JIANG, Wei. CHCF-Bench: Safety Alignment Evaluation of Large Language Models for Chinese High-Context Cultural Friction. Exploring Science Academic Conference Series, [S. l.], v. 16, p. 119–130, 2026. DOI: 10.70267/aitia.2026119130. Disponível em: https://journals.zeuspress.org/index.php/conference/article/view/1306. Acesso em: 14 sep. 2026.