SimMark: A Robust Sentence-Level Similarity-Based Watermarking Algorithm for Large Language Models

ACL ARR 2025 May Submission4943 Authors

Abstract: The widespread adoption of large language models (LLMs) necessitates reliable methods to detect LLM-generated text. We introduce SimMark, a robust sentence-level watermarking algorithm that makes LLM's outputs traceable without requiring access to model internals, making it compatible with both open and API-based LLMs. By leveraging the similarity of semantic sentence embeddings combined with rejection sampling to embed detectable statistical patterns imperceptible to humans, and employing a soft counting mechanism, SimMark achieves robustness against paraphrasing attacks. Experimental results demonstrate that SimMark sets a new benchmark for robust watermarking of LLM-generated content, surpassing prior sentence-level watermarking techniques in robustness, sampling efficiency, and applicability across diverse domains, all while maintaining the text quality and fluency.

Paper Type: Long

Research Area: Language Modeling

Research Area Keywords: safety and alignment, security and privacy, robustness, applications

Languages Studied: English

Submission Number: 4943