WaterMoE: Efficient Watermarking for MoE LLMs with Minimal Quality Loss

Jul 16, 2026

Researchers introduce WaterMoE, a watermarking method for Mixture-of-Experts (MoE) large language models that embeds signals by perturbing expert selection during inference. WaterMoE achieves high fidelity, incurs only about 1% additional inference latency, and demonstrates up to 4x speedup over existing watermarking approaches on a comprehensive benchmark, while outperforming state-of-the-art methods in quality and efficiency.

Why it matters: This work significantly advances practical LLM watermarking by minimizing performance and latency overhead, making watermarking feasible for real-world deployment in content provenance applications.

Full story at: arXiv Cryptography and Security ↗