# Efficiently Identifying Watermarked Segments in Mixed-Source Texts

arXiv: https://arxiv.org/abs/2410.03600 · HTML: https://mlsanity.com/paper/2410.03600/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security.
- Builds on 19 of its 38 references that are in the map.
- First posted on arXiv 4 Oct 2024.

## Placed in

- LLM safety and security / [Watermarking generated content and models](https://mlsanity.com/safety/watermarking-generated-content-and-models/)

## Builds on (most cited first, 19 of 19)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents](https://mlsanity.com/paper/1804.05685/) (2018)
- [Robust Distortion-free Watermarks for Language Models](https://mlsanity.com/paper/2307.15593/) (2023)
- [Provable Robust Watermarking for AI-Generated Text](https://mlsanity.com/paper/2306.17439/) (2023)
- [Undetectable Watermarks for Language Models](https://mlsanity.com/paper/2306.09194/) (2023)
- [On the Reliability of Watermarks for Large Language Models](https://mlsanity.com/paper/2306.04634/) (2023)
- [GPT detectors are biased against non-native English writers](https://mlsanity.com/paper/2304.02819/) (2023)
- [Unbiased Watermark for Large Language Models](https://mlsanity.com/paper/2310.10669/) (2023)
- [Strongly Adaptive Online Learning](https://mlsanity.com/paper/1502.07073/) (2015)
- [AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents](https://mlsanity.com/paper/2401.12963/) (2024)
- [Three Bricks to Consolidate Watermarks for Large Language Models](https://mlsanity.com/paper/2308.00113/) (2023)
- [Red Teaming Language Model Detectors with Language Models](https://mlsanity.com/paper/2305.19713/) (2023)
- [Optimal Dynamic Regret in Exp-Concave Online Learning](https://mlsanity.com/paper/2104.11824/) (2021)
- [An Optimal Reduction of TV-Denoising to Adaptive Online Learning](https://mlsanity.com/paper/2101.09438/) (2021)

## Built on by (most cited first, 6 of 6)

- [SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders](https://mlsanity.com/paper/2508.08211/) (2025)
- [Watermarking Degrades Alignment in Language Models: Analysis and Mitigation](https://mlsanity.com/paper/2506.04462/) (2025)
- [LLM Watermarking as Big Data Provenance: A Deployment-Oriented Systematization](https://mlsanity.com/paper/2607.10103/) (2026)
- [Stability-Aware Feature Design for Robust Watermark Detection in Machine-Generated Text](https://mlsanity.com/paper/2608.18102/) (2026)
- [Watermarkable Multi-Draft Speculative Sampling via Poisson Processes](https://mlsanity.com/paper/2609.21858/) (2026)
- [Anchor-ECC: Local Integrity Checking for Watermarked LLM Outputs via Error-Correcting Codes](https://mlsanity.com/paper/2609.38722/) (2026)

## Abstract (arXiv)

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. Our code is publicly available at https://github.com/XuandongZhao/llm-watermark-location