SOURCE-LINKED INTELLIGENCE

Learning to Follow In-Context Watermark Instructions via Self-Distillation

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

In-context watermarking (ICW) prepends an instruction to a query asking the model to embed a statistically detectable signal in its response. It thus equips LLMs with a watermarking interface that third parties can invoke without access to model internals. Its reliability hinges on the LLM following the instruction without degrading answer quality, yet how well current LLMs do so has not been measured. We introduce $\mathsf{ICWBench}$, a benchmark of three verifiable ICW instruction families, each scored on both detectability and answer quality. Evaluating 14 frontier proprietary and open-sour

Read original source ↗ Open in workspace

recordType

paper

region

Global