Palette: 一种模块化、可控且高效的框架，用于按需授权安全对齐放松的LLMs
Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs
AI总结：
提出Palette框架，通过多目标搜索识别拒绝方向并轻量级适配模型，实现按需放松授权领域的安全拒绝行为，同时保持其他区域的标准安全，支持模块化组合多领域授权。
摘要：
当前基础模型的安全对齐大多遵循“一刀切”范式，跨用户和上下文应用相同的拒绝策略。因此，模型可能拒绝对于一般用户不安全但授权专业人员合法的请求，限制了专业环境中的有用性。现有方法要么需要昂贵的重新对齐，要么依赖推理时控制，但存在控制不精确和延迟增加的问题。为此，我们提出Palette，一个模块化、可控且高效的框架，选择性地放松授权目标领域的拒绝行为，同时在其他地方保持标准安全。我们的方法通过多目标搜索识别拒绝方向，并通过轻量级适配将其内化到模型中。Palette进一步支持模块化组合：它独立学习领域特定的安全控制，并通过参数合并进行组合，无需重新训练即可实现按需多领域授权。在四个安全基准、多个模型变体以及LLMs和VLMs上的实验表明，Palette在不牺牲通用实用性的情况下提供精确的安全控制，为基础模型适应多样化专业需求提供了一条实用路径。
英文摘要：
Current safety alignment of foundation models largely follows a \emph{one-size-fits-all} paradigm, applying the same refusal policy across users and contexts. As a result, models may refuse requests that are unsafe for general users but legitimate for authorized professionals, limiting helpfulness in specialized professional settings. Existing approaches either require costly realignment or rely on inference-time steering that suffers from imprecise control and added latency. To this end, we propose \textsc{Palette}, a modular, controllable, and efficient framework that selectively relaxes refusal behavior on authorized target domains while preserving standard safety elsewhere. Our method identifies a refusal direction via multi-objective search and internalizes it into the model through lightweight adaptation. \textsc{Palette} further supports modular composition: it learns domain-specific safety controls independently and composes them through parameter merging, enabling on-demand multi-domain authorization without retraining. Experiments across four safety benchmarks, multiple model variants, and both LLMs and VLMs show that \textsc{Palette} delivers precise safety control without sacrificing general utility, offering a practical path toward foundation models that adapt to diverse professional needs.
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。
