Efficiently Identifying Watermarked Segments in Mixed-Source Texts

ACL ARR 2025 February Submission4733 Authors

Abstract: Text watermarks in large language models (LLMs) are increasingly used to detect synthetic text, mitigating misuse cases like fake news and academic dishonesty. While existing watermarking detection techniques primarily focus on classifying entire documents as watermarked or not, they often neglect the common scenario of identifying individual watermark segments within longer, mixed-source documents. Drawing inspiration from plagiarism detection systems, we propose two novel methods for partial watermark detection. First, we develop a geometry cover detection framework aimed at determining whether there is a watermark segment in long text. Second, we introduce an adaptive online learning algorithm to pinpoint the precise location of watermark segments within the text. Evaluated on three popular watermarking techniques (KGW-Watermark, Unigram-Watermark, and Gumbel-Watermark), our approach achieves high accuracy, significantly outperforming baseline methods. Moreover, our framework is adaptable to other watermarking techniques, offering new insights for precise watermark detection.

Paper Type: Long

Research Area: Ethics, Bias, and Fairness

Research Area Keywords: Watermark, Online learning, LLM

Contribution Types: Model analysis & interpretability, Approaches low compute settings-efficiency, Theory

Languages Studied: English

Submission Number: 4733