{"id":"https://openalex.org/W7167262568","doi":"https://doi.org/10.48550/arxiv.2607.01420","title":"MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering","display_name":"MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering","publication_year":2026,"publication_date":"2026-07-01","ids":{"openalex":"https://openalex.org/W7167262568","doi":"https://doi.org/10.48550/arxiv.2607.01420"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.01420","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.01420","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2607.01420","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139983025","display_name":"Dang Quang Thien Tran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tran, Dang Quang Thien","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113410427","display_name":"Quang V. Dang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dang, Quang V.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139955723","display_name":"Vinamra Tyagi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tyagi, Vinamra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140016422","display_name":"Sai Soorya Rao Veeravalli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Veeravalli, Sai Soorya Rao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140017945","display_name":"Trang Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Trang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139961512","display_name":"Ryan A. Rossi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rossi, Ryan A.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028863551","display_name":"Franck Dernoncourt","orcid":"https://orcid.org/0000-0002-1119-1346"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dernoncourt, Franck","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016933602","display_name":"Nedim Lipka","orcid":"https://orcid.org/0000-0002-3779-7784"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lipka, Nedim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140016854","display_name":"Koustava Goswami","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Goswami, Koustava","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139962978","display_name":"Samyadeep Basu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Basu, Samyadeep","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/T10028","display_name":"Topic Modeling","score":0.7139999866485596,"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":0.7139999866485596,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.05559999868273735,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.05429999902844429,"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/attribution","display_name":"Attribution","score":0.8646000027656555},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5666000247001648},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.534500002861023},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5223000049591064},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4799000024795532},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4083999991416931}],"concepts":[{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.8646000027656555},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.649399995803833},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5666000247001648},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.534500002861023},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5223000049591064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5123999714851379},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4799000024795532},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45840001106262207},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4083999991416931},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3686000108718872},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3208000063896179},{"id":"https://openalex.org/C3020202489","wikidata":"https://www.wikidata.org/wiki/Q2032038","display_name":"Authorship attribution","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.01420","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.01420","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2607.01420","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.01420","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"score":0.5888311266899109,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0,38],"grounded":[1,89],"QA":[2],"systems":[3],"are":[4],"increasingly":[5],"deployed":[6],"in":[7,30,90,108],"AI":[8],"assistants,":[9],"accurately":[10],"attributing":[11],"generated":[12],"answers":[13],"to":[14,60,159,167],"evidence":[15,63],"is":[16,98],"critical":[17],"for":[18,71,86,105,146],"user":[19],"trust":[20],"and":[21,57,128,149],"model":[22],"safety.":[23],"While":[24],"unimodal":[25,148],"attributions":[26,85,156],"have":[27],"been":[28],"explored":[29],"depth,":[31],"the":[32,72,99,130,162,170],"multimodal":[33,91,106,150],"setting":[34],"remains":[35],"relatively":[36],"under-researched.":[37],"a":[39,44,50,65,77,118],"result,":[40],"we":[41,74],"introduce":[42,75],"MultAttnAttrib,":[43],"training-free":[45],"attribution-generation":[46,121],"method":[47,139],"that":[48,114],"leverages":[49],"model's":[51],"prefill":[52],"pass,":[53],"selected":[54],"attention":[55],"heads,":[56],"calibrated":[58],"thresholds":[59],"locate":[61],"source":[62,92],"within":[64],"document.":[66],"To":[67,94],"establish":[68],"baseline":[69],"results":[70,112],"method,":[73],"MultAttrEval,":[76],"complementary":[78],"benchmark":[79],"dataset":[80,102],"annotated":[81],"with":[82],"fine-grained,":[83],"ground-truth":[84],"answer":[87],"components":[88],"documents.":[93,110],"our":[95],"knowledge,":[96],"this":[97],"first":[100],"evaluation":[101],"designed":[103],"specifically":[104],"attribution":[107,144,151],"long-form":[109],"Experimental":[111],"show":[113],"MultAttnAttrib":[115],"consistently":[116],"outperforms":[117],"variety":[119],"of":[120,161],"methods,":[122],"including":[123],"several":[124],"strong":[125],"prompting-based":[126],"approaches":[127],"matches":[129],"latest":[131],"frontier":[132],"models":[133],"such":[134],"as":[135],"GPT":[136],"5.4.":[137],"Our":[138],"not":[140],"only":[141],"substantially":[142],"improves":[143],"accuracy":[145],"both":[147],"types,":[152],"but":[153],"also":[154],"produces":[155],"at":[157],"up":[158],"one-seventh":[160],"direct":[163],"inference":[164],"latency":[165],"compared":[166],"prompting":[168],"on":[169],"same":[171],"base":[172],"model.":[173]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-04T00:00:00"}