让大模型按用户权限控制知识访问，高手可解锁隐藏内容。
SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment
- 用授权对齐机制实现不同用户对模型知识的分级访问
- 有SUDO密钥的用户可访问全部参数化知识，他人被屏蔽
- 适用于需要权限管理的场景，如专业工具或敏感信息
现有偏好对齐是统一机制，所有用户都被禁止访问模型中非偏好特征的知识。但这些知识对高级用户而言可能有用，因其具备处理能力。统一屏蔽降低了模型对合格用户的实用性。为此，我们提出SudoLM框架，通过授权对齐让大模型根据用户权限动态控制特定参数化知识的访问。拥有指定SUDO密钥的授权用户可解锁全部知识，非合格用户则被限制访问。在两个应用场景的实验表明，SudoLM能有效控制用户对参数化知识的访问，同时保持模型的一般可用性。
原文摘要 · Abstract (English)
Existing preference alignment is a one-size-fits-all alignment mechanism, where the part of the large language model (LLM) parametric knowledge with non-preferred features is uniformly blocked to all the users. However, this part of knowledge can be useful to advanced users whose expertise qualifies them to handle these information. The one-size-fits-all alignment mechanism undermines LLM's utility for these qualified users. To address this problem, we propose SudoLM, a framework that lets LLMs learn access control over specific parametric knowledge for users with different credentials via authorization alignment. SudoLM allows authorized users to unlock their access to all the parametric knowledge with an assigned SUDO key while blocking access to non-qualified users. Experiments on two application scenarios demonstrate that SudoLM effectively controls the user's access to the parametric knowledge and maintains its general utility.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。