":[117],"from":[118],"three":[119],"complementary":[120],"perspectives:":[121],"Visual":[122],"Structural":[123],"Awareness":[124],"(VSA),":[125],"Logical":[126],"Paths":[128],"(LRP),":[129],"External":[131],"Knowledge":[132],"Augmentation":[133],"(EKA).":[134],"decision":[139,151],"employ":[142],"Group":[143],"Relative":[144],"Policy":[145],"Optimization":[146],"(GRPO)":[147],"train":[149],"model":[152],"that":[153,184],"produces":[154],"final":[156],"answer":[157],"based":[158],"these":[160],"We":[162],"conduct":[163],"comprehensive":[164],"evaluations":[165],"using":[166],"Qwen2.5-VL-7B-Instruct":[167],"CEP-7K":[170],"dataset,":[171],"covering":[172],"structure":[174],"extraction,":[177],"association.":[180],"Experimental":[181],"results":[182],"demonstrate":[183],"outperforms":[186],"advanced":[187],"MLLMs":[188],"accuracy,":[190],"validating":[191],"its":[192],"effectiveness":[193],"for":[194]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}