Feng, Duanyu, Bowen Qin, Chen Huang, Youcheng Huang, Zheng Zhang, and Wenqiang Lei. “LEGEND: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets”. Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 26 (April 11, 2025): 27277–27285. Accessed May 31, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/34937.