Constitution-Guided Watermarking

Key points

• However, its desired properties can conflict (\ie stronger watermark signals can degrade text quality), while designs that resist editing may also facilitate forgery.1
• To allow flexible and adaptable designs, we introduce Constitution-Guided Watermarking, a framework that selects request-appropriate trade-offs from provider requirements, listed as natural-language principles.1
• Offline, a pretrained reasoning agent examines constitutional rules alongside watermark implementations and iteratively refines rule-specific configurations using empirical feedback.1
• In a proof-of-concept evaluation using KGW and a five-rule constitution, our framework selects configurations responsive to provider priorities and improves post-paraphrase detection on robustness-prioritized requests by up to $14$ percentage points over fixed configurations, while matching or exceeding all baselines in aggregate quality and clean detection at a nominal $0.1%$ false-positive rate.1

Sources (1)

• [1]Constitution-Guided Watermarking
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 06:50 AM

  Watermarking enables language model providers to identify text generated by their models.

  However, its desired properties can conflict (\ie stronger watermark signals can degrade text quality), while designs that resist editing may also facilitate forgery.

Extractive summary: sentences quoted from the sources.