{"id":"https://openalex.org/W4409395937","doi":"https://doi.org/10.1093/llc/fqaf026","title":"XunZi-MLLM: a multimodal large language model for ancient text and image recognition","display_name":"XunZi-MLLM: a multimodal large language model for ancient text and image recognition","publication_year":2025,"publication_date":"2025-04-10","ids":{"openalex":"https://openalex.org/W4409395937","doi":"https://doi.org/10.1093/llc/fqaf026"},"language":"en","primary_location":{"id":"doi:10.1093/llc/fqaf026","is_oa":false,"landing_page_url":"https://doi.org/10.1093/llc/fqaf026","pdf_url":null,"source":{"id":"https://openalex.org/S2734814886","display_name":"Digital Scholarship in the Humanities","issn_l":"2055-7671","issn":["2055-7671","2055-768X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital Scholarship in the Humanities","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101537504","display_name":"Dongmei Zhu","orcid":"https://orcid.org/0000-0002-2684-8830"},"institutions":[{"id":"https://openalex.org/I119454577","display_name":"Nanjing Agricultural University","ror":"https://ror.org/05td3s095","country_code":"CN","type":"education","lineage":["https://openalex.org/I119454577"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dongmei Zhu","raw_affiliation_strings":["College of Information Management, Nanjing Agricultural University , Nanjing 210095,"],"affiliations":[{"raw_affiliation_string":"College of Information Management, Nanjing Agricultural University , Nanjing 210095,","institution_ids":["https://openalex.org/I119454577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353315","display_name":"Chang Liu","orcid":"https://orcid.org/0000-0002-9306-2475"},"institutions":[{"id":"https://openalex.org/I119454577","display_name":"Nanjing Agricultural University","ror":"https://ror.org/05td3s095","country_code":"CN","type":"education","lineage":["https://openalex.org/I119454577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Liu","raw_affiliation_strings":["College of Information Management, Nanjing Agricultural University , Nanjing 210095,"],"affiliations":[{"raw_affiliation_string":"College of Information Management, Nanjing Agricultural University , Nanjing 210095,","institution_ids":["https://openalex.org/I119454577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100445847","display_name":"Xue Zhao","orcid":"https://orcid.org/0000-0002-5107-3707"},"institutions":[{"id":"https://openalex.org/I119454577","display_name":"Nanjing Agricultural University","ror":"https://ror.org/05td3s095","country_code":"CN","type":"education","lineage":["https://openalex.org/I119454577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue Zhao","raw_affiliation_strings":["College of Information Management, Nanjing Agricultural University , Nanjing 210095,"],"affiliations":[{"raw_affiliation_string":"College of Information Management, Nanjing Agricultural University , Nanjing 210095,","institution_ids":["https://openalex.org/I119454577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111037932","display_name":"Zhixiao Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I119454577","display_name":"Nanjing Agricultural University","ror":"https://ror.org/05td3s095","country_code":"CN","type":"education","lineage":["https://openalex.org/I119454577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixiao Zhao","raw_affiliation_strings":["College of Information Management, Nanjing Agricultural University , Nanjing 210095,"],"affiliations":[{"raw_affiliation_string":"College of Information Management, Nanjing Agricultural University , Nanjing 210095,","institution_ids":["https://openalex.org/I119454577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109756269","display_name":"Si Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si Shen","raw_affiliation_strings":["School of Economics & Management, Nanjing University of Science and Technology , Nanjing 210094,"],"affiliations":[{"raw_affiliation_string":"School of Economics & Management, Nanjing University of Science and Technology , Nanjing 210094,","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101788189","display_name":"Dongbo Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I119454577","display_name":"Nanjing Agricultural University","ror":"https://ror.org/05td3s095","country_code":"CN","type":"education","lineage":["https://openalex.org/I119454577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbo Wang","raw_affiliation_strings":["College of Information Management, Nanjing Agricultural University , Nanjing 210095,"],"affiliations":[{"raw_affiliation_string":"College of Information Management, Nanjing Agricultural University , Nanjing 210095,","institution_ids":["https://openalex.org/I119454577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101537504"],"corresponding_institution_ids":["https://openalex.org/I119454577"],"apc_list":{"value":2522,"currency":"GBP","value_usd":3093},"apc_paid":null,"fwci":2.4362,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88169935,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"40","issue":"2","first_page":"709","last_page":"722"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9926000237464905,"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":0.9926000237464905,"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":0.9896000027656555,"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/T10028","display_name":"Topic Modeling","score":0.954200029373169,"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/image","display_name":"Image (mathematics)","score":0.5977466106414795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5435215830802917},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5431197881698608},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5192072987556458},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4975910484790802},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.17779970169067383}],"concepts":[{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5977466106414795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5435215830802917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5431197881698608},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5192072987556458},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4975910484790802},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.17779970169067383}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1093/llc/fqaf026","is_oa":false,"landing_page_url":"https://doi.org/10.1093/llc/fqaf026","pdf_url":null,"source":{"id":"https://openalex.org/S2734814886","display_name":"Digital Scholarship in the Humanities","issn_l":"2055-7671","issn":["2055-7671","2055-768X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital Scholarship in the Humanities","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335869","display_name":"National Social Science Fund of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W4220941542","https://openalex.org/W4229368176","https://openalex.org/W4318147449","https://openalex.org/W4324302630","https://openalex.org/W4389131500","https://openalex.org/W4391094120","https://openalex.org/W4391136507","https://openalex.org/W4391429251","https://openalex.org/W4391494850","https://openalex.org/W4392773006","https://openalex.org/W4401434720"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Abstract":[0],"Photocopies":[1],"of":[2,9,17,30,39,51,117],"ancient":[3,52,65,93,118,152],"works,":[4],"as":[5,137],"valuable":[6],"cultural":[7],"heritage":[8],"China,":[10],"can":[11],"be":[12],"digitized":[13],"through":[14],"the":[15,35,49,77,101,110,128],"integration":[16],"multimodal":[18,158],"large":[19],"language":[20],"models":[21,133],"(MLLMs).":[22],"This":[23,145],"approach":[24],"allows":[25],"for":[26,81,97],"more":[27],"vivid":[28],"representations":[29],"these":[31],"historical":[32],"documents,":[33],"fostering":[34],"preservation":[36],"and":[37,72,91,108,120,142,154],"advancement":[38],"traditional":[40],"culture.":[41],"We":[42],"propose":[43],"a":[44],"MLLM":[45],"specifically":[46],"dedicated":[47],"to":[48,62,75],"digitization":[50],"works":[53,66,119],"photocopies.":[54],"Specifically,":[55],"we":[56,85,105],"first":[57],"use":[58],"web":[59],"crawling":[60],"technology":[61],"efficiently":[63],"gather":[64],"data,":[67],"followed":[68],"by":[69],"data":[70,78],"cleaning":[71],"format":[73],"conversion":[74],"ensure":[76],"were":[79],"suitable":[80],"model":[82,130,146],"training.":[83],"Next,":[84],"construct":[86],"an":[87,92],"unlabeled":[88],"pre-training":[89],"dataset":[90,96],"text":[94],"dialogue":[95],"fine-tuning":[98],"based":[99],"on":[100],"collected":[102],"data.":[103],"Finally,":[104],"further":[106],"pre-train":[107],"fine-tune":[109],"MiniCPM-v-2.6-chat":[111],"baseline":[112],"model,":[113],"enhancing":[114],"its":[115,121],"understanding":[116],"conversational":[122],"ability.":[123],"Experimental":[124],"results":[125],"indicate":[126],"that":[127],"Xunzi-MiniCPM-v-2.6-chat":[129],"surpasses":[131],"existing":[132],"in":[134,150],"metrics":[135],"such":[136],"BLEU,":[138],"ROUGE,":[139],"accuracy,":[140],"recall,":[141],"F1":[143],"score.":[144],"demonstrates":[147],"strong":[148],"performance":[149],"recognizing":[151],"texts":[153],"images,":[155],"effectively":[156],"processing":[157],"information.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
