HumorReject:用一点幽默将大语言模型安全性与拒绝前缀解耦
HumorReject: Decoupling LLM Safety from Refusal Prefix via A Little Humor
AI总结:
本文提出 HumorReject,通过幽默式间接拒绝替代显式拒绝前缀,以数据驱动方式解耦 LLM 安全与拒绝前缀,缓解过度防御并提升对前缀注入等攻击的鲁棒性。
摘要:
大语言模型(LLMs)通常依赖显式的拒绝前缀来保障安全,这使其容易受到前缀注入攻击。我们提出 HumorReject,一种新颖的数据驱动方法,通过将幽默作为一种间接拒绝策略,重新构想 LLM 安全机制,使其与拒绝前缀解耦。HumorReject 不是明确拒绝有害指令,而是以语境恰当的幽默作出回应,从而自然地化解潜在危险请求。我们的方法有效解决了常见的“过度防御”问题,同时展现出对各种攻击向量的更强鲁棒性。我们的研究结果表明,在实现有效的 LLM 安全方面,训练数据设计的改进可能与对齐算法本身同样重要。代码和数据集可在 https://github.com/wooozihui/HumorReject 获取。
英文摘要:
Large Language Models (LLMs) commonly rely on explicit refusal prefixes for safety, making them vulnerable to prefix injection attacks. We introduce HumorReject, a novel data-driven approach that reimagines LLM safety by decoupling it from refusal prefixes through humor as an indirect refusal strategy. Rather than explicitly rejecting harmful instructions, HumorReject responds with contextually appropriate humor that naturally defuses potentially dangerous requests. Our approach effectively addresses common "over-defense" issues while demonstrating superior robustness against various attack vectors. Our findings suggest that improvements in training data design can be as important as the alignment algorithm itself in achieving effective LLM safety. The code and dataset are available at https://github.com/wooozihui/HumorReject.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。