Efficient Online LLM Watermark Detection via Rao-Blackwellized E-Processes

arXiv:2607.21958 · stat.ML, cs.LG · Submitted 2026-07-24 · Read on arXiv

Lu Luo, Dandan Mo, Chengdong Xu, Ting Li, Jinhan Xie, Huiqiong Li, Niansheng Tang

stat.ML, cs.LG

Submitted: 2026-07-24

Comments: 25 pages, 3 figures

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Consistency — 3× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 3× in this paper · explained in 6 episodes
• Provenance — 3× in this paper · explained in 4 episodes
• Theoretical Guarantees — 3× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Exchangeability — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 3 episodes
• Score Function — 1× in this paper · explained in 4 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• GPT-4 Technical Report
• Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature
• Sparks of Artificial General Intelligence: Early experiments with GPT-4
• Online Detection of LLM-Generated Texts via Sequential Hypothesis Testing by Betting
• Rao-Blackwellized e-variables
• The Llama 3 Herd of Models
• Unbiased Watermark for Large Language Models
• Towards Anytime-Valid Statistical Watermarking
• DeepSeek-V3 Technical Report
• Raidar: geneRative AI Detection viA Rewriting
• WebGPT: Browser-assisted question-answering with human feedback
• Online LLM watermark detection via e-processes
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• ReAct: Synergizing Reasoning and Acting in Language Models
• OPT: Open Pre-trained Transformer Language Models
• AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guarantees
• Detecting LLM-Generated Text with Performance Guarantees

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing
• Online Conformal Prediction for Non-Exchangeable Panel Data
• Deep Time-Series Forecasting in 10 Years: A Survey