FENG, Duanyu; QIN, Bowen; HUANG, Chen; HUANG, Youcheng; ZHANG, Zheng; LEI, Wenqiang. LEGEND: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 39, n. 26, p. 27277–27285, 2025. DOI: 10.1609/aaai.v39i26.34937. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/34937. Acesso em: 31 may. 2026.