# Yet Another Watermark for Large Language Models

arXiv: https://arxiv.org/abs/2509.12574 · HTML: https://mlsanity.com/paper/2509.12574/

## 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 14 of its 23 references that are in the map.
- First posted on arXiv 16 Sep 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, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus](https://mlsanity.com/paper/2104.08758/) (2021)
- [Who Wrote this Code? Watermarking for Code Generation](https://mlsanity.com/paper/2305.15060/) (2023)
- [On the Learnability of Watermarks for Language Models](https://mlsanity.com/paper/2312.04469/) (2023)
- [An Entropy-based Text Watermarking Detection Method](https://mlsanity.com/paper/2403.13485/) (2024)
- [Semantic-Preserving Linguistic Steganography by Pivot Translation and Semantic-Aware Bins Coding](https://mlsanity.com/paper/2203.03795/) (2022)
- [Autoregressive Linguistic Steganography Based on BERT and Consistency Coding](https://mlsanity.com/paper/2203.13972/) (2022)
- [Generative Model Watermarking Based on Human Visual System](https://mlsanity.com/paper/2209.15268/) (2022)
- [TokenMark: A Modality-Agnostic Watermark for Pre-trained Transformers](https://mlsanity.com/paper/2403.05842/) (2024)

## Abstract (arXiv)

Existing watermarking methods for large language models (LLMs) mainly embed watermark by adjusting the token sampling prediction or post-processing, lacking intrinsic coupling with LLMs, which may significantly reduce the semantic quality of the generated marked texts. Traditional watermarking methods based on training or fine-tuning may be extendable to LLMs. However, most of them are limited to the white-box scenario, or very time-consuming due to the massive parameters of LLMs. In this paper, we present a new watermarking framework for LLMs, where the watermark is embedded into the LLM by manipulating the internal parameters of the LLM, and can be extracted from the generated text without accessing the LLM. Comparing with related methods, the proposed method entangles the watermark with the intrinsic parameters of the LLM, which better balances the robustness and imperceptibility of the watermark. Moreover, the proposed method enables us to extract the watermark under the black-box scenario, which is computationally efficient for use. Experimental results have also verified the feasibility, superiority and practicality. This work provides a new perspective different from mainstream works, which may shed light on future research.