Legal Nugget Extraction for Granular Retrieval over Long Jurisprudential Texts
Lucas Pereira, Erick Brito, Roberto Lotufo, Jayr Pereira
Abstract
Legal retrieval over jurisprudential collections is challenging because court decisions are long, heterogeneous documents whose relevant legal thesis may occupy only a small portion of the text. This paper asks whether legal nuggets, defined as short and self-contained legal theses extracted from source documents, can improve dense retrieval over Brazilian legal collections. We propose a pipeline that extracts nuggets from each document, indexes them with embeddings, retrieves nugget-level evidence, and aggregates the retrieved nuggets back to document-level rankings. We evaluate this approach…
Who it is from
NeuralMindautor: Roberto Lotufo (cofundador e CTO)
Other papers from the same organizations
- Structural Segmentation for Brazilian Legal Document RetrievalNeuralMind
- Domain-Adaptive Dense Retrieval for Brazilian Legal SearchNeuralMind
- 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