cs.CRNov 1, 2026

Query-efficient scan-and-search watermark localization

Authors: Liyuan Wang, Xinsong Ma, Ziye Ma

Organizations: Department of Computer Science City University of Hong Kong

Abstract

Recently, the detection of AI-generated content has been of particular importance in various fields of our society. For accountability purposes, many large language models (LLMs) have implicitly watermarked their outputs. Localizing such watermarks requires a piece of text to undergo an additional verification process. Existing localization methods typically rely on dense token-level scoring, making verification costly even when an LLM-generated watermark only sparsely appears. To tackle this problem, we design a new adaptive allocation strategy that first maintains broad document coverage and then progressively concentrates the detection budget on regions that exhibit stronger watermark evidence or are more likely to contain watermarked content. We then transform the statistical signals from the selected regions into e-values and employ the proposed token-weighted e-BH procedure to determine the localized watermark regions. The resulting framework is called BELL (Budgeted E-evidence Localization for LLM Watermarks). Theoretically, BELL can control the token-weighted false discovery rate (FDR) without independence assumptions across regions. Finally, extensive experimental results demonstrate that BELL consistently outperforms competing methods across multiple LLMs, datasets, and watermarking schemes.

Figures & tables

Appendix figures & tables14 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Optimal Watermark Localization in Mixed-Source Large Language Model Texts

    Aug 14, 2026Jose H. Blanchet, T. Tony Cai, Xiang Li +3LLM WatermarkingRobust Watermarking

  2. Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks

    Aug 13, 2026Xiaoyan Feng, Yanjun Zhang, He Zhang +2Data ProvenanceLLM Watermarking

  3. AutoMark: Enabling Autoresearch to Discover Better LLM Watermarks

    Sep 29, 2026Thibaud Gloaguen, Robin Staab, Martin VechevText WatermarkingLLM Watermarking