{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T18:07:35Z","timestamp":1789063655612,"version":"build-2803163510"},"reference-count":46,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T00:00:00Z","timestamp":1788998400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>\n                    Legal judgment prediction (LJP) aims to predict judgment results based on the factual descriptions of criminal cases and is gradually becoming a popular research topic in the legal field. Case factual descriptions contain a large amount of keyword information, and there are complex dependencies among the subtasks. For example, law article prediction can guide charge prediction and term of penalty prediction. However, most of the previous methods often failed to take advantage of the effective keywords that are commonly present in case descriptions, or failed to consider the interrelationships between sub-tasks. To address the shortcomings, we propose a multi-task legal judgment prediction framework based on Dynamic Task Graph and Keyword-aware Contrastive Learning, termed DTG-KCL. Specifically, we design a sample-level method of dynamic task relationship graph convolution to encode task relationships from the perspective of each input case description. Subsequently, we enhance the ability to distinguish confusing charges by developing a more profound and novel keyword fusion mechanism based on soft keyword representation and an approach of keyword-aware contrastive learning. Our model effectively improved the performance of the sub-tasks. Experimental results on two real legal datasets demonstrated that our model had a significant advantage over the five methods in terms of prediction performance. Code can be obtained from:\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/YiLisiForever\/DTG-KCL\" xlink:type=\"simple\">https:\/\/github.com\/YiLisiForever\/DTG-KCL<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1371\/journal.pone.0357463","type":"journal-article","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T17:26:14Z","timestamp":1789061174000},"page":"e0357463","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Legal judgment prediction via dynamic task graph and keyword-aware contrastive learning"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3789-3140","authenticated-orcid":true,"given":"Jiawei","family":"Li","sequence":"first","affiliation":[{"name":"Henan University, School of Software","place":["Kaifeng, China"],"department":["Department of Network Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengjia","family":"Zhang","sequence":"additional","affiliation":[{"name":"Henan University, International School of Technology","place":["Kaifeng, China"],"department":["Department of Computer Science and Technology"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"pone.0357463.ref001","doi-asserted-by":"crossref","unstructured":"Kim Y, editor. Convolutional neural networks for sentence classification. Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP). 2014.","DOI":"10.3115\/v1\/D14-1181"},{"key":"pone.0357463.ref002","doi-asserted-by":"crossref","unstructured":"Chen H, Cai D, Dai W, Dai Z, Ding Y, editors. Charge-based prison term prediction with deep gating network. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.","DOI":"10.18653\/v1\/D19-1667"},{"key":"pone.0357463.ref003","doi-asserted-by":"crossref","unstructured":"Zhong H, Guo Z, Tu C, Xiao C, Liu Z, Sun M, editors. Legal judgment prediction via topological learning. Proceedings of the 2018 conference on empirical methods in natural language processing. 2018.","DOI":"10.18653\/v1\/D18-1390"},{"key":"pone.0357463.ref004","doi-asserted-by":"crossref","unstructured":"Yang W, Jia W, Zhou X, Luo Y. Legal judgment prediction via multi-perspective bi-feedback network. arXiv preprint arXiv:190503969. 2019.","DOI":"10.24963\/ijcai.2019\/567"},{"key":"pone.0357463.ref005","doi-asserted-by":"crossref","unstructured":"Xu N, Wang P, Chen L, Pan L, Wang X, Zhao J, editors. Distinguish confusing law articles for legal judgment prediction. Proceedings of the 58th annual meeting of the association for computational linguistics. 2020.","DOI":"10.18653\/v1\/2020.acl-main.280"},{"key":"pone.0357463.ref006","unstructured":"Joachims T. A probabilistic analysis of the Rocchio algorithm with TFIDF for text categorization. 1996."},{"key":"pone.0357463.ref007","doi-asserted-by":"crossref","first-page":"107960","DOI":"10.1016\/j.knosys.2021.107960","article-title":"MVE-FLK: A multi-task legal judgment prediction via multi-view encoder fusing legal keywords","volume":"239","author":"S Yang","year":"2022","journal-title":"Knowl-Based Syst"},{"issue":"4","key":"pone.0357463.ref008","doi-asserted-by":"crossref","first-page":"891","DOI":"10.2307\/1955796","article-title":"Predicting Supreme Court cases probabilistically: The search and seizure cases, 1962-1981","volume":"78","author":"JA Segal","year":"1984","journal-title":"Am Polit Sci Rev"},{"issue":"4","key":"pone.0357463.ref009","doi-asserted-by":"crossref","first-page":"847","DOI":"10.1017\/S0003055412000469","article-title":"The Supreme Court\u2019s Many Median Justices","volume":"106","author":"BE LAUDERDALE","year":"2012","journal-title":"Am Polit Sci Rev"},{"issue":"1","key":"pone.0357463.ref010","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1016\/j.ipm.2014.07.003","article-title":"Predicting associated statutes for legal problems","volume":"51","author":"Y-H Liu","year":"2015","journal-title":"Inform Process Manage"},{"key":"pone.0357463.ref011","doi-asserted-by":"crossref","unstructured":"Liu Y, Wu Y, Zhang Y, Sun C, Lu W, Wu F, et al., editors. Ml-ljp: Multi-law aware legal judgment prediction. Proceedings of the 46th international ACM SIGIR conference on research and development in information retrieval. 2023.","DOI":"10.1145\/3539618.3591731"},{"key":"pone.0357463.ref012","unstructured":"Hu Z, Li X, Tu C, Liu Z, Sun M, editors. Few-shot charge prediction with discriminative legal attributes. Proceedings of the 27th international conference on computational linguistics. 2018."},{"key":"pone.0357463.ref013","doi-asserted-by":"crossref","unstructured":"Xu Z, Li X, Li Y, Wang Z, Fanxu Y, Lai X, editors. Multi-task legal judgement prediction combining a subtask of the seriousness of charges. China National Conference on Chinese Computational Linguistics. Springer; 2020.","DOI":"10.1007\/978-3-030-63031-7_30"},{"issue":"3","key":"pone.0357463.ref014","first-page":"1217","article-title":"Prison Term Prediction on Criminal Case Description with Deep Learning","volume":"62","author":"S Li","year":"2020","journal-title":"Comput Mater Contin"},{"key":"pone.0357463.ref015","doi-asserted-by":"crossref","unstructured":"Guo Y, Li Y, Ge F, Yu H, Wang S, Miao Z, editors. Legal judgment prediction via fine-grained element graphs and external knowledge. 2024 International Joint Conference on Neural Networks (IJCNN). IEEE; 2024.","DOI":"10.1109\/IJCNN60899.2024.10649936"},{"issue":"12","key":"pone.0357463.ref016","doi-asserted-by":"crossref","first-page":"5586","DOI":"10.1109\/TKDE.2021.3070203","article-title":"A Survey on Multi-Task Learning","volume":"34","author":"Y Zhang","year":"2022","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"6","key":"pone.0357463.ref017","doi-asserted-by":"crossref","first-page":"4390","DOI":"10.1109\/TII.2020.3030709","article-title":"Predicting Grain Losses and Waste Rate Along the Entire Chain: A Multitask Multigated Recurrent Unit Autoencoder Based Method","volume":"17","author":"J Cao","year":"2021","journal-title":"IEEE Trans Ind Inf"},{"key":"pone.0357463.ref018","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1016\/j.neucom.2020.05.018","article-title":"Gated hierarchical multi-task learning network for judicial decision prediction","volume":"411","author":"F Yao","year":"2020","journal-title":"Neurocomputing"},{"key":"pone.0357463.ref019","doi-asserted-by":"crossref","unstructured":"Qin W, Cao Z, Yu W, Si Z, Chen S, Xu J, editors. Explicitly integrating judgment prediction with legal document retrieval: a law-guided generative approach. Proceedings of the 47th international ACM SIGIR conference on research and development in information retrieval. 2024.","DOI":"10.1145\/3626772.3657717"},{"key":"pone.0357463.ref020","unstructured":"Chen T, Kornblith S, Norouzi M, Hinton G, editors. A simple framework for contrastive learning of visual representations. International conference on machine learning. PmLR; 2020."},{"key":"pone.0357463.ref021","doi-asserted-by":"crossref","unstructured":"He K, Fan H, Wu Y, Xie S, Girshick R, editors. Momentum contrast for unsupervised visual representation learning. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2020.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"pone.0357463.ref022","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"P Khosla","year":"2020","journal-title":"Adv Neural Inform Process Syst"},{"key":"pone.0357463.ref023","unstructured":"Oord Avd, Li Y, Vinyals O. Representation learning with contrastive predictive coding. arXiv preprint arXiv:180703748. 2018."},{"key":"pone.0357463.ref024","doi-asserted-by":"crossref","unstructured":"Gao T, Yao X, Chen D, editors. Simcse: Simple contrastive learning of sentence embeddings. Proceedings of the 2021 conference on empirical methods in natural language processing. 2021.","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"pone.0357463.ref025","unstructured":"Wu Z, Wang S, Gu J, Khabsa M, Sun F, Ma H. Clear: Contrastive learning for sentence representation. arXiv preprint arXiv:201215466. 2020."},{"key":"pone.0357463.ref026","first-page":"23102","article-title":"Coco-lm: Correcting and contrasting text sequences for language model pretraining","volume":"34","author":"Y Meng","year":"2021","journal-title":"Adv Neural Inform Process Syst"},{"issue":"4","key":"pone.0357463.ref027","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3580489","article-title":"Contrastive Learning for Legal Judgment Prediction","volume":"41","author":"H Zhang","year":"2023","journal-title":"ACM Trans Inf Syst"},{"key":"pone.0357463.ref028","article-title":"Information extraction from employment tribunal judgments using a large language model","author":"J Ribeiro de Faria","year":"2025","journal-title":"Artif Intell Law"},{"key":"pone.0357463.ref029","doi-asserted-by":"crossref","first-page":"2733","DOI":"10.1109\/JSAC.2025.3644295","article-title":"Large-Small Model Collaboration in Mobile Edge Networks With Heterogeneous Computational Resources","volume":"44","author":"L Cheng","year":"2026","journal-title":"IEEE J Sel Areas Commun"},{"key":"pone.0357463.ref030","first-page":"143569","article-title":"Gam-agent: Game-theoretic and uncertainty-aware collaboration for complex visual reasoning","volume":"38","author":"Y Fan","year":"2026","journal-title":"Adv Neural Inform Process Syst"},{"key":"pone.0357463.ref031","doi-asserted-by":"crossref","first-page":"125723","DOI":"10.1016\/j.eswa.2024.125723","article-title":"Mitigating reasoning hallucination through Multi-agent Collaborative Filtering","volume":"263","author":"J Shi","year":"2025","journal-title":"Exp Syst Appl"},{"issue":"8","key":"pone.0357463.ref032","doi-asserted-by":"crossref","first-page":"641","DOI":"10.3390\/systems13080641","article-title":"AgentsBench: A Multi-Agent LLM Simulation Framework for Legal Judgment Prediction","volume":"13","author":"C Jiang","year":"2025","journal-title":"Systems"},{"key":"pone.0357463.ref033","unstructured":"Sun M, Chen X, Zhang K, Guo Z, Liu Z. Thulac: An efficient lexical analyzer for chinese. Retrieved Jan. 2016;10:2022."},{"issue":"11","key":"pone.0357463.ref034","doi-asserted-by":"crossref","first-page":"2673","DOI":"10.1109\/78.650093","article-title":"Bidirectional recurrent neural networks","volume":"45","author":"M Schuster","year":"1997","journal-title":"IEEE Trans Signal Process"},{"issue":"8","key":"pone.0357463.ref035","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"S Hochreiter","year":"1997","journal-title":"Neural Comput"},{"key":"pone.0357463.ref036","unstructured":"Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:14090473. 2014."},{"key":"pone.0357463.ref037","doi-asserted-by":"crossref","first-page":"87571","DOI":"10.1109\/ACCESS.2023.3305259","article-title":"Knowledge-Enriched Multi-Cross Attention Network for Legal Judgment Prediction","volume":"11","author":"C He","year":"2023","journal-title":"IEEE Access"},{"key":"pone.0357463.ref038","unstructured":"Kipf TN, Welling M. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:160902907. 2016."},{"key":"pone.0357463.ref039","article-title":"Inductive representation learning on large graphs","volume":"30","author":"W Hamilton","year":"2017","journal-title":"Adv Neural Inform Process Syst"},{"key":"pone.0357463.ref040","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J, editors. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.","DOI":"10.1109\/CVPR.2016.90"},{"key":"pone.0357463.ref041","unstructured":"Xiao C, Zhong H, Guo Z, Tu C, Liu Z, Sun M, et al. Cail2018: A large-scale legal dataset for judgment prediction. arXiv preprint arXiv:180702478. 2018."},{"key":"pone.0357463.ref042","unstructured":"Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv:14126980. 2014."},{"key":"pone.0357463.ref043","doi-asserted-by":"crossref","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K, editors. Bert: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). 2019.","DOI":"10.18653\/v1\/N19-1423"},{"issue":"11","key":"pone.0357463.ref044","article-title":"Visualizing data using t-SNE","volume":"9","author":"L Van der Maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"pone.0357463.ref045","doi-asserted-by":"crossref","first-page":"103426","DOI":"10.1016\/j.inffus.2025.103426","article-title":"Legal knowledge infusion for large language models: A survey","volume":"125","author":"Q Liu","year":"2026","journal-title":"Inf Fusio"},{"key":"pone.0357463.ref046","doi-asserted-by":"crossref","first-page":"112033","DOI":"10.1016\/j.knosys.2024.112033","article-title":"HD-LJP: A Hierarchical Dependency-based Legal Judgment Prediction Framework for Multi-task Learning","volume":"299","author":"Y Zhang","year":"2024","journal-title":"Knowl-Based Syst"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0357463","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T17:26:26Z","timestamp":1789061186000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0357463"}},"subtitle":[],"editor":[{"given":"Ming","family":"Zhang","sequence":"first","affiliation":[{"name":"Hubei University","place":["CHINA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,10]]},"references-count":46,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,10]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0357463","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,10]]}}}