Amelia Hardy, Houjun Liu, Allie Griffith, Bernard Lange, Duncan Eddy, Mykel J. Kochenderfer. ASTPrompter: Preference-Aligned Automated Language Model Red-Teaming to Generate Low-Perplexity Unsafe Prompts. In Christos Christodoulopoulos 0001, Tanmoy Chakraborty 0002, Carolyn Rose, Violet Peng, editors, Findings of the Association for Computational Linguistics: EMNLP 2025, Suzhou, China, November 4-9, 2025. pages 2668-2683, Association for Computational Linguistics, 2025. [doi]
Abstract is missing.