{"id":"https://openalex.org/W4417493454","doi":null,"title":"HW-MLVQA: Elucidating Multilingual Handwritten Document Understanding with a Comprehensive VQA Benchmark","display_name":"HW-MLVQA: Elucidating Multilingual Handwritten Document Understanding with a Comprehensive VQA Benchmark","publication_year":2025,"publication_date":"2025-07-21","ids":{"openalex":"https://openalex.org/W4417493454"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2507.15655","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15655","pdf_url":"https://arxiv.org/pdf/2507.15655","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"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.15655","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059378440","display_name":"Aniket Pal","orcid":"https://orcid.org/0000-0002-9971-8674","observed_orcids":["https://orcid.org/0000-0002-9971-8674"]},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pal, Aniket","raw_affiliation_strings":["CVIT , IIIT Hyderabad "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CVIT , IIIT Hyderabad ","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052301812","display_name":"Ajoy Mondal","orcid":"https://orcid.org/0000-0002-4808-8860","observed_orcids":["https://orcid.org/0000-0002-4808-8860"]},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mondal, Ajoy","raw_affiliation_strings":["CVIT , IIIT Hyderabad "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CVIT , IIIT Hyderabad ","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026729420","display_name":"Minesh Mathew","orcid":"https://orcid.org/0000-0002-0809-2590","observed_orcids":["https://orcid.org/0000-0002-0809-2590"]},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mathew, Minesh","raw_affiliation_strings":["CVIT , IIIT Hyderabad "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CVIT , IIIT Hyderabad ","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053112307","display_name":"C. V. Jawahar","orcid":"https://orcid.org/0000-0001-6767-7057","observed_orcids":["https://orcid.org/0000-0001-6767-7057"]},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jawahar, C. V.","raw_affiliation_strings":["CVIT , IIIT Hyderabad "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CVIT , IIIT Hyderabad ","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I64189192"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9448000192642212,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9448000192642212,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.05350000038743019,"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":0.0005000000237487257,"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/ocr-evaluation","display_name":"OCR evaluation","score":0.593999981880188},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.6669999957084656},{"id":"https://openalex.org/keywords/handwriting-recognition","display_name":"handwriting recognition","score":0.45100000500679016},{"id":"https://openalex.org/keywords/image-text-understanding","display_name":"image-text understanding","score":0.33500000834465027}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8511000275611877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.77920001745224},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6865000128746033},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.59170001745224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5533000230789185},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4465000033378601},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34380000829696655},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.273499995470047},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2507.15655","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15655","pdf_url":"https://arxiv.org/pdf/2507.15655","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.15655","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15655","pdf_url":"https://arxiv.org/pdf/2507.15655","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417493454.pdf","grobid_xml":"https://content.openalex.org/works/W4417493454.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2251512949","https://openalex.org/W2936135081","https://openalex.org/W2962749469","https://openalex.org/W2963341956","https://openalex.org/W2980404057","https://openalex.org/W3045462440","https://openalex.org/W3200050180","https://openalex.org/W4321854000","https://openalex.org/W4389524513","https://openalex.org/W4401306886","https://openalex.org/W4403853618"],"related_works":["https://openalex.org/W4415106390","https://openalex.org/W7203856511","https://openalex.org/W7214796471","https://openalex.org/W4414311642","https://openalex.org/W4413000190","https://openalex.org/W7204154938","https://openalex.org/W6910650483","https://openalex.org/W7203965592","https://openalex.org/W6929653720","https://openalex.org/W4415540439"],"abstract_inverted_index":{"The":[0,135],"proliferation":[1],"of":[2,12,56,73,84,119,129],"MultiLingual":[3],"Visual":[4],"Question":[5],"Answering":[6],"(MLVQA)":[7],"benchmarks":[8],"augments":[9],"the":[10,26,40,53,71],"capabilities":[11,49],"large":[13],"language":[14],"models":[15],"(LLMs)":[16],"and":[17,30,106,131,149],"multi-modal":[18],"LLMs,":[19],"thereby":[20],"enabling":[21],"them":[22],"to":[23,45,69,138],"adeptly":[24],"capture":[25],"intricate":[27],"linguistic":[28],"subtleties":[29],"visual":[31],"complexities":[32],"inherent":[33],"across":[34],"diverse":[35],"languages.":[36],"Despite":[37],"its":[38,48],"potential,":[39],"current":[41],"MLVQA":[42],"model":[43],"struggles":[44],"fully":[46],"utilize":[47],"when":[50],"dealing":[51],"with":[52],"extensive":[54,82],"variety":[55],"handwritten":[57,86,144],"documents.":[58],"This":[59],"article":[60],"delineates":[61],"HW-MLVQA,":[62],"an":[63,81,107],"avant-garde":[64],"VQA":[65],"benchmark":[66,97,136],"meticulously":[67],"crafted":[68],"mitigate":[70],"dearth":[72],"authentic":[74,115],"Multilingual":[75],"Handwritten":[76],"document":[77,145],"comprehension.":[78],"HW-MLVQA":[79],"encompasses":[80],"collection":[83],"1,600":[85],"Pages":[87],"complemented":[88],"by":[89],"2,400":[90],"question-answers.":[91],"Furthermore,":[92],"it":[93],"provides":[94],"a":[95,126],"robust":[96],"evaluation":[98],"framework":[99],"spanning":[100],"three":[101],"distinct":[102],"modalities:":[103],"text,":[104],"image,":[105],"integrated":[108],"image":[109],"&":[110],"text":[111],"modality.":[112],"To":[113],"simulate":[114],"real-world":[116],"contexts":[117],"devoid":[118],"ground":[120],"truth":[121],"textual":[122],"transcriptions,":[123],"we":[124],"facilitates":[125],"rigorous":[127],"assessment":[128],"proprietary":[130],"open-source":[132],"OCR":[133],"models.":[134],"aspires":[137],"facilitate":[139],"pivotal":[140],"advancements":[141],"in":[142],"multilingual":[143],"interpretation,":[146],"fostering":[147],"innovation":[148],"scholarly":[150],"inquiry":[151],"within":[152],"this":[153],"specialized":[154],"domain.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}