Exposing Long-Tail Safety Failures in Large Language Models through Efficient Diverse Response Sampling

תקציר מקורי באנגליתarXiv:2603.14355v2 Announce Type: replace Abstract: Safety tuning through supervised fine-tuning and reinforcement learning from human feedback has substantially improved the robustness of large language models. However, it typically suppresses rather eliminates unsafe behaviors, leaving rare but critical failures hidden in the long tail of the output distribution. While most red-teaming work emphasizes adversarial prompt search, we show that these hidden risks can be systematically exposed through diverse response generation. Specifically, we show that, for a fixed safety-critical prompt, increasing the number and diversity of sampled responses monotonically raises the jailbreak success rate. To efficiently uncover these failures, we propose Progressive Diverse Population Sampling (PDPS).