Marcos Piau
Research Subjects
Marcos Piau has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Rodrigo Nogueira
State University of Campinas (UNICAMP)
5 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 - Ramon Pires
Maritaca AI
4 shared publications - Roseval Malaquias Junior
Maritaca AI
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
- 30 January 2025
- Published by Springer Nature
- p. 324-338
ptt5-v2: A Closer Look at Continued Pretraining of T5 Models for the Portuguese Language
- 30 January 2025
- Published by Springer Nature
- p. 324-338
ptt5-v2: A Closer Look at Continued Pretraining of T5 Models for the Portuguese Language
- Open Access
The Chronicles of RAG: The Retriever, the Chunk and the Generator
Retrieval Augmented Generation (RAG) has become one of the most popular paradigms for enabling LLMs to access external data, and also as a mechanism for grounding to mitigate against hallucinations. When implementing RAG you can face several challenges like effective integration of retrieval models, efficient representation learning, data diversity, computational efficiency optimization, evaluation, and quality of text generation. Given all these challenges, every day a new technique to improve RAG appears, making it unfeasible to experiment with all combinations for your problem. In this context, this paper presents good practices to implement, optimize, and evaluate RAG for the Brazilian Portuguese language, focusing on the establishment of a simple pipeline for inference and experiments. We explored a diverse set of methods to answer questions about the first Harry Potter book. To generate the answers we used the OpenAI's gpt-4, gpt-4-1106-preview, gpt-3.5-turbo-1106, and Google's Gemini Pro. Focusing on the quality of the retriever, our approach achieved an improvement of MRR@10 by 35.4% compared to the baseline. When optimizing the input size in the application, we observed that it is possible to further enhance it by 2.4%. Finally, we present the complete architecture of the RAG with our recommendations. As result, we moved from a baseline of 57.88% to a maximum relative score of 98.61%.
Open AccessThe Chronicles of RAG: The Retriever, the Chunk and the Generator
Retrieval Augmented Generation (RAG) has become one of the most popular paradigms for enabling LLMs to access external data, and also as a mechanism for grounding to mitigate against hallucinations. When implementing RAG you can face several challenges like effective integration of retrieval models, efficient representation learning, data diversity, computational efficiency optimization, evaluation, and quality of text generation. Given all these challenges, every day a new technique to improve RAG appears, making it unfeasible to experiment with all combinations for your problem. In this context, this paper presents good practices to implement, optimize, and evaluate RAG for the Brazilian Portuguese language, focusing on the establishment of a simple pipeline for inference and experiments. We explored a diverse set of methods to answer questions about the first Harry Potter book. To generate the answers we used the OpenAI's gpt-4, gpt-4-1106-preview, gpt-3.5-turbo-1106, and Google's Gemini Pro. Focusing on the quality of the retriever, our approach achieved an improvement of MRR@10 by 35.4% compared to the baseline. When optimizing the input size in the application, we observed that it is possible to further enhance it by 2.4%. Finally, we present the complete architecture of the RAG with our recommendations. As result, we moved from a baseline of 57.88% to a maximum relative score of 98.61%.