Valentino, Marco, Geonhee Kim, Dhairya Dalal, Zhixue Zhao, and André Freitas. “Mitigating Content Effects on Reasoning in Language Models Through Fine-Grained Activation Steering”. Proceedings of the AAAI Conference on Artificial Intelligence 40, no. 39 (March 14, 2026): 33314–33322. Accessed May 18, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/40617.