用二项式编码让每个字都嵌入多比特水印，提升隐蔽性和准确性。
Every Bit, Everywhere, All at Once: A Binomial Multibit LLM Watermark
- 在每个词位置直接嵌入所有比特，实现全位同步编码
- 64比特水印下准确率超基线，低干扰场景优势更明显
- 提出按位置信度评分，更贴近真实应用评估需求
随着大模型水印已投入商用，实际应用亟需支持复杂信息（如用户ID或时间戳）的多比特水印技术。本文提出一种全新多比特水印方法：引入二项式编码，使每个比特在每一步生成中都被同时编码。结合状态化编码器，在生成过程中动态将编码压力集中于未充分编码的比特。在最多64比特负载下对8种基线方法的评估显示，本方案在消息准确率与鲁棒性上均表现更优，且在大负载和低失真场景下优势进一步扩大。同时，我们质疑现有评估指标的实用性，提出基于每比特置信度的评分机制，作为更贴近实际应用的评价标准。
原文摘要 · Abstract (English)
With LLM watermarking already being deployed commercially, practical applications increasingly require multibit watermarks that encode more complex payloads, such as user IDs or timestamps, into the generated text. In this work, we propose a fundamentally new approach for multibit watermarking: introducing binomial encoding to directly encode every bit of the payload at every token position. We complement our approach with a stateful encoder that during generation dynamically redirects encoding pressure toward underencoded bits. Our evaluation against 8 baselines on up to 64-bit payloads shows that our scheme achieves superior message accuracy and robustness, with the gap to baseline methods widening in more relevant settings (i.e., large payloads and low-distortion regimes). At the same time, we challenge prior works' evaluation metrics, highlighting their lack of practical insights, and introduce per-bit confidence scoring as a practically relevant metric for evaluating multibit LLM watermarks.
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。