{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T17:10:18Z","timestamp":1763831418138,"version":"3.41.0"},"reference-count":30,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2025,4,13]],"date-time":"2025-04-13T00:00:00Z","timestamp":1744502400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/501100012456","name":"National Social Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research on the Construction and Application of a Cross-Language Knowledge Base for Ancient Chinese Books","award":["21&ZD331"],"award-info":[{"award-number":["21&ZD331"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Photocopies of ancient works, as valuable cultural heritage of China, can be digitized through the integration of multimodal large language models (MLLMs). This approach allows for more vivid representations of these historical documents, fostering the preservation and advancement of traditional culture. We propose a MLLM specifically dedicated to the digitization of ancient works photocopies. Specifically, we first use web crawling technology to efficiently gather ancient works data, followed by data cleaning and format conversion to ensure the data were suitable for model training. Next, we construct an unlabeled pre-training dataset and an ancient text dialogue dataset for fine-tuning based on the collected data. Finally, we further pre-train and fine-tune\u00a0the MiniCPM-v-2.6-chat baseline model, enhancing its understanding of ancient works and its conversational ability. Experimental results indicate that the Xunzi-MiniCPM-v-2.6-chat model surpasses existing models in metrics such as BLEU, ROUGE, accuracy, recall, and F1 score. This model demonstrates strong performance in recognizing ancient texts and images, effectively processing multimodal information.<\/jats:p>","DOI":"10.1093\/llc\/fqaf026","type":"journal-article","created":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T11:29:47Z","timestamp":1744284587000},"page":"709-722","source":"Crossref","is-referenced-by-count":2,"title":["XunZi-MLLM: a multimodal large language model for ancient text and image recognition"],"prefix":"10.1093","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2684-8830","authenticated-orcid":false,"given":"Dongmei","family":"Zhu","sequence":"first","affiliation":[{"name":"College of Information Management, Nanjing Agricultural University , Nanjing 210095,","place":["China"]}]},{"given":"Chang","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Information Management, Nanjing Agricultural University , Nanjing 210095,","place":["China"]}]},{"given":"Xue","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Information Management, Nanjing Agricultural University , Nanjing 210095,","place":["China"]}]},{"given":"Zhixiao","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Information Management, Nanjing Agricultural University , Nanjing 210095,","place":["China"]}]},{"given":"Si","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Economics & Management, Nanjing University of Science and Technology , Nanjing 210094,","place":["China"]}]},{"given":"Dongbo","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Information Management, Nanjing Agricultural University , Nanjing 210095,","place":["China"]}]}],"member":"286","published-online":{"date-parts":[[2025,4,13]]},"reference":[{"key":"2025053003521675600_fqaf026-B1","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1038\/s41586-022-04448-z","article-title":"Restoring and Attributing Ancient Texts using Deep Neural Networks","author":"Assael","year":"2022","journal-title":"Nature"},{"year":"2024","author":"Cao","key":"2025053003521675600_fqaf026-B2"},{"key":"2025053003521675600_fqaf026-B3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3641289","article-title":"\u2018A Survey on Evaluation of Large Language Models\u2019","volume":"15","author":"Chang","year":"2024","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"key":"2025053003521675600_fqaf026-B4","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1108\/EL-01-2022-0007","article-title":"\u2018Development and Application of a Digital Humanities Research Platform for Biographies of Malaysian Personalities\u2019","volume":"40","author":"Chen","year":"2022","journal-title":"The Electronic Library"},{"key":"2025053003521675600_fqaf026-B5","doi-asserted-by":"publisher","DOI":"10.1108\/DTA-01-2024-0009","article-title":"\u2018A Knowledge Graph Analysis Tool of People and Organizations to Facilitate Digital Humanities Research\u2019,","author":"Chen","year":"2024","journal-title":"Data Technologies and Applications"},{"year":"2022","author":"Cheng","key":"2025053003521675600_fqaf026-B6"},{"first-page":"4171","year":"2018","author":"Devlin","key":"2025053003521675600_fqaf026-B7"},{"year":"2020","author":"Feng","key":"2025053003521675600_fqaf026-B8"},{"key":"2025053003521675600_fqaf026-B9","first-page":"138","article-title":"\u2018Automatic Text Classification of Depart of Siku Quanshu From the Perspective of Digital Humanities Based on SikuBERT and Siku-RoBERTa Pre-Trained Models\u2019","author":"Hu","year":"2022","journal-title":"Library Tribune"},{"key":"2025053003521675600_fqaf026-B10","first-page":"17","article-title":"\u2018Advancing Ancient Text Work in the New Era: Accelerating Innovative Intelligent Development\u2019,","author":"Huang","year":"2022","journal-title":"Journal of Agricultural Library and Information Science"},{"key":"2025053003521675600_fqaf026-B11","first-page":"4","article-title":"\u2018Centennial Retrospective on the Photocopying of Ancient Texts\u2019,","author":"Jai","year":"2015","journal-title":"Work Review"},{"year":"2021","author":"Jia","key":"2025053003521675600_fqaf026-B12"},{"key":"2025053003521675600_fqaf026-B13","doi-asserted-by":"publisher","first-page":"20230254","DOI":"10.1098\/rsta.2023.0254","article-title":"\u2018Gpt-4 Passes the Bar Exam\u2019,","volume":"382","author":"Katz","year":"2024","journal-title":"Philosophical Transactions of the Royal Society A"},{"key":"2025053003521675600_fqaf026-B14","doi-asserted-by":"publisher","first-page":"638","DOI":"10.3390\/info14120638","article-title":"\u2018adaptmllm: Fine-Tuning Multilingual Language Models on Low-Resource Languages with Integrated llm Playgrounds\u2019,","volume":"14","author":"Lankford","year":"2023","journal-title":"Information"},{"key":"2025053003521675600_fqaf026-B15","first-page":"23","article-title":"A practical Exploration of AIGC-Powered Digital Humanities Research: A SikuGPT Driven Research Of Ancient Poetry Generation","author":"Liu","year":"2023","journal-title":"Information studies: Theory & Application"},{"year":"2024","author":"Luo","key":"2025053003521675600_fqaf026-B16"},{"year":"2024","author":"Qiu","key":"2025053003521675600_fqaf026-B17"},{"year":"2022","author":"Qin","key":"2025053003521675600_fqaf026-B18"},{"year":"2021","author":"Radford","key":"2025053003521675600_fqaf026-B19"},{"key":"2025053003521675600_fqaf026-B20","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1162\/tacl_a_00633","article-title":"\u2018mGPT: Few-Shot Learners Go Multilingual\u2019,","author":"Shliazhko","year":"2024","journal-title":"Transactions of the Association for Computational Linguistics"},{"year":"2023","author":"Siriguleng","key":"2025053003521675600_fqaf026-B21","doi-asserted-by":"publisher","DOI":"10.1109\/ITAIC58329.2023.10408974"},{"key":"2025053003521675600_fqaf026-B22","doi-asserted-by":"publisher","first-page":"1267","DOI":"10.1093\/llc\/fqad008","article-title":"\u2018A Multimodal Turn in Digital Humanities. Using Contrastive Machine Learning Models to Explore, Enrich, and Analyze Digital Visual Historical Collections\u2019,","volume":"38","author":"Smits","year":"2023","journal-title":"Digital Scholarship in the Humanities"},{"year":"2011","author":"Stanco","key":"2025053003521675600_fqaf026-B23"},{"year":"2023","author":"Wang","key":"2025053003521675600_fqaf026-B24"},{"key":"2025053003521675600_fqaf026-B25","first-page":"65","article-title":"\u2018Research on Automatic Recognition of Basic Entity Component of Historic Events for Xian Qin Classics\u2019,","author":"Wang","year":"2018","journal-title":"Journal of the National Library of China"},{"first-page":"121475","year":"2024","author":"Wang","key":"2025053003521675600_fqaf026-B26"},{"year":"2023","author":"Wu","key":"2025053003521675600_fqaf026-B27","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386743"},{"year":"2021","author":"Yao","key":"2025053003521675600_fqaf026-B28"},{"year":"2024","author":"Yao","key":"2025053003521675600_fqaf026-B29"},{"year":"2022","author":"Zhang","key":"2025053003521675600_fqaf026-B30","doi-asserted-by":"publisher","DOI":"10.1109\/IMCEC55388.2022.10019874"}],"container-title":["Digital Scholarship in the Humanities"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/dsh\/article-pdf\/40\/2\/709\/62923113\/fqaf026.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/dsh\/article-pdf\/40\/2\/709\/62923113\/fqaf026.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T07:52:26Z","timestamp":1748591546000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/dsh\/article\/40\/2\/709\/8112937"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,13]]},"references-count":30,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,4,13]]},"published-print":{"date-parts":[[2025,6,1]]}},"URL":"https:\/\/doi.org\/10.1093\/llc\/fqaf026","relation":{},"ISSN":["2055-7671","2055-768X"],"issn-type":[{"type":"print","value":"2055-7671"},{"type":"electronic","value":"2055-768X"}],"subject":[],"published-other":{"date-parts":[[2025,6]]},"published":{"date-parts":[[2025,4,13]]}}}