{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T01:02:42Z","timestamp":1771894962572,"version":"3.50.1"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T00:00:00Z","timestamp":1740182400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T00:00:00Z","timestamp":1740182400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Rev Socionetwork Strat"],"published-print":{"date-parts":[[2025,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Fine-tuning pretrained large language models (LLMs) has become a mainstream paradigm for solving downstream natural language processing tasks. However, training a language model for legal applications requires a large corpus of legal documents to enable the language model to learn legal terminology and the particularity of legal formatting. Typical NLP approaches usually rely on manually annotated datasets for training; however, such legal field datasets are difficult to obtain. In this study, a large corpus of public, annotation-free legal documents in Chinese but without word segmentation were used to fine-tune a pretrained LLM to generate content for legal document drafts. Moreover, this was performed locally, ensuring information privacy and improving security. Finally, an evaluation method for the generated documents was developed to enable objectively assessing the quality of the drafts.<\/jats:p>","DOI":"10.1007\/s12626-025-00179-5","type":"journal-article","created":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T06:46:24Z","timestamp":1740206784000},"page":"83-110","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Assisting Drafting of Chinese Legal Documents Using Fine-Tuned Pre-trained Large Language Models"],"prefix":"10.1007","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0281-0272","authenticated-orcid":false,"given":"Chun-Hsien","family":"Lin","sequence":"first","affiliation":[]},{"given":"Pu-Jen","family":"Cheng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,2,22]]},"reference":[{"key":"179_CR1","doi-asserted-by":"crossref","unstructured":"Vuong, Y.T.-H., et al. (2022). SM-BERT-CR: a deep learning approach for case law retrieval with supporting model. Artificial Intelligence and Law.","DOI":"10.1007\/s10506-022-09319-6"},{"key":"179_CR2","doi-asserted-by":"crossref","unstructured":"Kim, m.-y., Y. Xu, and R. Goebel (2017). Applying a Convolutional Neural Network to Legal Question Answering. 282\u2013294.","DOI":"10.1007\/978-3-319-50953-2_20"},{"key":"179_CR3","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al. (2020). Language models are few-shot learners. Advances in neural information processing systems., 33, 1877\u20131901.","journal-title":"Advances in neural information processing systems."},{"key":"179_CR4","doi-asserted-by":"crossref","unstructured":"Ma, J., K. Ganchev, and D. Weiss (2018). State-of-the-art Chinese Word Segmentation with Bi-LSTMs. in Brussels, Belgium: Association for Computational Linguistics.","DOI":"10.18653\/v1\/D18-1529"},{"key":"179_CR5","unstructured":"O'Shea, K. and R. Nash (2015). An introduction to convolutional neural networks. arXiv preprint arXiv:1511.08458."},{"issue":"6088","key":"179_CR6","first-page":"533","volume":"323","author":"DE Rumelhart","year":"1986","unstructured":"Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. nature., 323(6088), 533\u2013536.","journal-title":"Learning representations by back-propagating errors. nature."},{"issue":"8","key":"179_CR7","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation., 9(8), 1735\u20131780.","journal-title":"Neural Computation."},{"key":"179_CR8","unstructured":"Vaswani, A., et al. (2017). Attention is All you Need. in."},{"key":"179_CR9","unstructured":"Devlin, J., et al. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. in."},{"key":"179_CR10","doi-asserted-by":"crossref","unstructured":"Bouraoui, Z., J. Camacho-Collados, and S. Schockaert (2020). Inducing relational knowledge from BERT. in Proceedings of the AAAI Conference on Artificial Intelligence.","DOI":"10.1609\/aaai.v34i05.6242"},{"issue":"2","key":"179_CR11","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1162\/daed_a_01905","volume":"151","author":"CD Manning","year":"2022","unstructured":"Manning, C. D. (2022). Human language understanding & reasoning. Daedalus, 151(2), 127\u2013138.","journal-title":"Daedalus"},{"key":"179_CR12","doi-asserted-by":"crossref","unstructured":"Paul, S., et al. (2023). Pre-trained Language Models for the Legal Domain: A Case Study on Indian Law, in Proceedings of the Nineteenth International Conference on Artificial Intelligence and Law. Association for Computing Machinery: Braga, Portugal. p. 187\u2013196.","DOI":"10.1145\/3594536.3595165"},{"key":"179_CR13","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.aiopen.2021.06.003","volume":"2","author":"C Xiao","year":"2021","unstructured":"Xiao, C., et al. (2021). Lawformer: A pre-trained language model for Chinese legal long documents. AI Open., 2, 79\u201384.","journal-title":"AI Open."},{"key":"179_CR14","unstructured":"Liu, Y., et al. (2019). Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692."},{"key":"179_CR15","doi-asserted-by":"crossref","unstructured":"Tagarelli, A. and A. Simeri (2021). Unsupervised law article mining based on deep pre-trained language representation models with application to the Italian civil code. Artificial Intelligence and Law.","DOI":"10.1007\/s10506-021-09301-8"},{"key":"179_CR16","doi-asserted-by":"crossref","unstructured":"Ganguly, D., et al. (2023). Legal IR and NLP: the History, Challenges, and State-of-the-Art. in European Conference on Information Retrieval. Springer.","DOI":"10.1007\/978-3-031-28241-6_34"},{"key":"179_CR17","first-page":"21","volume":"58","author":"J Savelka","year":"2017","unstructured":"Savelka, J., et al. (2017). Sentence boundary detection in adjudicatory decisions in the united states. Traitement automatique des langues., 58, 21.","journal-title":"Traitement automatique des langues."},{"key":"179_CR18","doi-asserted-by":"crossref","unstructured":"Au, T.W.T., I.J. Cox, and V. Lampos (2022). E-NER--An Annotated Named Entity Recognition Corpus of Legal Text. arXiv preprint arXiv:2212.09306.","DOI":"10.18653\/v1\/2022.nllp-1.22"},{"key":"179_CR19","doi-asserted-by":"crossref","unstructured":"Chalkidis, I., et al. (2020). LEGAL-BERT: The Muppets straight out of Law School. in Online: Association for Computational Linguistics.","DOI":"10.18653\/v1\/2020.findings-emnlp.261"},{"key":"179_CR20","doi-asserted-by":"crossref","unstructured":"Markovi\u0107, M. and S. Gostoji\u0107 (2022). Legal document assembly system for introducing law students with legal drafting. Artificial Intelligence and Law.","DOI":"10.1007\/s10506-022-09339-2"},{"key":"179_CR21","unstructured":"Zhao, W.X., et al. (2023). A survey of large language models. arXiv preprint arXiv:2303.18223."},{"key":"179_CR22","unstructured":"Drugs, U.N.O.o. and Crime (2015). International Classification of Crime for Statistical Purposes (ICCS)\u2014Version 1.0. United Nations Office on Drugs and Crime Vienna, Austria."},{"issue":"05","key":"179_CR23","doi-asserted-by":"publisher","first-page":"8236","DOI":"10.1609\/aaai.v34i05.6338","volume":"34","author":"P-H Li","year":"2020","unstructured":"Li, P.-H., Fu, T.-J., & Ma, W.-Y. (2020). Why attention? Analyze BiLSTM deficiency and its remedies in the case of NER. Proceedings of the AAAI Conference on Artificial Intelligence., 34(05), 8236\u20138244.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence."},{"issue":"3","key":"179_CR24","doi-asserted-by":"publisher","first-page":"419","DOI":"10.2307\/838275","volume":"15","author":"J Dainow","year":"1966","unstructured":"Dainow, J. (1966). The civil law and the common law: some points of comparison. The American Journal of Comparative Law., 15(3), 419\u2013435.","journal-title":"The American Journal of Comparative Law."},{"key":"179_CR25","unstructured":"Friedrich, R., M. Luzzatto, and E. Ash (2020). Entropy in Legal Language. in 2nd Workshop on Natural Legal Language Processing (NLLP, collocated with KDD 2020)(virtual)."},{"key":"179_CR26","unstructured":"Lin, C.-Y. (2004). Rouge: A package for automatic evaluation of summaries. in Text summarization branches out."},{"key":"179_CR27","unstructured":"Niwattanakul, S., et al. (2013). Using of Jaccard coefficient for keywords similarity. in Proceedings of the international multiconference of engineers and computer scientists."},{"key":"179_CR28","unstructured":"Scao, T.L., et al. (2022). Bloom: A 176b-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100."},{"key":"179_CR29","unstructured":"Zhang, P., et al. (2024). Tinyllama: An open-source small language model. arXiv preprint arXiv:2401.02385."},{"key":"179_CR30","unstructured":"Ennen, P., et al. (2023). Extending the Pre-Training of BLOOM for Improved Support of Traditional Chinese: Models, Methods and Results. arXiv preprint arXiv:2303.04715."},{"key":"179_CR31","unstructured":"Hu, E.J., et al. (2021). Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685."},{"issue":"1","key":"179_CR32","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1162\/089120103321337458","volume":"29","author":"C Tillmann","year":"2003","unstructured":"Tillmann, C., & Ney, H. (2003). Word reordering and a dynamic programming beam search algorithm for statistical machine translation. Computational linguistics., 29(1), 97\u2013133.","journal-title":"Computational linguistics."},{"key":"179_CR33","doi-asserted-by":"crossref","unstructured":"Fan, A., M. Lewis, and Y. Dauphin (2018). Hierarchical Neural Story Generation. in Melbourne, Australia: Association for Computational Linguistics.","DOI":"10.18653\/v1\/P18-1082"},{"key":"179_CR34","doi-asserted-by":"crossref","unstructured":"Gao, Y., et al. (2020). Estimating gpu memory consumption of deep learning models. in Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering.","DOI":"10.1145\/3368089.3417050"},{"issue":"12","key":"179_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3571730","volume":"55","author":"Z Ji","year":"2023","unstructured":"Ji, Z., et al. (2023). Survey of hallucination in natural language generation. ACM Computing Surveys., 55(12), 1\u201338.","journal-title":"ACM Computing Surveys."}],"container-title":["The Review of Socionetwork Strategies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12626-025-00179-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12626-025-00179-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12626-025-00179-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T08:07:51Z","timestamp":1744272471000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12626-025-00179-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,22]]},"references-count":35,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["179"],"URL":"https:\/\/doi.org\/10.1007\/s12626-025-00179-5","relation":{},"ISSN":["2523-3173","1867-3236"],"issn-type":[{"value":"2523-3173","type":"print"},{"value":"1867-3236","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,22]]},"assertion":[{"value":"3 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 January 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 February 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}