Jona te Lintelo

WoE Wrote It? Watermarking Mixture-of-Experts LLMs for Black-Box Text Provenance

WoE remains detectable under adversarial supervised fine-tuning, model extraction, and output-level paraphrasing, forcing malicious actors into a trade-off in which weakening the attribution signal requires additional model adaptation or text-rewriting operations, or compromises the utility of the resulting output.