Beyond Semantic Narrowing: Robust and Efficient LLM Watermarking with Hamming Neighborhoods

תקציר מקורי באנגליתarXiv:2609.37218v1 Announce Type: cross Abstract: Semantic watermarking improves robustness against watermark removal attacks by embedding detectable signals into sentence-level representations. However, existing watermarking methods typically impose watermark-specific semantic preferences on generated sentences without explicitly accounting for the highly non-uniform and context-dependent semantic preference of LLM generation. When these two preferences are poorly aligned, many natural continuations become incompatible with the watermark, causing semantic narrowing: reduced semantic freedom, increased resampling cost, and potential degradation on tasks with strict semantic requirements. To alleviate this problem, we propose HammingMark, which uses the semantic hash of the preceding senten