AI RESEARCH
MOSAIC: Composable Safety Alignment with Modular Control Tokens
arXiv CS.AI
•
ArXi:2603.16210v1 Announce Type: new Safety alignment in large language models (LLMs) is commonly implemented as a single static policy embedded in model parameters. However, real-world deployments often require context-dependent safety rules that vary across users, regions, and applications. Existing approaches struggle to provide such conditional control: parameter-level alignment entangles safety behaviors with general capabilities, while prompt-based methods rely on natural language instructions that provide weak enforcement.