# Who Gets Flagged? The Pluralistic Evaluation Gap in AI Content Watermarking

arXiv: https://arxiv.org/abs/2604.13776 · HTML: https://mlsanity.com/paper/2604.13776/

## Key facts

- Cited by 2 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 35 of its 59 references that are in the map.
- First posted on arXiv 15 Apr 2026.

## 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, 30 of 35)

- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [StegaStamp: Invisible Hyperlinks in Physical Photographs](https://mlsanity.com/paper/1904.05343/) (2019)
- [Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale](https://mlsanity.com/paper/2211.03759/) (2022)
- [Language Model Tokenizers Introduce Unfairness Between Languages](https://mlsanity.com/paper/2305.15425/) (2023)
- [Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models](https://mlsanity.com/paper/2305.13707/) (2023)
- [Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust](https://mlsanity.com/paper/2305.20030/) (2023)
- [A Roadmap to Pluralistic Alignment](https://mlsanity.com/paper/2402.05070/) (2024)
- [Does Object Recognition Work for Everyone?](https://mlsanity.com/paper/1906.02659/) (2019)
- [Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models](https://mlsanity.com/paper/2404.04956/) (2024)
- [Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances](https://mlsanity.com/paper/2410.18775/) (2024)
- [Benchmarking Vision Language Models for Cultural Understanding](https://mlsanity.com/paper/2407.10920/) (2024)
- [The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselines](https://mlsanity.com/paper/1803.10609/) (2018)
- [Proactive Detection of Voice Cloning with Localized Watermarking](https://mlsanity.com/paper/2401.17264/) (2024)
- [Mark My Words: Analyzing and Evaluating Language Model Watermarks](https://mlsanity.com/paper/2312.00273/) (2023)
- [SoK: Watermarking for AI-Generated Content](https://mlsanity.com/paper/2411.18479/) (2024)
- [WavMark: Watermarking for Audio Generation](https://mlsanity.com/paper/2308.12770/) (2023)
- ['Person' == Light-skinned, Western Man, and Sexualization of Women of Color: Stereotypes in Stable Diffusion](https://mlsanity.com/paper/2310.19981/) (2023)
- [Can Watermarks Survive Translation? On the Cross-lingual Consistency of Text Watermark for Large Language Models](https://mlsanity.com/paper/2402.14007/) (2024)
- [WaterBench: Towards Holistic Evaluation of Watermarks for Large Language Models](https://mlsanity.com/paper/2311.07138/) (2023)
- [SynthID-Image: Image watermarking at internet scale](https://mlsanity.com/paper/2510.09263/) (2025)
- [PostMark: A Robust Blackbox Watermark for Large Language Models](https://mlsanity.com/paper/2406.14517/) (2024)
- [AudioMarkBench: Benchmarking Robustness of Audio Watermarking](https://mlsanity.com/paper/2406.06979/) (2024)
- [Towards Geographic Inclusion in the Evaluation of Text-to-Image Models](https://mlsanity.com/paper/2405.04457/) (2024)
- [A Comprehensive Real-World Assessment of Audio Watermarking Algorithms: Will They Survive Neural Codecs?](https://mlsanity.com/paper/2505.19663/) (2025)
- [SoK: How Robust is Audio Watermarking in Generative AI models?](https://mlsanity.com/paper/2503.19176/) (2025)
- [Watermark under Fire: A Robustness Evaluation of LLM Watermarking](https://mlsanity.com/paper/2411.13425/) (2024)
- ["It's not a representation of me": Examining Accent Bias and Digital Exclusion in Synthetic AI Voice Services](https://mlsanity.com/paper/2504.09346/) (2025)
- [Watermarking Without Standards Is Not AI Governance](https://mlsanity.com/paper/2505.23814/) (2025)
- [Topic-Based Watermarks for Large Language Models](https://mlsanity.com/paper/2404.02138/) (2024)
- [Does lossy image compression affect racial bias within face recognition?](https://mlsanity.com/paper/2208.07613/) (2022)

## Built on by (most cited first, 2 of 2)

- [Auditing Cross-Lingual Fairness in Language Model Watermarking](https://mlsanity.com/paper/2608.20047/) (2026)
- [Watermarks Without Verification: AI Text Watermarking After the EU AI Act](https://mlsanity.com/paper/2609.09604/) (2026)

## Abstract (arXiv)

Watermarking is becoming the default mechanism for AI content authentication, with governance policies and frameworks referencing it as infrastructure for content provenance. Yet across text, image, and audio modalities, watermark signal strength, detectability, and robustness depend on statistical properties of the content itself, properties that vary systematically across languages, cultural visual traditions, and demographic groups. We examine how this content dependence creates modality-specific pathways to bias. Reviewing the major watermarking benchmarks across modalities, we find that, with one exception, none report performance across languages, cultural content types, or population groups. To address this, we propose three concrete evaluation dimensions for pluralistic watermark benchmarking: cross-lingual detection parity, culturally diverse content coverage, and demographic disaggregation of detection metrics. We argue that watermarking is part of the pluralistic alignment pipeline and should be held to the same evaluation standards. We connect this to governance frameworks currently mandating watermarking deployment without requiring fairness evaluation. Our position is that evaluation must precede deployment, and that the same bias auditing requirements applied to AI models should extend to the verification layer.