Watermarking of large language models (LLMs) generation embeds an imperceptible statistical pattern within texts, making it algorithmically detectable. Watermarking is a promising method for addressing potential harm and biases from LLMs, as it enables traceability, accountability, and detection of manipulated content, helping to mitigate unintended consequences. However, for open-source models, watermarking faces two major challenges: (i) incompatibility with fine-tuned models, and (ii) vulnerability to fine-tuning attacks. In this work, we propose WAPITI, a new method that transfers watermarking from base models to fine-tuned models through parameter integration. To the best of our knowledge, we propose the first watermark for fine-tuned open-source LLMs that preserves their fine-tuned capabilities. Furthermore, our approach offers an effective defense against fine-tuning attacks. We test our method on various model architectures and watermarking strategies. Results demonstrate that our method can successfully inject watermarks and is highly compatible with fine-tuned models. Additionally, we offer an in-depth analysis of how parameter editing influences the watermark strength and overall capabilities of the resulting models.
@article{arxiv.2410.06467,
title = {WAPITI: A Watermark for Finetuned Open-Source LLMs},
author = {Lingjie Chen and Ruizhong Qiu and Siyu Yuan and Zhining Liu and Tianxin Wei and Hyunsik Yoo and Zhichen Zeng and Deqing Yang and Hanghang Tong},
journal= {arXiv preprint arXiv:2410.06467},
year = {2024}
}