让大模型智能选时机加水印，兼顾可检测性和文本质量。
Learning to Watermark: A Selective Watermarking Framework for Large Language Models via Multi-Objective Optimization
- 通过分析句子嵌入等信号，动态决定何时加水印。
- 在不降低可检测性前提下，显著提升生成文本质量。
- 适合需要高质量输出的AI内容安全场景。
大语言模型的快速发展引发了对其潜在滥用的担忧，催生了多种水印方案，但现有技术常在水印可检测性与生成文本质量间存在权衡。本文提出学习型水印（LTW）框架，采用多目标优化实现两者平衡。该框架包含轻量级网络，通过分析句子嵌入、词元熵和当前水印比例，自适应决策是否加水印。训练过程使用两个定制损失函数，引导模型收敛至帕累托最优解，协调水印可检测性与文本质量。将LTW集成至两种基线水印方法后，实验表明其在不牺牲可检测性的前提下显著提升文本质量。该选择性水印方法为大模型水印设计提供了新思路，有助于在保持高文本质量的同时实现有效溯源。代码已开源：https://github.com/fattyray/learning-to-watermark
原文摘要 · Abstract (English)
The rapid development of LLMs has raised concerns about their potential misuse, leading to various watermarking schemes that typically offer high detectability. However, existing watermarking techniques often face trade-off between watermark detectability and generated text quality. In this paper, we introduce Learning to Watermark (LTW), a novel selective watermarking framework that leverages multi-objective optimization to effectively balance these competing goals. LTW features a lightweight network that adaptively decides when to apply the watermark by analyzing sentence embeddings, token entropy, and current watermarking ratio. Training of the network involves two specifically constructed loss functions that guide the model toward Pareto-optimal solutions, thereby harmonizing watermark detectability and text quality. By integrating LTW with two baseline watermarking methods, our experimental evaluations demonstrate that LTW significantly enhances text quality without compromising detectability. Our selective watermarking approach offers a new perspective for designing watermarks for LLMs and a way to preserve high text quality for watermarks. The code is publicly available at: https://github.com/fattyray/learning-to-watermark
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。