VALENTINO, Marco; KIM, Geonhee; DALAL, Dhairya; ZHAO, Zhixue; FREITAS, André. Mitigating Content Effects on Reasoning in Language Models Through Fine-Grained Activation Steering. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 39, p. 33314–33322, 2026. DOI: 10.1609/aaai.v40i39.40617. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/40617. Acesso em: 18 may. 2026.