Valentino M, Kim G, Dalal D, Zhao Z, Freitas A. Mitigating Content Effects on Reasoning in Language Models Through Fine-Grained Activation Steering. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 18];40(39):33314-22. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/40617