Evaluating the Simplification of Brazilian Legal Rulings in LLMs Using Readability Scores as a Target

Antonio Flavio Paula, Celso Camilo-Junior


Abstract
Legal documents are often characterized by complex language, including jargon and technical terms, making them challenging for Natural Language Processing (NLP) applications. We apply the readability-controlled text modification task with an emphasis on legal texts simplification. Additionally, our work explores an evaluation based on the comparison of word complexity in the documents using Zipf scale, demonstrating the models’ ability to simplify text according to the target readability scores, while also identifying a limit to this capability. Our results with Llama-3 and Sabiá-2 show that while the complexity score decreases with higher readability targets, there is a trade-off with reduced semantic similarity.
Anthology ID:
2024.tsar-1.12
Volume:
Proceedings of the Third Workshop on Text Simplification, Accessibility and Readability (TSAR 2024)
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Matthew Shardlow, Horacio Saggion, Fernando Alva-Manchego, Marcos Zampieri, Kai North, Sanja Štajner, Regina Stodden
Venue:
TSAR
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
117–125
Language:
URL:
https://aclanthology.org/2024.tsar-1.12
DOI:
Bibkey:
Cite (ACL):
Antonio Flavio Paula and Celso Camilo-Junior. 2024. Evaluating the Simplification of Brazilian Legal Rulings in LLMs Using Readability Scores as a Target. In Proceedings of the Third Workshop on Text Simplification, Accessibility and Readability (TSAR 2024), pages 117–125, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Evaluating the Simplification of Brazilian Legal Rulings in LLMs Using Readability Scores as a Target (Paula & Camilo-Junior, TSAR 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.tsar-1.12.pdf