{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T16:17:13Z","timestamp":1791994633564,"version":"4.4.0"},"reference-count":27,"publisher":"Public Library of Science (PLoS)","issue":"1","license":[{"start":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T00:00:00Z","timestamp":1768521600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62062012"],"award-info":[{"award-number":["62062012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>\n                    Legal Judgment Prediction (LJP) is a core task in Legal AI systems, which aims to predict law articles, charges, and term-of-penalty from case facts. While existing deep-learning-based LJP approaches for civil law systems have achieved certain progress, they still suffer from two key limitations: (1) insufficient deep understanding and effective utilization of external judicial knowledge; and (2) the lack of effective strategies to filter out erroneous dependency information in multi-task LJP frameworks. To address these challenges, we propose a legal judgment prediction model based on knowledge fusion and dependency masking. Specifically, we first integrate a CNN-based local semantic refinement component into the existing BERT-based legal knowledge extraction method, thereby enabling the model to further extract the core knowledge embedded in judicial documents. Then, we introduce differential attention to reduce noise in conventional attention fusion methods and help the model locate key information in case facts more accurately. Furthermore, we propose a multi-task dependency information masking mechanism to accurately identify and filter erroneous dependency information for multi-task LJP methods. Experiments conducted on real-world datasets demonstrate the superiority of our proposed model. This code is available online at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/PaperCode-GNU\/KFTM\" xlink:type=\"simple\">https:\/\/github.com\/PaperCode-GNU\/KFTM<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1371\/journal.pone.0340717","type":"journal-article","created":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T18:48:52Z","timestamp":1768589332000},"page":"e0340717","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["A legal judgment prediction model based on knowledge fusion and dependency masking"],"prefix":"10.1371","volume":"21","author":[{"given":"Yishan","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyi","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4689-5191","authenticated-orcid":true,"given":"Zhiyun","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengfei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinhua","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,1,16]]},"reference":[{"issue":"10","key":"pone.0340717.ref001","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0312623","article-title":"Empowering legal justice with AI: a reinforcement learning SAC-VAE framework for advanced legal text summarization","volume":"19","author":"X Wang","year":"2024","journal-title":"PLoS One"},{"key":"pone.0340717.ref002","doi-asserted-by":"crossref","first-page":"102050","DOI":"10.1109\/ACCESS.2023.3317083","article-title":"A survey on legal judgment prediction: datasets, metrics, models and challenges","volume":"11","author":"J Cui","year":"2023","journal-title":"IEEE Access"},{"key":"pone.0340717.ref003","first-page":"2658","article-title":"Augmenting legal judgment prediction with contrastive case relations","author":"D Liu","year":"2022","journal-title":"COLING 2022"},{"key":"pone.0340717.ref004","first-page":"6362","article-title":"Charge-based prison term prediction with deep gating network","author":"H Chen","year":"2019","journal-title":"EMNLP"},{"key":"pone.0340717.ref005","first-page":"1802","article-title":"Learning to predict charges for legal judgment via self-attentive capsule network","author":"Y Le","year":"2020","journal-title":"ECAI"},{"key":"pone.0340717.ref006","first-page":"2727","article-title":"Learning to predict charges for criminal cases with legal basis","author":"B Luo","year":"2017","journal-title":"EMNLP"},{"key":"pone.0340717.ref007","first-page":"240","article-title":"Learning to predict charges for judgment with legal graph","author":"S Chen","year":"2019","journal-title":"ANN"},{"key":"pone.0340717.ref008","doi-asserted-by":"crossref","first-page":"151144","DOI":"10.1109\/ACCESS.2019.2945771","article-title":"MANN: a multichannel attentive neural network for legal judgment prediction","volume":"7","author":"S Li","year":"2019","journal-title":"IEEE Access"},{"key":"pone.0340717.ref009","first-page":"3540","article-title":"Legal judgment prediction via topological learning","author":"H Zhong","year":"2018","journal-title":"EMNLP"},{"key":"pone.0340717.ref010","first-page":"4085","article-title":"Legal judgment prediction via multi perspective bi-feedback network","author":"W Yang","year":"2019","journal-title":"IJCAI"},{"key":"pone.0340717.ref011","first-page":"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":"KBS"},{"key":"pone.0340717.ref012","first-page":"3132","article-title":"Fewshot and zero-shot multi-label learning for structured label spaces","author":"A Rios","year":"2018","journal-title":"EMNLP"},{"key":"pone.0340717.ref013","first-page":"6314","article-title":"Large-scale multi-label text classification on EU legislation","author":"I Chalkidis","year":"2019","journal-title":"ACL"},{"key":"pone.0340717.ref014","first-page":"648","article-title":"Legal judgment prediction via event extraction with constraints","author":"Y Feng","year":"2022","journal-title":"ACL"},{"key":"pone.0340717.ref015","first-page":"3086","article-title":"Distinguish confusing law articles for legal judgment prediction","author":"N Xu","year":"2020","journal-title":"ACL"},{"issue":"4","key":"pone.0340717.ref016","doi-asserted-by":"crossref","first-page":"889","DOI":"10.1007\/s10506-024-09407-9","article-title":"Graph contrastive learning networks with augmentation for legal judgment prediction","volume":"33","author":"Y Dong","year":"2024","journal-title":"Artif Intell Law"},{"key":"pone.0340717.ref017","article-title":"LERT: a linguistically-motivated pre-trained language model.","author":"Y Cui","year":"2022"},{"key":"pone.0340717.ref018","first-page":"1","article-title":"Differential transformer","author":"T Ye","year":"2025","journal-title":"ICLR"},{"key":"pone.0340717.ref019","first-page":"716","article-title":"Predicting the law area and decisions of french supreme court cases","author":"OM Sulea","year":"2017","journal-title":"RANLP"},{"issue":"4","key":"pone.0340717.ref020","article-title":"A general approach for predicting the behavior of the Supreme Court of the United States","volume":"12","author":"DM Katz","year":"2017","journal-title":"PLoS One"},{"key":"pone.0340717.ref021","first-page":"3317","article-title":"Empirical study of deep learning for text classification in legal document review","author":"F Wei","year":"2018","journal-title":"Proc. IEEE Int. Conf. Big Data"},{"key":"pone.0340717.ref022","first-page":"2727","article-title":"Learning to predict charges for criminal cases with legal basis","author":"B Luo","year":"2017","journal-title":"EMNLP"},{"key":"pone.0340717.ref023","first-page":"4171","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","author":"J Devlin","year":"2019","journal-title":"NAACL"},{"key":"pone.0340717.ref024","doi-asserted-by":"crossref","article-title":"Revisiting and advancing chinese natural language understanding with accelerated heterogeneous knowledge pre-training.","author":"T Zhang","DOI":"10.18653\/v1\/2022.emnlp-industry.57"},{"key":"pone.0340717.ref025","volume-title":"Open Chinese language pre-trained model zoo","author":"H Zhong","year":"2019"},{"issue":"5","key":"pone.0340717.ref026","doi-asserted-by":"crossref","first-page":"6503","DOI":"10.1007\/s11227-021-04097-5","article-title":"Financial causal sentence recognition based on BERT-CNN text classification","volume":"78","author":"C-X Wan","year":"2021","journal-title":"J Supercomput"},{"key":"pone.0340717.ref027","doi-asserted-by":"crossref","first-page":"2604","DOI":"10.1016\/j.procs.2023.01.234","article-title":"BERT-CNN: improving BERT for requirements classification using CNN","volume":"218","author":"K Kaur","year":"2023","journal-title":"Procedia Comput Sci"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0340717","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T18:48:58Z","timestamp":1768589338000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0340717"}},"subtitle":[],"editor":[{"given":"Qingan","family":"Qiu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,1,16]]},"references-count":27,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1,16]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0340717","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,16]]}}}