N. Madrueño Sierro, I. Martín de Diego, A. Fernández Isabel

Recent advances in generative artificial intelligence (GenAI) offer new opportunities for improving natural language processing models. Specifically, the text generation and in-context learning capabilities of large language models (LLMs) can enhance model generalization and robustness. Within this context, a new framework is presented to improve systems across the model lifecycle. It addresses stages ranging from data preparation and robustness evaluation to defense against problematic inputs. The proposed framework demonstrates how LLMs can be leveraged effectively during both training and inference time. Consequently, it contributes to the development of more accurate and reliable NLP models for real-world applications.

Keywords: Generative artificial intelligence, Large language model, Prompt engineering, In-context learning

Scheduled

GT SW II: Inteligencia Artificial y Aprendizaje Automático
September 5, 2026  10:00 AM
Aula 21


Other papers in the same session


Cookie policy

We use cookies in order to be able to identify and authenticate you on the website. They are necessary for the correct functioning of it, and therefore they can not be disabled. If you continue browsing the website, you are agreeing with their acceptance, as well as our Privacy Policy.

Additionally, we use Google Analytics in order to analyze the website traffic. They also use cookies and you can accept or refuse them with the buttons below.

You can read more details about our Cookie Policy and our Privacy Policy.