{"id":"https://openalex.org/W7154471599","doi":"https://doi.org/10.48550/arxiv.2604.12812","title":"DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding","display_name":"DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding","publication_year":2026,"publication_date":"2026-04-14","ids":{"openalex":"https://openalex.org/W7154471599","doi":"https://doi.org/10.48550/arxiv.2604.12812"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.12812","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.12812","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.12812","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133700755","display_name":"Hao Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133694544","display_name":"Yuliang Liu","orcid":"https://orcid.org/0000-0002-7944-2754"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yuliang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133664791","display_name":"Xingchen Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xingchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133723774","display_name":"Yuyi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yuyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030174783","display_name":"Minghui Liao","orcid":"https://orcid.org/0000-0002-2583-4314"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liao, Minghui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133715856","display_name":"Jihao Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Jihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133634276","display_name":"Wei Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133627814","display_name":"Xiang Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Xiang","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":null,"has_fulltext":false,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9666000008583069,"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":0.9666000008583069,"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":0.008799999952316284,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.0052999998442828655,"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/task","display_name":"Task (project management)","score":0.7034000158309937},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.4999000132083893},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.451200008392334},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.413100004196167},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.40230000019073486},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.38960000872612},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.3873000144958496},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3779999911785126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7914999723434448},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7034000158309937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5898000001907349},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.4999000132083893},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45329999923706055},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.451200008392334},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42260000109672546},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.413100004196167},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.40230000019073486},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28459998965263367},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.12812","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.12812","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.12812","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.12812","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":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"Existing":[0],"Multimodal":[1],"Large":[2],"Language":[3],"Models":[4],"(MLLMs)":[5],"suffer":[6],"from":[7,23,160],"significant":[8],"performance":[9,148],"degradation":[10],"on":[11,95,138,149],"the":[12,69],"long":[13],"document":[14,18],"understanding":[15],"task":[16],"as":[17,44,176],"length":[19],"increases.":[20],"This":[21],"stems":[22],"two":[24],"fundamental":[25],"challenges:":[26],"1)":[27],"a":[28,52,65,73,86,127,177],"low":[29],"Signal-to-Noise":[30],"Ratio":[31],"(SNR),":[32],"with":[33,170],"crucial":[34],"evidence":[35,119],"buried":[36],"in":[37],"irrelevant":[38],"pages;":[39],"and":[40,77,121,152,166],"2)":[41],"supervision":[42],"scarcity,":[43],"datasets":[45],"offering":[46],"only":[47],"final":[48],"short":[49],"answers":[50],"provide":[51],"weak":[53],"learning":[54],"signal.":[55],"In":[56],"this":[57,82],"paper,":[58],"we":[59,84,90,106,125],"address":[60],"these":[61],"challenges":[62],"by":[63],"proposing":[64],"paradigm":[66],"that":[67,144],"requires":[68],"model":[70],"to":[71,132,163],"execute":[72],"structured":[74],"Analysis,":[75],"Localization":[76],"Reasoning":[78],"workflow.":[79],"To":[80],"instill":[81],"capability,":[83],"design":[85],"two-stage":[87],"training":[88,137,162],"framework:":[89],"first":[91],"perform":[92],"Supervised":[93],"Fine-Tuning":[94],"high-quality":[96],"data":[97],"generated":[98],"via":[99],"an":[100,108],"efficient":[101],"knowledge":[102],"distillation":[103],"strategy.":[104],"Subsequently,":[105],"employ":[107],"Evidence-aware":[109],"Group":[110],"Relative":[111],"Policy":[112],"Optimization":[113],"which":[114],"jointly":[115],"optimizes":[116],"for":[117,180],"both":[118,150],"localization":[120],"answer":[122],"accuracy.":[123],"Additionally,":[124],"introduce":[126],"Evidence-Guided":[128],"Resolution":[129],"Allocation":[130],"strategy":[131],"mitigate":[133],"memory":[134],"constraints":[135],"of":[136],"multi-pages":[139],"documents.":[140],"Extensive":[141],"experiments":[142],"demonstrate":[143],"DocSeeker":[145],"achieves":[146],"superior":[147],"in-domain":[151],"out-of-domain":[153],"tasks.":[154],"We":[155],"show":[156],"it":[157],"robustly":[158],"generalizes":[159],"short-page":[161],"ultra-long":[164],"documents":[165],"is":[167],"naturally":[168],"synergistic":[169],"visual":[171],"Retrieval-Augmented":[172],"Generation":[173],"systems,":[174],"serving":[175],"solid":[178],"foundation":[179],"their":[181],"implementation.":[182]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-16T00:00:00"}