ACL Findings2026
LR-DWM: Efficient Watermarking for Diffusion Language Models
Ofek Raban, Gal Chechik, Ethan Fetaya
Abstract
Watermarking (WM) is a critical mechanism for detecting and attributing AI-generated content. Current WM methods for Large Language Models (LLMs) are predominantly tailored for autoregressive (AR) models: They rely on tokens being generated sequentially, and embed stable signals within the generated sequence based on the previously sampled text. Diffusion Language Models (DLMs) generate text via non-sequential iterative denoising, which requires significant modification to use WM methods designed for AR models. Recent work proposed to watermark DLMs by inverting the process when needed, but suffers significant computational or memory overhead.
We introduce Left-Right Diffusion Watermarking (LR-DWM), a scheme that biases the generated token based on both left and right neighbors, when they are available. LR-DWM incurs minimal runtime and memory overhead, remaining close to the non-watermarked baseline DLM while enabling reliable statistical detection under standard evaluation settings. Our results demonstrate that DLMs can be watermarked efficiently, achieving high detectability with negligible computational and memory overhead.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Large Language Diffusion Models cites Denoising Diffusion Probabilistic Models
- Large Language Diffusion Models cites Score-Based Generative Modeling through Stochastic Differential Equations
- Watermarking Diffusion Language Models cites Large Language Diffusion Models
- Watermarking Diffusion Language Models cites Denoising Diffusion Probabilistic Models
- Watermarking Diffusion Language Models cites A Watermark for Large Language Models
- dgMARK: Decoding-Guided Watermarking for Diffusion Language Models cites Large Language Diffusion Models
- dgMARK: Decoding-Guided Watermarking for Diffusion Language Models cites Watermarking Diffusion Language Models
- dgMARK: Decoding-Guided Watermarking for Diffusion Language Models cites Denoising Diffusion Probabilistic Models
- dgMARK: Decoding-Guided Watermarking for Diffusion Language Models cites A Watermark for Large Language Models
- dgMARK: Decoding-Guided Watermarking for Diffusion Language Models cites Score-Based Generative Modeling through Stochastic Differential Equations
- Score-Based Generative Modeling through Stochastic Differential Equations cites Denoising Diffusion Probabilistic Models
Cited by top-tier papers1
Builds on7
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- Score-Based Generative Modeling through Stochastic Differential EquationsYang Song, Jascha Sohl-Dickstein, Diederik P. Kingma, Abhishek Kumar et al.ICLR 2021 · 1,270 citations
- Large Language Diffusion ModelsShen Nie, Fengqi Zhu, Zebin You, Xiaolu Zhang et al.NeurIPS 2025 · 949 citations
- A Watermark for Large Language ModelsJohn Kirchenbauer, Jonas Geiping, Yuxin Wen, Jonathan Katz et al.ICML 2023 · 854 citations
- Watermarking Diffusion Language ModelsThibaud Gloaguen, Robin Staab, Nikola Jovanović, Martin VechevICLR 2026 · 13 citations
Related papers
- You Can Have a Second Chance: Unbiased and Multi-bit Watermarking for Diffusion Language Models with Regret-based RemaskingKe Yang, Dongyang Liang, Jing Yu, Shuguang Yuan et al.ACL 2026
- Your Text Encoder Can Be an Object-Level Watermarking ControllerNaresh Kumar Devulapally, Mingzhen Huang, Vishal Asnani, Shruti Agarwal et al.ICCV 2025 · 1 citation
- HeavyWater and SimplexWater: Distortion-free LLM Watermarks for Low-Entropy DistributionsDor Tsur, Carol Xuan Long, Claudio Mayrink Verdun, Sajani Vithana et al.NeurIPS 2025 · 9 citations
- Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive ApproachHaiyun He, Yepeng Liu, Ziqiao Wang, Yongyi Mao et al.NeurIPS 2025 · 26 citations
- Optimizing Watermarks for Large Language ModelsBram WoutersICML 2024 · 25 citations
