LineageMark: Multi-user White-box Watermarking for Contribution Tracing in Model Derivation Chains (opens in new tab)

In open large language model (LLM) ecosystems, models are frequently adapted across multiple domains and applications, forming multi-stage derivation chains. Consequently, tracking and verifying historical contributions is essential for model provenance and intellectual property protection. However, existing watermarking methods are mainly designed for single-user, one-time embeddings, often fail under repeated model derivation and incremental u...