CATMark: A Context-Aware Thresholding Framework for Robust Cross-Task Watermarking in Large Language Models
Watermarking 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 \textbf{C}ontext-\textbf{A}ware \textbf{T}hreshold watermarking ($\myalgo$), a novel framework that dynamically adjusts watermarking intensity based on real-time semantic context. $\myalgo$ 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 $\myalgo$ improves text quality in cross-tasks without sacrificing detection accuracy.
Code (0)
등록된 구현이 없습니다.
Tasks
Text GenerationSimilar Papers 제목 키워드 기반
Weakly supervised multimodal segmentation of acoustic borehole images with depth-aware cross-attention
Acoustic borehole images provide high-resolution borehole-wall structure, but large-scale interpretation remains difficult because dense expert annotations are rarely available and subsurface information is intrinsically…
CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models
Large Language Models (LLMs) have dramatically advanced AI applications, yet their deployment remains challenging due to their immense inference costs. Recent studies ameliorate the computational costs of LLMs by increas…
GPUInclusive Speaker Verification with Adaptive thresholding
While using a speaker verification (SV) based system in a commercial application, it is important that customers have an inclusive experience irrespective of their gender, age, or ethnicity. In this paper, we analyze the…
Speaker VerificationFlashPrefill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling
Long-context modeling is a pivotal capability for Large Language Models, yet the quadratic complexity of attention remains a critical bottleneck, particularly during the compute-intensive prefilling phase. While various …
Study of Proximal Normalized Subband Adaptive Algorithm for Acoustic Echo Cancellation
In this paper, we propose a novel normalized subband adaptive filter algorithm suited for sparse scenarios, which combines the proportionate and sparsity-aware mechanisms. The proposed algorithm is derived based on the p…
Acoustic echo cancellation