344 citations · 1.7k across the 55 of their papers we have counts for
55 papers
Sabiá-3 Technical Report
Hugo Abonizio, Thales Sales Almeida, Thiago Laitz +4
This report presents Sabiá-3, our new flagship language model, and Sabiazinho-3, a more cost-effective sibling. The models were trained on a large brazilian-centric corpus. Evaluat…
Sabiá-2: A New Generation of Portuguese Large Language Models
Thales Sales Almeida, Hugo Abonizio, Rodrigo Nogueira +1
We introduce Sabiá-2, a family of large language models trained on Portuguese texts. The models are evaluated on a diverse range of exams, including entry-level tests for Brazilian…
BLUEX: A benchmark based on Brazilian Leading Universities Entrance eXams
Thales Sales Almeida, Thiago Laitz, Giovana K. Bonás +1
One common trend in recent studies of language models (LMs) is the use of standardized tests for evaluation. However, despite being the fifth most spoken language worldwide, few su…
InPars Toolkit: A Unified and Reproducible Synthetic Data Generation Pipeline for Neural Information Retrieval
Hugo Abonizio, Luiz Bonifacio, Vitor Jeronymo +3
Recent work has explored Large Language Models (LLMs) to overcome the lack of training data for Information Retrieval (IR) tasks. The generalization abilities of these models have…
A Personalized Dense Retrieval Framework for Unified Information Access
Hansi Zeng, Surya Kallumadi, Zaid Alibadi +2
Developing a universal model that can efficiently and effectively respond to a wide range of information access requests -- from retrieval to recommendation to question answering -…
Sabiá: Portuguese Large Language Models
Ramon Pires, Hugo Abonizio, Thales Sales Almeida +1
As the capabilities of language models continue to advance, it is conceivable that "one-size-fits-all" model will remain as the main paradigm. For instance, given the vast number o…
Evaluating GPT-3.5 and GPT-4 Models on Brazilian University Admission Exams
Desnes Nunes, Ricardo Primi, Ramon Pires +2
The present study aims to explore the capabilities of Language Models (LMs) in tackling high-stakes multiple-choice tests, represented here by the Exame Nacional do Ensino Médio (E…
NeuralMind-UNICAMP at 2022 TREC NeuCLIR: Large Boring Rerankers for Cross-lingual Retrieval
Vitor Jeronymo, Roberto Lotufo, Rodrigo Nogueira
This paper reports on a study of cross-lingual information retrieval (CLIR) using the mT5-XXL reranker on the NeuCLIR track of TREC 2022. Perhaps the biggest contribution of this s…
ExaRanker: Explanation-Augmented Neural Ranker
Fernando Ferraretto, Thiago Laitz, Roberto Lotufo +1
Recent work has shown that inducing a large language model (LLM) to generate explanations prior to outputting an answer is an effective strategy to improve performance on a wide ra…
InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrieval
Vitor Jeronymo, Luiz Bonifacio, Hugo Abonizio +4
Recently, InPars introduced a method to efficiently use large language models (LLMs) in information retrieval tasks: via few-shot examples, an LLM is induced to generate relevant q…
Visconde: Multi-document QA with GPT-3 and Neural Reranking
Jayr Pereira, Robson Fidalgo, Roberto Lotufo +1
This paper proposes a question-answering system that can answer questions whose supporting evidence is spread over multiple (potentially long) documents. The system, called Viscond…
In Defense of Cross-Encoders for Zero-Shot Retrieval
Guilherme Rosa, Luiz Bonifacio, Vitor Jeronymo +4
Bi-encoders and cross-encoders are widely used in many state-of-the-art retrieval pipelines. In this work we study the generalization ability of these two types of architectures on…
NeuralSearchX: Serving a Multi-billion-parameter Reranker for Multilingual Metasearch at a Low Cost
Thales Sales Almeida, Thiago Laitz, João Seródio +3
The widespread availability of search API's (both free and commercial) brings the promise of increased coverage and quality of search results for metasearch engines, while decreasi…
mRobust04: A Multilingual Version of the TREC Robust 2004 Benchmark
Vitor Jeronymo, Mauricio Nascimento, Roberto Lotufo +1
Robust 2004 is an information retrieval benchmark whose large number of judgments per query make it a reliable evaluation dataset. In this paper, we present mRobust04, a multilingu…
MonoByte: A Pool of Monolingual Byte-level Language Models
Hugo Abonizio, Leandro Rodrigues de Souza, Roberto Lotufo +1
The zero-shot cross-lingual ability of models pretrained on multilingual and even monolingual corpora has spurred many hypotheses to explain this intriguing empirical result. Howev…
A Boring-yet-effective Approach for the Product Ranking Task of the Amazon KDD Cup 2022
Vitor Jeronymo, Guilherme Rosa, Surya Kallumadi +2
In this work we describe our submission to the product ranking task of the Amazon KDD Cup 2022. We rely on a receipt that showed to be effective in previous competitions: we focus…
Induced Natural Language Rationales and Interleaved Markup Tokens Enable Extrapolation in Large Language Models
Mirelle Bueno, Carlos Gemmell, Jeffrey Dalton +2
The ability to extrapolate, i.e., to make predictions on sequences that are longer than those presented as training examples, is a challenging problem for current deep learning mod…
No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval
Guilherme Moraes Rosa, Luiz Bonifacio, Vitor Jeronymo +4
Recent work has shown that small distilled language models are strong competitors to models that are orders of magnitude larger and slower in a wide range of information retrieval…
Billions of Parameters Are Worth More Than In-domain Training Data: A case study in the Legal Case Entailment Task
Guilherme Moraes Rosa, Luiz Bonifacio, Vitor Jeronymo +3
Recent work has shown that language models scaled to billions of parameters, such as GPT-3, perform remarkably well in zero-shot and few-shot scenarios. In this work, we experiment…
InPars: Data Augmentation for Information Retrieval using Large Language Models
Luiz Bonifacio, Hugo Abonizio, Marzieh Fadaee +1
The information retrieval community has recently witnessed a revolution due to large pretrained transformer models. Another key ingredient for this revolution was the MS MARCO data…
To Tune or Not To Tune? Zero-shot Models for Legal Case Entailment
Guilherme Moraes Rosa, Ruan Chaves Rodrigues, Roberto de Alencar Lotufo +1
There has been mounting evidence that pretrained language models fine-tuned on large and diverse supervised datasets can transfer well to a variety of out-of-domain tasks. In this…
Sequence-to-Sequence Models for Extracting Information from Registration and Legal Documents
Ramon Pires, Fábio C. de Souza, Guilherme Rosa +2
A typical information extraction pipeline consists of token- or span-level classification models coupled with a series of pre- and post-processing scripts. In a production pipeline…
On the ability of monolingual models to learn language-agnostic representations
Leandro Rodrigues de Souza, Rodrigo Nogueira, Roberto Lotufo
Pretrained multilingual models have become a de facto default approach for zero-shot cross-lingual transfer. Previous work has shown that these models are able to achieve cross-lin…
mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset
Luiz Bonifacio, Vitor Jeronymo, Hugo Queiroz Abonizio +4
The MS MARCO ranking dataset has been widely used for training deep learning models for IR tasks, achieving considerable effectiveness on diverse zero-shot scenarios. However, this…