Artificial Intelligence Applied to Brazilian Law: State of the Art, Applications, and Challenges
DOI:
https://doi.org/10.5753/compbr.2026.56.8609Keywords:
Artificial Intelligence, Law, Natural Language Processing, Information Retrieval, Legal AnalyticsAbstract
Brazil has one of the largest judicial systems in the world, with over 75 million cases in progress and approximately 27 million new cases per year. This scenario drives the development of Artificial Intelligence (AI) solutions to support lawyers, judges, and court personnel. This paper presents an overview of the main AI applications in the Brazilian legal context, organized around three axes: information retrieval and document organization, workflow classification and automation, and predictive systems and intelligent legal assistants. Technical and ethical challenges are discussed, including domain specialization, annotated data scarcity, algorithmic bias, and model interpretability, along with the regulatory framework established by CNJ Resolution No. 455/2022. The paper concludes by identifying trends for the consolidation of generative AI in the Brazilian legal ecosystem, highlighting the importance of partnerships between academia, industry, and the Judiciary.
Downloads
References
NOVAES, L. et al. Modelagem de tópicos para a tarefa de recuperação de casos legais. In: Simpósio Brasileiro de Bancos de Dados, XXXVIII, Porto Alegre. p. 128–140, 2023.
MENTZINGEN, H. et al. Textual similarity for legal precedents discovery: assessing the performance of machine learning techniques in an administrative court. International Journal of Information Management Data Insights, v. 4, p. 100247, 2024.
RIBEIRO, L. et al. JurisTCU: a Brazilian Portuguese information retrieval dataset with query relevance judgments. arXiv preprint, arXiv:2503.08379, 2025.
VIANNA, D. et al. A topic discovery approach for unsupervised organization of legal document collections. Artificial Intelligence and Law, v. 32, n. 4, p. 1045–1074, 2024.
FELTRIN, G. et al. Um estudo sobre métricas de avaliação para sumarização de acórdãos. In: Simpósio Brasileiro de Bancos de Dados, XXXVIII. p. 295–305, 2023.
LINS, A. A. et al. CLSJUR.BR a model for abstractive summarization of legal documents in Portuguese language based on contrastive learning. In: Conf. of Computational Processing of Portuguese. p. 429–440. 2024.
INAZAWA, P. et al. Projeto Victor. Computação Brasil, n. 39, p. 19–24, 2019.
DOMINGUES, M. A. et al. A large-scale benchmark for session-based recommendations on the legal domain. Artificial Intelligence and Law, v. 33, p. 43–78, 2025.
MOREIRA, J. et al. A study on unsupervised question and answer generation for legal information retrieval and precedents understanding. In: International ACM SIGIR Conference, p. 2865–2869. 2024.
MARINHO, L. B. et al. Na prática, qual IA entende o direito? Um estudo experimental com IAs generalistas e uma IA jurídica. arXiv preprint, arXiv:2510.18108, 2025.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
