让大模型自动生成带水印的文本，且水印可被检测
Can you Finetune your Binoculars? Embedding Text Watermarks into the Weights of Large Language Models
- 用低秩适配器联合训练生成与检测模型，端到端嵌入水印
- 水印在保持文本自然度的同时，仍能被准确检测
- 适合需要内容溯源的AI生成场景
AI生成内容与人类文本难以区分，带来透明性与责任认定难题。现有方法多在API后端加水印，但直接将水印嵌入模型权重并反映在输出中仍具挑战。本文提出一种新策略：微调一对低秩适配器，一个用于文本生成，另一个用于水印检测，使生成文本隐含微妙水印，同时优化检测性能。该方法实现水印策略的端到端学习。过程中需权衡水印鲁棒性、文本自然度与任务表现，我们探讨了相应的最小-最大优化策略，并展示了其对指令微调的影响。
原文摘要 · Abstract (English)
The indistinguishability of AI-generated content from human text raises challenges in transparency and accountability. While several methods exist to watermark models behind APIs, embedding watermark strategies directly into model weights that are later reflected in the outputs of the model is challenging. In this study we propose a strategy to finetune a pair of low-rank adapters of a model, one serving as the text-generating model, and the other as the detector, so that a subtle watermark is embedded into the text generated by the first model and simultaneously optimized for detectability by the second. In this way, the watermarking strategy is fully learned end-to-end. This process imposes an optimization challenge, as balancing watermark robustness, naturalness, and task performance requires trade-offs. We discuss strategies on how to optimize this min-max objective and present results showing the effect of this modification to instruction finetuning.
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。