SIMPLIFYING LEGAL LANGUAGE WITH ARTIFICIAL INTELLIGENCE

Authors

  • Keila Mara Lara Rosado Ministério Público Federal
  • Célia da Consolação Dias Federal University of Minas Gerais image/svg+xml

Keywords:

legal terminology, plain language movement, generative artificial intelligence, legal language, terminological work

Abstract

This study presents an excerpt from a doctoral thesis in Information Science and addresses the employment of generative artificial intelligence as an auxiliary resource in terminological work. The objective was to verify whether generative artificial intelligence resources can support researchers in rewriting legal terms and definitions using the principles of the Plain Language Movement. The qualitative, empirical, and exploratory methodology involved prior conceptual modeling and empirical testing with specific prompts to evaluate the consistency of the machines' suggestions. The results demonstrated that the technology offers positive contributions, such as suggesting more user-friendly terms and assisting in the elimination of textual ambiguities. However, the research identified significant semantic flaws, including the use of technically incorrect synonyms for the context of use within the legal domain, and the production of texts with informal or infantilized language. It is concluded that terminological work is an essentially cognitive and human activity. Although artificial intelligence is useful in a subsidiary capacity, expert mediation is indispensable to ensure that language simplification does not compromise the conceptual rigor of Law.

Author Biographies

  • Keila Mara Lara Rosado, Ministério Público Federal

    Doctor and Master in Knowledge Management and Organization from the Federal University of Minas Gerais (UFMG). Librarianship Analyst at the Federal Public Prosecutor's Office (MPF), working at the Attorney General's Office of the Republic (2023 to present). Specialist in Team Management and Project Feasibility (2013) and in Public Management (2012). Bachelor in Librarianship from the Federal University of Minas Gerais (2007) and in Graphic Design from the State University of Minas Gerais (2008).

  • Célia da Consolação Dias, Federal University of Minas Gerais

    Associate Professor in the Department of Information Organization and Processing at the School of Information Science at the Federal University of Minas Gerais (UFMG), Brazil. Postdoctoral fellow at Universidad Carlos III de Madrid, Spain. Vice President of ISKO Brazil. Holds a PhD and a Master's in Information Science from the School of Information Science at UFMG. Graduated in Library Science from the same institution. Coordinates the Knowledge Representation and Information Retrieval Research Group (RECRI/UFMG).

Downloads

Published

2026-11-13

Conference Proceedings Volume

2026: XXVI ENCONTRO NACIONAL DE PESQUISA E PÓS-GRADUAÇÃO EM CIÊNCIA DA INFORMAÇÃO

Section

GT 2 – Organização e Representação do Conhecimento

Categories