A carregar...
Publicação
Graph-based reasoning for retrieval-augmented generation: a study in the Portuguese legal domain
| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 2.84 MB | Adobe PDF |
Orientador(es)
Resumo(s)
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. Self reflection techniques show promising results, particularly for weaker LLMs and when different
techniques are paired. However, there is an increment in computational cost to consider.
Descrição
Palavras-chave
Retrieval-Augmented Generation RAG Large Language Models LLM Artificial Intelligence AI Hallucination Question answering RAG evaluation Vector store Chunking Legal AI Graph-based reasoning Self-assessment Self-reflection Multi-Agent Systems MAS