Guan MY, Joglekar M, Wallace E, Jain S, Barak B, Helyar A, et al. Deliberative Alignment: Reasoning Enables Safer Language Models. SI [Internet]. 2025 Jul. 20 [cited 2026 Aug. 25];2(3). Available from: https://ticket17180.pkpmisc01.publicknowledgeproject.org/index.php/agi/article/view/15159