Piras, G., Mura, R., Brau, F., Oneto, L., Roli, F., & Biggio, B. (2026). SOM Directions Are Better than One: Multi-Directional Refusal Suppression in Language Models. Proceedings of the AAAI Conference on Artificial Intelligence, 40(39), 32728–32736. https://doi.org/10.1609/aaai.v40i39.40551