Search Results for author:
Found 10 papers, 3 papers with code
TiEBe: A Benchmark for Assessing the Current Knowledge of Large Language Models
In a rapidly evolving knowledge landscape and the increasing adoption of large language models, a need has emerged to keep these models continuously updated with current events.
The interplay between domain specialization and model size: a case study in the legal domain
To compare general and specialized training, we filtered a web-based dataset to extract legal domain data.
Sabiá-3 Technical Report
This report presents Sabi\'a-3, our new flagship language model, and Sabiazinho-3, a more cost-effective sibling.
SurveySum: A Dataset for Summarizing Multiple Scientific Articles into a Survey Section
Document summarization is a task to shorten texts into concise and informative summaries.
Measuring Cross-lingual Transfer in Bytes
We also found evidence that this transfer is not related to language contamination or language proximity, which strengthens the hypothesis that the model also relies on language-agnostic knowledge.
Sabiá-2: A New Generation of Portuguese Large Language Models
We introduce Sabi\'a-2, a family of large language models trained on Portuguese texts.
Evaluating GPT-4's Vision Capabilities on Brazilian University Admission Exams
Recent advancements in language models have showcased human-comparable performance in academic entrance exams.
BLUEX: A benchmark based on Brazilian Leading Universities Entrance eXams
One common trend in recent studies of language models (LMs) is the use of standardized tests for evaluation.
Sabiá: Portuguese Large Language Models
By evaluating on datasets originally conceived in the target language as well as translated ones, we study the contributions of language-specific pretraining in terms of 1) capturing linguistic nuances and structures inherent to the target language, and 2) enriching the model's knowledge about a domain or culture.
NeuralSearchX: Serving a Multi-billion-parameter Reranker for Multilingual Metasearch at a Low Cost
We compare our system with Microsoft's Biomedical Search and show that our design choices led to a much cost-effective system with competitive QPS while having close to state-of-the-art results on a wide range of public benchmarks.
