activity
20172024
most citedEquilibria in the Tangle

102 citations · 144 across the 5 of their papers we have counts for

collaborators

6 papers

cs.LG2024★ 15 cited

The Chronicles of RAG: The Retriever, the Chunk and the Generator

Paulo Finardi, Leonardo Avila, Rodrigo Castaldoni +5

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 again…

cs.CL2023

Portuguese FAQ for Financial Services

Paulo Finardi, Wanderley M. Melo, Edgard D. Medeiros Neto +3

Scarcity of domain-specific data in the Portuguese financial domain has disfavored the development of Natural Language Processing (NLP) applications. To address this limitation, th…

cs.CL2023★ 4 cited

Cabrita: closing the gap for foreign languages

Celio Larcher, Marcos Piau, Paulo Finardi +3

The strategy of training the model from scratch in a specific language or domain serves two essential purposes: i) enhancing performance in the particular linguistic or domain cont…

cs.CL2021

BERTaú: Itaú BERT for digital customer service

Paulo Finardi, José Dié Viegas, Gustavo T. Ferreira +2

In the last few years, three major topics received increased interest: deep learning, NLP and conversational agents. Bringing these three topics together to create an amazing digit…

cs.LG2020★ 23 cited

Electricity Theft Detection with self-attention

Paulo Finardi, Israel Campiotti, Gustavo Plensack +4

In this work we propose a novel self-attention mechanism model to address electricity theft detection on an imbalanced realistic dataset that presents a daily electricity consumpti…

math.PR2017★ 102 cited

Equilibria in the Tangle

Serguei Popov, Olivia Saa, Paulo Finardi

We analyse the Tangle --- a DAG-valued stochastic process where new vertices get attached to the graph at Poissonian times, and the attachment's locations are chosen by means of ra…