# Making Open-Source Text LLM Watermarks Durable Against Merging

arXiv: https://arxiv.org/abs/2607.20435 · HTML: https://mlsanity.com/paper/2607.20435/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security.
- Builds on 29 of its 43 references that are in the map.
- First posted on arXiv 11 May 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, 29 of 29)

- [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)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models](https://mlsanity.com/paper/2309.12284/) (2023)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch](https://mlsanity.com/paper/2311.03099/) (2023)
- [Can AI-Generated Text be Reliably Detected?](https://mlsanity.com/paper/2303.11156/) (2023)
- [Robust Distortion-free Watermarks for Language Models](https://mlsanity.com/paper/2307.15593/) (2023)
- [OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data](https://mlsanity.com/paper/2410.01560/) (2024)
- [Arcee's MergeKit: A Toolkit for Merging Large Language Models](https://mlsanity.com/paper/2403.13257/) (2024)
- [On the Reliability of Watermarks for Large Language Models](https://mlsanity.com/paper/2306.04634/) (2023)
- [Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks](https://mlsanity.com/paper/2312.06795/) (2023)
- [Watermark Stealing in Large Language Models](https://mlsanity.com/paper/2402.19361/) (2024)
- [On the Learnability of Watermarks for Language Models](https://mlsanity.com/paper/2312.04469/) (2023)
- [FuseChat: Knowledge Fusion of Chat Models](https://mlsanity.com/paper/2408.07990/) (2024)
- [No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices](https://mlsanity.com/paper/2402.16187/) (2024)
- [Can Watermarks Survive Translation? On the Cross-lingual Consistency of Text Watermark for Large Language Models](https://mlsanity.com/paper/2402.14007/) (2024)
- [GaussMark: A Practical Approach for Structural Watermarking of Language Models](https://mlsanity.com/paper/2501.13941/) (2025)
- [Towards Watermarking of Open-Source LLMs](https://mlsanity.com/paper/2502.10525/) (2025)
- [LLM Fingerprinting via Semantically Conditioned Watermarks](https://mlsanity.com/paper/2505.16723/) (2025)
- [PRO: Enabling Precise and Robust Text Watermark for Open-Source LLMs](https://mlsanity.com/paper/2510.23891/) (2025)

## Abstract (arXiv)

Open-source LLMs (OSMs)arereaching near state-of-the-art performance, prompting prior works to trace the text they generate by embedding text watermarking algorithms directly into their weights. Yet, OSMs are subject to post-training modifications, which has been shown to remove the watermark. Model merging in particular, a prominent method used for combining expert knowledge and preventing catastrophic forgetting, strongly removes such OSM watermarks. A key question is how to enable OSM watermarks that survive subsequent merging. In this work, we show for the first time how to design an OSM watermark that is durable against model merging. We propose Merge-Adversarial Training, an adversarial training algorithm to distill text watermarks into model weights while being robust to subsequent model merging. Our approach consistently outperforms all baselines (e.g. with SLERP up to +51 percentage points (pp) TPR@1%FPR with +25 pp on average) while preserving downstream capabilities. We also for the first time evaluate OSM watermarks against realistic merge scenarios, representing common use-cases such as combining expert capabilities or preventing catastrophic forgetting, and with 3 prominent merging algorithms. More broadly, our findings suggest that adversarial training is a reliable approach for increasing OSM watermark durability against post-training modifications.