paper7Updated Nov 21, 2026 · Português
← All papers

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