{"id":"https://openalex.org/W4415320162","doi":"https://doi.org/10.48550/arxiv.2505.11651","title":"MIRACL-VISION: A Large, multilingual, visual document retrieval benchmark","display_name":"MIRACL-VISION: A Large, multilingual, visual document retrieval benchmark","publication_year":2025,"publication_date":"2025-05-16","ids":{"openalex":"https://openalex.org/W4415320162","doi":"https://doi.org/10.48550/arxiv.2505.11651"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.11651","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.11651","pdf_url":"https://arxiv.org/pdf/2505.11651","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.11651","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107496333","display_name":"Radek Osmulski","orcid":"https://orcid.org/0009-0007-0208-5211","observed_orcids":["https://orcid.org/0009-0007-0208-5211"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Osmulski, Radek","raw_affiliation_strings":["NVIDIA Berlin , Germany","NVIDIA Brisbane , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Berlin , Germany","institution_ids":[]},{"raw_affiliation_string":"NVIDIA Brisbane , Australia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054449710","display_name":"Gabriel de Souza Pereira Moreira","orcid":"https://orcid.org/0000-0002-9745-5014","observed_orcids":["https://orcid.org/0000-0002-9745-5014"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moreira, Gabriel de Souza P.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110359515","display_name":"Ronay Ak","orcid":"https://orcid.org/0000-0003-2768-6535","observed_orcids":["https://orcid.org/0000-0003-2768-6535"]},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ak, Ronay","raw_affiliation_strings":["NVIDIA Berlin , Germany","NVIDIA Sarasota , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Berlin , Germany","institution_ids":[]},{"raw_affiliation_string":"NVIDIA Sarasota , USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112528146","display_name":"Mengyao Xu","orcid":"https://orcid.org/0009-0000-5772-1739","observed_orcids":["https://orcid.org/0009-0000-5772-1739"]},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu, Mengyao","raw_affiliation_strings":["NVIDIA Berlin , Germany","NVIDIA Santa Clara , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Berlin , Germany","institution_ids":[]},{"raw_affiliation_string":"NVIDIA Santa Clara , USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061514003","display_name":"Benedikt Schifferer","orcid":"https://orcid.org/0009-0007-0941-4110","observed_orcids":["https://orcid.org/0009-0007-0941-4110"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schifferer, Benedikt","raw_affiliation_strings":["NVIDIA S\u00e3o Paulo , Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA S\u00e3o Paulo , Brazil","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023954126","display_name":"Even Oldridge","orcid":"https://orcid.org/0009-0002-1990-0941","observed_orcids":["https://orcid.org/0009-0002-1990-0941"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oldridge, Even","raw_affiliation_strings":["NVIDIA Vancouver , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Vancouver , Canada","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":16,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.551800012588501,"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"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.551800012588501,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.36399999260902405,"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":0.03779999911785126,"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/multilingual-information-retrieval","display_name":"multilingual information retrieval","score":0.5950000286102295},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.765999972820282},{"id":"https://openalex.org/keywords/retrieval-benchmark","display_name":"retrieval benchmark","score":0.6380000114440918},{"id":"https://openalex.org/keywords/document-layout","display_name":"document layout","score":0.4129999876022339},{"id":"https://openalex.org/keywords/tables-and-charts","display_name":"charts and tables","score":0.49300000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8476999998092651},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7465000152587891},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6338000297546387},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.5990999937057495},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.5202999711036682},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.515999972820282},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.47369998693466187},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4697999954223633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4171000123023987},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4153999984264374},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4099999964237213},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4036000072956085},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3971000015735626},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C156365220","wikidata":"https://www.wikidata.org/wiki/Q845734","display_name":"Infographic","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C90288658","wikidata":"https://www.wikidata.org/wiki/Q3318149","display_name":"Human\u2013computer information retrieval","level":3,"score":0.3659999966621399},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.2687999904155731}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.11651","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.11651","pdf_url":"https://arxiv.org/pdf/2505.11651","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.11651","doi":"https://doi.org/10.48550/arxiv.2505.11651","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.11651","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.11651","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.11651","pdf_url":"https://arxiv.org/pdf/2505.11651","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415320162.pdf","grobid_xml":"https://content.openalex.org/works/W4415320162.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W3015883388","https://openalex.org/W3153833878","https://openalex.org/W4306891354","https://openalex.org/W4310923309","https://openalex.org/W4386185600","https://openalex.org/W4391709827","https://openalex.org/W4400373146","https://openalex.org/W4402670856","https://openalex.org/W4402672004","https://openalex.org/W4404782721","https://openalex.org/W4404783220","https://openalex.org/W4405090824","https://openalex.org/W4405173149","https://openalex.org/W4406879573","https://openalex.org/W4413146941"],"related_works":["https://openalex.org/W6910650483","https://openalex.org/W4400373146","https://openalex.org/W4415545971","https://openalex.org/W4411268915","https://openalex.org/W7165867757","https://openalex.org/W4405032003","https://openalex.org/W7133662660","https://openalex.org/W4415244801","https://openalex.org/W7165689667","https://openalex.org/W7117277172"],"abstract_inverted_index":{"Document":[0],"retrieval":[1,50,76,105,127,205,210,220,239],"is":[2,113,222,230],"an":[3,114],"important":[4],"task":[5],"for":[6,164,213,237,249],"search":[7],"and":[8,32,38,91,112,185,241],"Retrieval-Augmented":[9],"Generation":[10],"(RAG)":[11],"applications.":[12],"Large":[13],"Language":[14],"Models":[15],"(LLMs)":[16],"have":[17,52,160],"contributed":[18],"to":[19,62,123,137,143,148,202,226],"improving":[20],"the":[21,117,156,166,170,214,217,244],"accuracy":[22,206,221],"of":[23,116],"text-based":[24,125,209,227],"document":[25,49,75,104,250],"retrieval.":[26,251],"However,":[27],"documents":[28],"with":[29,178,200],"complex":[30],"layout":[31],"visual":[33,57,74,103,218,238],"elements":[34],"like":[35],"tables,":[36],"charts":[37],"infographics":[39],"are":[40,77],"not":[41],"perfectly":[42],"represented":[43],"in":[44,192],"textual":[45],"format.":[46],"Recently,":[47],"image-based":[48],"pipelines":[51,240],"become":[53],"popular,":[54],"which":[55],"use":[56],"large":[58],"language":[59],"models":[60,196,219,248],"(VLMs)":[61],"retrieve":[63],"relevant":[64],"page":[65],"images":[66],"given":[67],"a":[68,93,101,120,133,162,190,208,231],"query.":[69],"Current":[70],"evaluation":[71,106,150,235],"benchmarks":[72],"on":[73,87,197],"limited,":[78],"as":[79],"they":[80],"primarily":[81],"focus":[82],"only":[83],"English":[84,215],"language,":[85,216],"rely":[86],"synthetically":[88],"generated":[89],"questions":[90],"offer":[92],"small":[94],"corpus":[95,146],"size.":[96],"Therefore,":[97],"we":[98,159],"introduce":[99],"MIRACL-VISION,":[100],"multilingual":[102,126,198,234],"benchmark.":[107],"MIRACL-VISION":[108,145,177,229],"covers":[109],"18":[110],"languages,":[111],"extension":[115],"MIRACL":[118,129],"dataset,":[119],"popular":[121,182],"benchmark":[122,236],"evaluate":[124],"pipelines.":[128],"was":[130],"built":[131],"using":[132,181],"human-intensive":[134],"annotation":[135],"process":[136],"generate":[138],"high-quality":[139],"questions.":[140],"In":[141],"order":[142],"reduce":[144],"size":[147],"make":[149],"more":[151],"compute":[152],"friendly":[153],"while":[154],"keeping":[155],"datasets":[157],"challenging,":[158,232],"designed":[161],"method":[163],"eliminating":[165],"\"easy\"":[167],"negatives":[168],"from":[169],"corpus.":[171],"We":[172,188],"conducted":[173],"extensive":[174],"experiments":[175],"comparing":[176],"other":[179],"benchmarks,":[180],"public":[183],"text":[184],"image":[186],"models.":[187,211,228],"observe":[189],"gap":[191],"state-of-the-art":[193],"VLM-based":[194],"embedding":[195],"capabilities,":[199],"up":[201],"59.7%":[203],"lower":[204,224],"than":[207],"Even":[212],"12.1%":[223],"compared":[225],"representative,":[233],"will":[242],"help":[243],"community":[245],"build":[246],"robust":[247]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-18T00:00:00"}