Work

Optimizing document reranking in a retrieval-augmented generation pipeline for Portuguese legal research

Year: 2025

Type: dissertation

Abstract: This study explores RAG systems tailored to the Portuguese legal domain, highlighting challenges in underrepresented languages. Fixed-size chunking strategies, particularly TokenTextSplitter, 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. Although reranking techniques have been shown to improve retrieval in previous research this may only be true for large and diverse datasets.

Source: Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)

Author: Wollny, Carolyn Svea

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Fundação para a Ciência e a Tecnologia

Awards: G1516346500, G3257768443, G3821169523, Nova School of Business and Economics, Nova School of Business and Economics, G946021960

OpenAlex ID: W7078547505

Cites: 72

Cited by:

Related to: 10