2 papers
cs.CL2026
Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations
Pere Martra, Eugenio Martínez Cámara, Alfonso Ureña López
This work presents Fairness Pruning, a lightweight structural intervention method designed for the management and future mitigation of demographic bias in large language models (LL…
cs.CL2025
Enhancing Disinformation Detection with Explainable AI and Named Entity Replacement
Santiago González-Silot, Andrés Montoro-Montarroso, Eugenio Martínez Cámara +1
The automatic detection of disinformation presents a significant challenge in the field of natural language processing. This task addresses a multifaceted societal and communicatio…