6 papers
In-context Learning vs. Instruction Tuning: The Case of Small and Multilingual Language Models
David Ponce, Thierry Etchegoyhen
Instruction following is a critical ability for Large Language Models to perform downstream tasks. The standard approach to instruction tuning has relied on a specific phase of sup…
Text Adaptation to Plain Language and Easy Read via Automatic Post-Editing Cycles
Jesús Calleja, David Ponce, Thierry Etchegoyhen
We describe Vicomtech's participation in the CLEARS challenge on text adaptation to Plain Language and Easy Read in Spanish. Our approach features automatic post-editing of differe…
GeLaCo: An Evolutionary Approach to Layer Compression
David Ponce, Thierry Etchegoyhen, Javier Del Ser
Large Language Models (LLM) have achieved remarkable performance across a large number of tasks, but face critical deployment and usage barriers due to substantial computational re…
Automating Easy Read Text Segmentation
Jesús Calleja, Thierry Etchegoyhen, David Ponce
Easy Read text is one of the main forms of access to information for people with reading difficulties. One of the key characteristics of this type of text is the requirement to spl…
Does Context Help Mitigate Gender Bias in Neural Machine Translation?
Harritxu Gete, Thierry Etchegoyhen
Neural Machine Translation models tend to perpetuate gender bias present in their training data distribution. Context-aware models have been previously suggested as a means to miti…
Split and Rephrase with Large Language Models
David Ponce, Thierry Etchegoyhen, Jesús Calleja Pérez +1
The Split and Rephrase (SPRP) task, which consists in splitting complex sentences into a sequence of shorter grammatical sentences, while preserving the original meaning, can facil…