Roseval Malaquias Junior
Roseval Malaquias Junior has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Rodrigo Nogueira
State University of Campinas (UNICAMP)
7 shared publications - Ramon Pires
Maritaca AI
6 shared publications - Celio Larcher
Jusbrasil
4 shared publications - Giovana Kerche Bonás
Instituto de Computac ¸ão (IC) Universidade Estadual de Campinas (UNICAMP) Campinas -SP Brazil
4 shared publications - Hugo Abonizio
Maritaca AI
4 shared publications - Marcos Piau
Jusbrasil
4 shared publications
Latest Publications
- 3 October 2026
- Published by Springer Nature
- p. 108-122
Prosa: Rubric-Based Evaluation of LLMs on Real User Chats in Brazilian Portuguese
- 3 October 2026
- Published by Springer Nature
- p. 108-122
Prosa: Rubric-Based Evaluation of LLMs on Real User Chats in Brazilian Portuguese
- 2 October 2026
- Published by Springer Nature
- p. 315-328
Do LLMs Take Sides? Measuring Opinion Bias and Sycophancy via Multi-turn Probing
- 2 October 2026
- Published by Springer Nature
- p. 315-328
Do LLMs Take Sides? Measuring Opinion Bias and Sycophancy via Multi-turn Probing
- 30 September 2026
- Published by Springer Nature
- p. 460-472
MARCA: A Checklist-Based Benchmark for Multilingual Web Search
- 30 September 2026
- Published by Springer Nature
- p. 460-472
MARCA: A Checklist-Based Benchmark for Multilingual Web Search
- 30 September 2026
- Published by Springer Nature
- p. 368-381
CAPITU: A Benchmark for Evaluating Instruction-Following in Brazilian Portuguese with Literary Context
- 30 September 2026
- Published by Springer Nature
- p. 368-381
CAPITU: A Benchmark for Evaluating Instruction-Following in Brazilian Portuguese with Literary Context
- Top Cited Papers
- 30 January 2026
- Published by Springer Nature
- p. 121-134
Juru: Legal Brazilian Large Language Model from Reputable Sources
- 30 January 2026
- Published by Springer Nature
- p. 121-134
Top Cited PapersJuru: Legal Brazilian Large Language Model from Reputable Sources
- Open Access
- 16 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 420-424
Automatic Legal Writing Evaluation of LLMs
- 16 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 420-424
Open AccessAutomatic Legal Writing Evaluation of LLMs
- Open Access
Explainable LightGBM Approach for Predicting Myocardial Infarction Mortality
Myocardial Infarction is a main cause of mortality globally, and accurate risk prediction is crucial for improving patient outcomes. Machine Learning techniques have shown promise in identifying high-risk patients and predicting outcomes. However, patient data often contain vast amounts of information and missing values, posing challenges for feature selection and imputation methods. In this article, we investigate the impact of the data preprocessing task and compare three ensembles boosted tree methods to predict the risk of mortality in patients with myocardial infarction. Further, we use the Tree Shapley Additive Explanations method to identify relationships among all the features for the performed predictions, leveraging the entirety of the available data in the analysis. Notably, our approach achieved a superior performance when compared to other existing machine learning approaches, with an F1-score of 91,2% and an accuracy of 91,8% for LightGBM without data preprocessing.
Open AccessExplainable LightGBM Approach for Predicting Myocardial Infarction Mortality
Myocardial Infarction is a main cause of mortality globally, and accurate risk prediction is crucial for improving patient outcomes. Machine Learning techniques have shown promise in identifying high-risk patients and predicting outcomes. However, patient data often contain vast amounts of information and missing values, posing challenges for feature selection and imputation methods. In this article, we investigate the impact of the data preprocessing task and compare three ensembles boosted tree methods to predict the risk of mortality in patients with myocardial infarction. Further, we use the Tree Shapley Additive Explanations method to identify relationships among all the features for the performed predictions, leveraging the entirety of the available data in the analysis. Notably, our approach achieved a superior performance when compared to other existing machine learning approaches, with an F1-score of 91,2% and an accuracy of 91,8% for LightGBM without data preprocessing.
- 12 October 2023
- Published by Springer Nature
- p. 63-77
Exploring Text Decoding Methods for Portuguese Legal Text Generation
- 12 October 2023
- Published by Springer Nature
- p. 63-77
Exploring Text Decoding Methods for Portuguese Legal Text Generation
- 1 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 86-91
Visualization of similarity queries in an immersive virtual reality environment
The virtual reality provides new possibilities for data interaction in visualization systems, assisting users in the analysis of data through improved intuition and perception. In content-based image retrieval systems the visualization of queries results allows adding the human visual perception in the analysis, improving the knowledge discovery process. Visualization allows users to better understand the distribution of data related to the queries and to incorporate their prior knowledge in the process of data retrieval and analysis. This work proposes the interactive visualization of similarity queries on complex data in a low cost immersive virtual reality environment. Thus, we proposed rendering options and techniques for interaction to avail advantages of the immersive environment and enable the cheap and practical visualization of similarity queries. We present visualization examples, through the virtual reality prototype produced, to demonstrate the advantages of its use in data analysis.
- 1 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 86-91
Visualization of similarity queries in an immersive virtual reality environment
The virtual reality provides new possibilities for data interaction in visualization systems, assisting users in the analysis of data through improved intuition and perception. In content-based image retrieval systems the visualization of queries results allows adding the human visual perception in the analysis, improving the knowledge discovery process. Visualization allows users to better understand the distribution of data related to the queries and to incorporate their prior knowledge in the process of data retrieval and analysis. This work proposes the interactive visualization of similarity queries on complex data in a low cost immersive virtual reality environment. Thus, we proposed rendering options and techniques for interaction to avail advantages of the immersive environment and enable the cheap and practical visualization of similarity queries. We present visualization examples, through the virtual reality prototype produced, to demonstrate the advantages of its use in data analysis.