Enhancing Watermarking Quality for LLMs via Contextual Generation States Awareness

TL;DR

This paper presents CAW, a novel watermarking framework for LLMs that dynamically adjusts embedding based on contextual states, improving content quality and detection accuracy.

Contribution

Introducing a plug-and-play, context-aware watermarking framework that evaluates and adapts embedding to enhance LLM output quality.

Findings

Outperforms baselines in detection rate

Maintains high generation quality

Effective across multiple domains

Abstract

Recent advancements in watermarking techniques have enabled the embedding of secret messages into AI-generated text (AIGT), serving as an important mechanism for AIGT detection. Existing methods typically interfere with the generation processes of large language models (LLMs) to embed signals within the generated text. However, these methods often rely on heuristic rules, which can result in suboptimal token selection and a subsequent decline in the quality of the generated content. In this paper, we introduce a plug-and-play contextual generation states-aware watermarking framework (CAW) that dynamically adjusts the embedding process. It can be seamlessly integrated with various existing watermarking methods to enhance generation quality. First, CAW incorporates a watermarking capacity evaluator, which can assess the impact of embedding messages at different token positions by analyzing the contextual generation states. Furthermore, we introduce a multi-branch pre-generation mechanism to avoid the latency caused by the proposed watermarking strategy. Building on this, CAW can dynamically adjust the watermarking process based on the evaluated watermark capacity of each token, thereby minimizing potential degradation in content quality. Extensive experiments conducted on datasets across multiple domains have verified the effectiveness of our method, demonstrating superior performance compared to various baselines in terms of both detection rate and generation quality.