# Improved Unbiased Watermark for Large Language Models

arXiv: https://arxiv.org/abs/2502.11268 · HTML: https://mlsanity.com/paper/2502.11268/

## Key facts

- Cited by 17 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 12 of its 19 references that are in the map.
- First posted on arXiv 16 Feb 2025.

## 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, 12 of 12)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense](https://mlsanity.com/paper/2303.13408/) (2023)
- [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)
- [A Watermark for Order-Agnostic Language Models](https://mlsanity.com/paper/2410.13805/) (2024)
- [Distortion-free Watermarks are not Truly Distortion-free under Watermark Key Collisions](https://mlsanity.com/paper/2406.02603/) (2024)

## Built on by (most cited first, 17 of 17)

- [In-Context Watermarks for Large Language Models](https://mlsanity.com/paper/2505.16934/) (2025)
- [Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption](https://mlsanity.com/paper/2510.18333/) (2025)
- [An Ensemble Framework for Unbiased Language Model Watermarking](https://mlsanity.com/paper/2509.24043/) (2025)
- [Analyzing and Evaluating Unbiased Language Model Watermark](https://mlsanity.com/paper/2509.24048/) (2025)
- [Leave No TRACE: Black-box Detection of Copyrighted Dataset Usage in Large Language Models via Watermarking](https://mlsanity.com/paper/2510.02962/) (2025)
- [A Unified Framework for LLM Watermarks](https://mlsanity.com/paper/2602.06754/) (2026)
- [MC2Mark: Distortion-Free Multi-Bit Watermarking for Long Messages](https://mlsanity.com/paper/2602.14030/) (2026)
- [Can You Detect the Difference?](https://mlsanity.com/paper/2507.10475/) (2025)
- [Every Bit, Everywhere, All at Once: A Binomial Multibit LLM Watermark](https://mlsanity.com/paper/2605.11653/) (2026)
- [Robust LLM Watermarking with Minimal Semantic Distortion for IP Protection](https://mlsanity.com/paper/2605.23175/) (2026)
- [Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks](https://mlsanity.com/paper/2608.12713/) (2026)
- [WorldCup Sampling for Multi-bit LLM Watermarking](https://mlsanity.com/paper/2602.01752/) (2026)
- [Optimal Multi-bit Generative Watermarking Schemes Under Worst-Case False-Alarm Constraints](https://mlsanity.com/paper/2604.08759/) (2026)
- [Learning to Follow In-Context Watermark Instructions via Self-Distillation](https://mlsanity.com/paper/2608.29030/) (2026)
- [TTMark: Pairwise Distortion-Free Watermarking Beyond Single-Token Entropy](https://mlsanity.com/paper/2609.36372/) (2026)
- [Grammar-Guided Code Watermarking with Green Temperature](https://mlsanity.com/paper/2610.05323/) (2026)
- [ByteMark: A Unified Byte-Level Watermark for Detection Across Language Models](https://mlsanity.com/paper/2610.14427/) (2026)

## Abstract (arXiv)

As artificial intelligence surpasses human capabilities in text generation, the necessity to authenticate the origins of AI-generated content has become paramount. Unbiased watermarks offer a powerful solution by embedding statistical signals into language model-generated text without distorting the quality. In this paper, we introduce MCmark, a family of unbiased, Multi-Channel-based watermarks. MCmark works by partitioning the model's vocabulary into segments and promoting token probabilities within a selected segment based on a watermark key. We demonstrate that MCmark not only preserves the original distribution of the language model but also offers significant improvements in detectability and robustness over existing unbiased watermarks. Our experiments with widely-used language models demonstrate an improvement in detectability of over 10% using MCmark, compared to existing state-of-the-art unbiased watermarks. This advancement underscores MCmark's potential in enhancing the practical application of watermarking in AI-generated texts.