{"id":"https://openalex.org/W4414311642","doi":"https://doi.org/10.1108/jd-03-2025-0082","title":"Benchmarking large language models for handwritten text recognition","display_name":"Benchmarking large language models for handwritten text recognition","publication_year":2025,"publication_date":"2025-08-15","ids":{"openalex":"https://openalex.org/W4414311642","doi":"https://doi.org/10.1108/jd-03-2025-0082"},"language":"en","primary_location":{"id":"doi:10.1108/jd-03-2025-0082","is_oa":true,"landing_page_url":"https://doi.org/10.1108/jd-03-2025-0082","pdf_url":"https://www.emerald.com/jd/article-pdf/doi/10.1108/JD-03-2025-0082/10070996/jd-03-2025-0082en.pdf","source":{"id":"https://openalex.org/S10082577","display_name":"Journal of Documentation","issn_l":"0022-0418","issn":["0022-0418","1758-7379"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Documentation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.emerald.com/jd/article-pdf/doi/10.1108/JD-03-2025-0082/10070996/jd-03-2025-0082en.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119662608","display_name":"Giorgia Crosilla","orcid":"https://orcid.org/0009-0008-8464-1636"},"institutions":[{"id":"https://openalex.org/I2800371562","display_name":"Societ\u00e0 Italiana di Fisica","ror":"https://ror.org/03bbgsb46","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I2800371562"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Giorgia Crosilla","raw_affiliation_strings":["University of Bologna Department of Classical Philology and Italian Studies, , ,"],"raw_orcid":"https://orcid.org/0009-0008-8464-1636","affiliations":[{"raw_affiliation_string":"University of Bologna Department of Classical Philology and Italian Studies, , ,","institution_ids":["https://openalex.org/I2800371562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081466884","display_name":"Lukas Klic","orcid":"https://orcid.org/0000-0002-9620-7107"},"institutions":[{"id":"https://openalex.org/I4210110242","display_name":"Digital Science (United States)","ror":"https://ror.org/020h4b682","country_code":"US","type":"company","lineage":["https://openalex.org/I4210110242","https://openalex.org/I4210112888","https://openalex.org/I4210118830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lukas Klic","raw_affiliation_strings":["Digital Humanities Lab, Villa I Tatti , ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Humanities Lab, Villa I Tatti , ,","institution_ids":["https://openalex.org/I4210110242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005227218","display_name":"Giovanni Colavizza","orcid":"https://orcid.org/0000-0002-9806-084X"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]},{"id":"https://openalex.org/I2800371562","display_name":"Societ\u00e0 Italiana di Fisica","ror":"https://ror.org/03bbgsb46","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I2800371562"]},{"id":"https://openalex.org/I4210088332","display_name":"University College Copenhagen","ror":"https://ror.org/004r9h172","country_code":"DK","type":"education","lineage":["https://openalex.org/I4210088332"]},{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK","IT"],"is_corresponding":false,"raw_author_name":"Giovanni Colavizza","raw_affiliation_strings":["University of Bologna Department of Classical Philology and Italian Studies, , ,","University of Copenhagen Department of Communication, , ,"],"raw_orcid":"https://orcid.org/0000-0002-9806-084X","affiliations":[{"raw_affiliation_string":"University of Bologna Department of Classical Philology and Italian Studies, , ,","institution_ids":["https://openalex.org/I2800371562"]},{"raw_affiliation_string":"University of Copenhagen Department of Communication, , ,","institution_ids":["https://openalex.org/I124055696","https://openalex.org/I83467386","https://openalex.org/I4210088332"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5119662608"],"corresponding_institution_ids":["https://openalex.org/I2800371562"],"apc_list":null,"apc_paid":null,"fwci":3.3997,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93304678,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"81","issue":"7","first_page":"334","last_page":"354"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"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":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9957000017166138,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9854000210762024,"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/benchmarking","display_name":"Benchmarking","score":0.8102999925613403},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5817000269889832},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5796999931335449},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.576200008392334},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.3012999892234802},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.29739999771118164}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8102999925613403},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7989000082015991},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6287999749183655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5914000272750854},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5817000269889832},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5796999931335449},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.576200008392334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31349998712539673},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2906999886035919},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.28610000014305115},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.27869999408721924},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2630000114440918},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1108/jd-03-2025-0082","is_oa":true,"landing_page_url":"https://doi.org/10.1108/jd-03-2025-0082","pdf_url":"https://www.emerald.com/jd/article-pdf/doi/10.1108/JD-03-2025-0082/10070996/jd-03-2025-0082en.pdf","source":{"id":"https://openalex.org/S10082577","display_name":"Journal of Documentation","issn_l":"0022-0418","issn":["0022-0418","1758-7379"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Documentation","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:publications/00ab4237-fd12-4080-8407-0abb8f0cd18b","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/00ab4237-fd12-4080-8407-0abb8f0cd18b","pdf_url":"https://curis.ku.dk/ws/files/538700348/jd-03-2025-0082en.pdf","source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Crosilla , G , Klic , L & Colavizza , G 2025 , ' Benchmarking large language models for handwritten text recognition ' , Journal of Documentation , vol. 81 , no. 7 , pp. 334-354 . https://doi.org/10.1108/JD-03-2025-0082","raw_type":"article"},{"id":"pmh:oai:cris.unibo.it:11585/1032170","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/en/publications/benchmarking-large-language-models-for-handwritten-text-recogniti/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1108/jd-03-2025-0082","is_oa":true,"landing_page_url":"https://doi.org/10.1108/jd-03-2025-0082","pdf_url":"https://www.emerald.com/jd/article-pdf/doi/10.1108/JD-03-2025-0082/10070996/jd-03-2025-0082en.pdf","source":{"id":"https://openalex.org/S10082577","display_name":"Journal of Documentation","issn_l":"0022-0418","issn":["0022-0418","1758-7379"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Documentation","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320308579","display_name":"Harvard University Center for Italian Renaissance Studies","ror":"https://ror.org/03vek6s52"},{"id":"https://openalex.org/F4320309622","display_name":"Harvard University","ror":"https://ror.org/03vek6s52"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414311642.pdf","grobid_xml":"https://content.openalex.org/works/W4414311642.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1647671624","https://openalex.org/W2007714563","https://openalex.org/W2115746737","https://openalex.org/W2152928267","https://openalex.org/W2286176598","https://openalex.org/W2573601984","https://openalex.org/W2577122925","https://openalex.org/W2786298913","https://openalex.org/W2786974559","https://openalex.org/W2895359355","https://openalex.org/W2949780281","https://openalex.org/W2962707697","https://openalex.org/W2963925710","https://openalex.org/W2987696791","https://openalex.org/W3003990305","https://openalex.org/W3034726763","https://openalex.org/W3101978173","https://openalex.org/W3112478873","https://openalex.org/W3157353160","https://openalex.org/W3181798399","https://openalex.org/W3196329608","https://openalex.org/W3201139606","https://openalex.org/W3208962647","https://openalex.org/W4221148079","https://openalex.org/W4224239860","https://openalex.org/W4224248609","https://openalex.org/W4230557946","https://openalex.org/W4312430353","https://openalex.org/W4362597616","https://openalex.org/W4382202677","https://openalex.org/W4389519044","https://openalex.org/W4390670543","https://openalex.org/W4396562622","https://openalex.org/W4402191334","https://openalex.org/W4403098592","https://openalex.org/W4406614923"],"related_works":[],"abstract_inverted_index":{"Purpose":[0],"The":[1,37,63,134],"aim":[2],"of":[3,11,15,41,45,60,139],"this":[4],"work":[5],"is":[6,39,130],"to":[7,31,48],"provide":[8],"an":[9],"overview":[10],"the":[12,58,103,110,122],"current":[13],"capabilities":[14],"Multimodal":[16],"Large":[17],"Language":[18],"Models":[19],"(MLLMs)":[20],"for":[21,57,94,119],"Handwritten":[22],"Text":[23],"Recognition":[24],"(HTR),":[25],"assessing":[26],"their":[27,97],"potential":[28],"when":[29],"compared":[30],"traditional":[32],"task-specific,":[33],"supervised":[34,55],"models.":[35],"Design/methodology/approach":[36],"approach":[38],"that":[40,66,105],"using":[42],"a":[43,70,79,91,140],"set":[44],"openly-available":[46],"benchmarks":[47],"compare":[49],"different":[50],"LLMs":[51,67,127],"with":[52,99],"strong":[53,71],"task-specific":[54],"baselines":[56],"task":[59],"HTR.":[61],"Findings":[62],"results":[64],"show":[65,69],"currently":[68],"performance":[72,81,124],"on":[73,82,115,144],"English":[74],"texts,":[75],"yet":[76],"they":[77],"demonstrate":[78],"weaker":[80],"languages":[83],"other":[84],"than":[85],"English,":[86],"and":[87,128],"do":[88],"not":[89,131,137],"possess":[90],"significant":[92],"capability":[93],"self-correction.":[95],"Moreover,":[96],"comparison":[98,125],"Transkribus\u2019s":[100],"models":[101,108],"highlight":[102],"fact":[104],"proprietary":[106],"LLM":[107],"are":[109,136],"best":[111],"performing,":[112],"in":[113],"particular":[114],"modern":[116],"handwriting,":[117],"while":[118],"historical":[120],"documents":[121],"overall":[123],"between":[126],"Transkribus":[129],"consistent.":[132],"Originality/value":[133],"authors":[135],"aware":[138],"similar":[141],"study":[142],"relying":[143],"open":[145],"benchmarks.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-09-18T00:00:00"}