Skip to content
conftrace_
2026 EMNLP EMNLP 2026

CATMark: A Context-Aware Thresholding Framework for Robust Cross-Task Watermarking in Large Language Models

AbstractWatermarking algorithms for Large Language Models (LLMs) effectively identify machine-generated content by embedding and detecting hidden statistical features in text. However, such embedding leads to a decline in text quality, especially in low-entropy scenarios where performance needs improvement. Existing methods that rely on entropy thresholds often require significant computational resources for tuning and demonstrate poor adaptability to unknown or cross-task generation scenarios. We propose Context-Aware Threshold watermarking (CATMark), a novel framework that dynamically adjusts watermarking intensity based on real-time semantic context. CATMark partitions text generation into semantic states using logits clustering, establishing context-aware entropy thresholds that preserve fidelity in structured content while embedding robust watermarks. Crucially, it requires no pre-defined thresholds or task-specific tuning. Experiments show CATMark improves text quality in cross-tasks without sacrificing detection accuracy.

More from EMNLP 2026

All EMNLP 2026 papers →