Valentino, M., Kim, G., Dalal, D., Zhao, Z., & Freitas, A. (2026). Mitigating Content Effects on Reasoning in Language Models Through Fine-Grained Activation Steering. Proceedings of the AAAI Conference on Artificial Intelligence, 40(39), 33314–33322. https://doi.org/10.1609/aaai.v40i39.40617