用稀疏自编码器实现多语言大模型文本水印，不改模型也能精准溯源。
SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders
- 通过推理时特征采样嵌入水印，无需修改模型参数或日志
- 在4个数据集上实现99.7%的检测准确率，保持文本质量
- 适用于闭源模型，适合需内容溯源的多语言场景
大模型生成文本的水印技术对内容归属和假信息防范至关重要。现有方法损害文本质量，依赖白盒模型访问与日志修改，难以应用于API模型及多语言场景。我们提出SAEMark，一种通用的后处理多比特水印框架，仅通过推理时基于特征的拒绝采样嵌入个性化信息，不改变模型日志，也无需训练。该方法基于生成文本的确定性特征，选择其特征统计与密钥导出目标一致的输出。该框架天然支持跨语言与跨领域，通过采样而非修改保持文本质量。我们提供理论保证，关联水印成功率与计算预算，适用于任意合适的特征提取器。实验采用稀疏自编码器（SAEs），在4个数据集上验证有效性，英文检测F1达99.7%，具备强多比特检测能力。SAEMark为闭源大模型提供了开箱即用的可扩展水印新范式，实现内容溯源。
原文摘要 · Abstract (English)
Watermarking LLM-generated text is critical for content attribution and misinformation prevention. However, existing methods compromise text quality, require white-box model access and logit manipulation. These limitations exclude API-based models and multilingual scenarios. We propose SAEMark, a general framework for post-hoc multi-bit watermarking that embeds personalized messages solely via inference-time, feature-based rejection sampling without altering model logits or requiring training. Our approach operates on deterministic features extracted from generated text, selecting outputs whose feature statistics align with key-derived targets. This framework naturally generalizes across languages and domains while preserving text quality through sampling LLM outputs instead of modifying. We provide theoretical guarantees relating watermark success probability and compute budget that hold for any suitable feature extractor. Empirically, we demonstrate the framework's effectiveness using Sparse Autoencoders (SAEs), achieving superior detection accuracy and text quality. Experiments across 4 datasets show SAEMark's consistent performance, with 99.7% F1 on English and strong multi-bit detection accuracy. SAEMark establishes a new paradigm for scalable watermarking that works out-of-the-box with closed-source LLMs while enabling content attribution.
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。