Extracting and Encoding: Leveraging Large Language Models and Medical Knowledge to Enhance Radiological Text Representation

1 code implementation • 2 Jul 2024 • Pablo Messina, René Vidal, Denis Parra, Álvaro Soto, Vladimir Araujo

In the first stage, we propose a \textit{Fact Extractor} that leverages large language models (LLMs) to identify factual statements from well-curated domain-specific datasets.

Natural Language Inference Representation Learning +2

Eigenpruning: an Interpretability-Inspired PEFT Method

1 code implementation • 4 Apr 2024 • Tomás Vergara-Browne, Álvaro Soto, Akiko Aizawa

In the case of a small synthetic task in integer multiplication, the Phi-2 model can improve its accuracy in the test set from 13. 75% to 97. 50%.

Bridging the visual gap in VLN via semantically richer instructions

no code implementations • 27 Oct 2022 • Joaquin Ossandón, Benjamin Earle, Álvaro Soto

In this work, we hypothesize that poor use of the visual information available is at the core of the low performance of current models.

Data Augmentation Navigate

DACT-BERT: Differentiable Adaptive Computation Time for an Efficient BERT Inference

no code implementations • nlppower (ACL) 2022 • Cristóbal Eyzaguirre, Felipe del Río, Vladimir Araujo, Álvaro Soto

Large-scale pre-trained language models have shown remarkable results in diverse NLP applications.