The Application of Natural Language Processing Technology in Legal Aid and Judicial Practice

Yexuan Yang

doi:10.54097/xvsq2r56

Authors

Yexuan Yang

DOI:

https://doi.org/10.54097/xvsq2r56

Keywords:

Natural language processing, legal aid, judicial practice, text information extraction.

Abstract

Natural language processing (NLP) technology is an important constituent of artificial intelligence, focusing on the interaction between computers and human natural language, with the aim of enabling computers to understand, analyze, generate and process human languages. The fields of legal aid and judicial practice are also strongly related to texts, therefore, natural language processing technology has shown great potential in the legal field nowadays. In this study, the author reviews the development status, core technologies, application areas, and application value of natural language processing technology in the fields of legal aid and judicial practice. In addition, the study summarizes the difficulties and challenges faced by natural language processing technology in the field of legal aid and judicial practice. In particular, the current legal natural language processing technology still has technical problems, such as difficulty in processing complex and long legal texts, a lack of certain logical reasoning ability, insufficient understanding of non-professional questions, and a lack of public datasets, which leads to high model training costs, etc. In response to these problems, the study points out the need to make natural language processing models more adaptable to legal language, and proposes suggestions such as enhancing the popularity of models and open datasets.

Downloads

Download data is not yet available.

References

[1] Louis A, van Dijck G, Spanakis G. Interpretable long-form legal question answering with retrieval-augmented large language models. Proceedings of the AAAI Conference on Artificial Intelligence, 2024, 38 (20): 22266-22275.

[2] An Z W, Lai Y X, Feng Y S. Natural language understanding for legal documents. Journal of Chinese Information Processing, 2022, 36 (08): 1-11.

[3] Ariai F, Mackenzie J, Demartini G. Natural language processing for the legal domain: A survey of tasks, datasets, models, and challenges. arXiv preprint arXiv:2410.21306, 2024.

[4] Song D, Gao S, He B, et al. On the effectiveness of pre-trained language models for legal natural language processing: An empirical study. IEEE Access, 2022, 10: 75835-75858.

[5] Zhang Z F, Ma H W, Jiang X. A review of bias evaluation and mitigation for pre-trained language models. Journal of Software Guide, 2025, 1-7.

[6] Su W, Hu Y, Xie A, et al. STARD: A Chinese statute retrieval dataset derived from real-life queries by non-professionals. Findings of the Association for Computational Linguistics: EMNLP 2024, 2024: 10658-10671.

[7] Sovrano F, Palmirani M, Sapienza S, Pistone V. DiscoLQA: Zero-shot discourse-based legal question answering on European legislation. Artificial Intelligence and Law, 2024.

[8] Lam J, Chen Y, Zulkernine F, et al. Legal text analytics for reasonable notice period prediction. Journal of Computational and Cognitive Engineering, 2025.

[9] Kumar H, Jayanth P. Large language models for Indian legal text summarisation. 2024 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT), IEEE, 2024: 1-5.

[10] Çetindağ C, Yazıcıoğlu B, Koç A. Named-entity recognition in Turkish legal texts. Natural Language Engineering, 2023, 29 (3): 615-642.

[11] Trautmann D, Petrova A, Schilder F. Legal prompt engineering for multilingual legal judgement prediction. arXiv preprint arXiv:2212.02199, 2022.

[12] Quevedo E, Cerny T, Rodriguez A, et al. Legal natural language processing from 2015 to 2022: A comprehensive systematic mapping study of advances and applications. IEEE Access, 2023, 12: 145286-145317.

[13] Katz D M, Hartung D, Gerlach L, et al. Natural language processing in the legal domain. arXiv preprint arXiv:2302.12039, 2023.