collaborators

6 papers

cs.IR2026

Legal Nugget Extraction for Granular Retrieval over Long Jurisprudential Texts

Lucas Pereira, Erick Brito, Roberto Lotufo +1

Legal retrieval over jurisprudential collections is challenging because court decisions are long, heterogeneous documents whose relevant legal thesis may occupy only a small portio…

cs.IR2026

Domain-Adaptive Dense Retrieval for Brazilian Legal Search

Jayr Pereira, Roberto Lotufo, Luiz Bonifacio

Brazilian legal retrieval is heterogeneous, covering case law, legislation, and question-based search. This makes training dense retrievers a trade-off between stronger domain spec…

cs.IR2026

JUÁ -- A Benchmark for Information Retrieval in Brazilian Legal Text Collections

Jayr Pereira, Leandro Fernandes, Erick de Brito +2

Legal information retrieval in Portuguese remains difficult to evaluate systematically because available datasets differ widely in document type, query style, and relevance definit…

cs.CL2025

PublicHearingBR: A Brazilian Portuguese Dataset of Public Hearing Transcripts for Summarization of Long Documents

Leandro Carísio Fernandes, Guilherme Zeferino Rodrigues Dobins, Roberto Lotufo +1

This paper introduces PublicHearingBR, a Brazilian Portuguese dataset designed for summarizing long documents. The dataset consists of transcripts of public hearings held by the Br…

cs.AI2025

RAISE: Reasoning Agent for Interactive SQL Exploration

Fernando Granado, Roberto Lotufo, Jayr Pereira

Recent advances in large language models (LLMs) have propelled research in natural language interfaces to databases. However, most state-of-the-art text-to-SQL systems still depend…

cs.CL2025

BR-TaxQA-R: A Dataset for Question Answering with References for Brazilian Personal Income Tax Law, including case law

Juvenal Domingos Júnior, Augusto Faria, E. Seiti de Oliveira +6

This paper presents BR-TaxQA-R, a novel dataset designed to support question answering with references in the context of Brazilian personal income tax law. The dataset contains 715…