Domain-Adaptive Dense Retrieval for Brazilian Legal Search
Jayr Pereira, Roberto Lotufo, Luiz Bonifacio
Resumo
Brazilian legal retrieval is heterogeneous, covering case law, legislation, and question-based search. This makes training dense retrievers a trade-off between stronger domain specialization and broader robustness across retrieval types of search. In this paper, we explore this trade-off using three training setups based on Qwen3-Embedding-4B: a base model with no fine-tuning, a version trained only on legal data, and a mixed setup that combines legal data with SQuAD-pt supervised dataset. We evaluate these models on five legal datasets from the JUÁ leaderboard, along with Quati dataset as an …
De quem é
NeuralMindautor: Roberto Lotufo (cofundador e CTO)
Outros papers das mesmas organizações
- Structural Segmentation for Brazilian Legal Document RetrievalNeuralMind
- Legal Nugget Extraction for Granular Retrieval over Long Jurisprudential TextsNeuralMind
- Teaching LLMs Brazilian Healthcare: Injecting Knowledge from Official Clinical GuidelinesMaritaca AI
- JUÁ -- A Benchmark for Information Retrieval in Brazilian Legal Text CollectionsNeuralMind
- Comparing Knowledge Injection Methods for LLMs in a Low-Resource RegimeMaritaca AI
- BR-TaxQA-R: A Dataset for Question Answering with References for Brazilian Personal Income Tax Law, including case lawNeuralMind