研究人员开发了PsychoSafe框架，通过采用心理学启发的沟通策略来改进大型语言模型拒绝有害请求的方式。这种方法将拒绝重新定义为支持性互动，增强了外部资源推荐和心理基础。另外，另一项研究引入了用于规避拒绝的潜在空间攻击，该研究分析了如何通过操纵模型内部表征来抑制拒绝行为，从而绕过大型语言模型的安全机制。 AI
影响 大型语言模型拒绝策略和规避技术的发展凸显了人工智能安全和对齐方面持续存在的挑战。
排序理由 两篇关于大型语言模型安全和拒绝机制的研究论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
Large language models (LLMs) routinely face requests that should be refused, creating a trade-off between helpfulness and harm prevention. However, refusals themselves can be helpful. In high-risk interactions involving crisis, coercion, or escalating intent, blunt non-compliance…
A psychologically-informed refusal framework called PsychoSafe is developed for large language models to improve harmful request handling through structured supportive communication, showing enhanced refusal quality and resource referral while maintaining performance on non-refus…
arXiv:2605.21706v2 Announce Type: replace Abstract: Safety-aligned language models are trained to refuse harmful requests, yet refusal behavior can be suppressed by steering their internal representations. Existing methods do so by ablating a refusal direction from model activati…