Large language models (LLMs) for legal analysis: RAG and beyond for optimizing domain adaptation in Portuguese legal domain
Year: 2024
Type: dissertation
Abstract: This study explores RAG systems tailored to the Portuguese legal domain, highlighting challenges in underrepresented languages. Fixed-size chunking strategies, particularly Token Text Splitter, were found to be most effective, while more advanced techniques like Recursive and Semantic splitting showed little benefits. Larger chunk sizes improved retrieval accuracy and answer quality, though the impact of chunk overlap remains inconclusive. Self-reflection techniques show promising results, particularly for weaker LLMs. Techniques such as adding a pre-post translation proved to be an efficient technique for mitigating language bias.
Author: Barros, Tiago Mendonça Alencar
Language: English
Subfield: Law
Field: Social Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W7204975254