AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs Paper • 2404.07921 • Published Apr 11, 2024 • 3
AmpleGCG-Plus: A Strong Generative Model of Adversarial Suffixes to Jailbreak LLMs with Higher Success Rates in Fewer Attempts Paper • 2410.22143 • Published Oct 29, 2024 • 1
How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs Paper • 2401.06373 • Published Jan 12, 2024 • 2
GLiNER2: An Efficient Multi-Task Information Extraction System with Schema-Driven Interface Paper • 2507.18546 • Published Jul 24 • 30