Towards Anytime-Valid Statistical Watermarking

• URL: http://arxiv.org/abs/2602.17608v1
• Date: Thu, 19 Feb 2026 18:32:26 GMT
• Title: Towards Anytime-Valid Statistical Watermarking
• Authors: Baihe Huang, Eric Xu, Kannan Ramchandran, Jiantao Jiao, Michael I. Jordan,
• Abstract summary: We develop the first e-value-based watermarking framework, Anchored E-Watermarking, that unifies optimal sampling with anytime-valid inference.<n>Our framework can significantly enhance sample efficiency, reducing the average token budget required for detection by 13-15% relative to state-of-the-art baselines.
• Score: 63.02116925616554
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The proliferation of Large Language Models (LLMs) necessitates efficient mechanisms to distinguish machine-generated content from human text. While statistical watermarking has emerged as a promising solution, existing methods suffer from two critical limitations: the lack of a principled approach for selecting sampling distributions and the reliance on fixed-horizon hypothesis testing, which precludes valid early stopping. In this paper, we bridge this gap by developing the first e-value-based watermarking framework, Anchored E-Watermarking, that unifies optimal sampling with anytime-valid inference. Unlike traditional approaches where optional stopping invalidates Type-I error guarantees, our framework enables valid, anytime-inference by constructing a test supermartingale for the detection process. By leveraging an anchor distribution to approximate the target model, we characterize the optimal e-value with respect to the worst-case log-growth rate and derive the optimal expected stopping time. Our theoretical claims are substantiated by simulations and evaluations on established benchmarks, showing that our framework can significantly enhance sample efficiency, reducing the average token budget required for detection by 13-15% relative to state-of-the-art baselines.

Related papers

• Observationally Informed Adaptive Causal Experimental Design [55.998153710215654]
  We propose Active Residual Learning, a new paradigm that leverages the observational model as a foundational prior.<n>This approach shifts the experimental focus from learning target causal quantities from scratch to efficiently estimating the residuals required to correct observational bias.<n> Experiments on synthetic and semi-synthetic benchmarks demonstrate that R-Design significantly outperforms baselines.
  arXiv  Detail & Related papers  (2026-03-04T06:52:37Z)
• Improve the Trade-off Between Watermark Strength and Speculative Sampling Efficiency for Language Models [18.988823703120865]
  Speculative sampling accelerates inference, with efficiency improving as the acceptance rate increases.<n>Recent work reveals a fundamental trade-off: higher watermark strength reduces acceptance, preventing their simultaneous achievement.<n>We introduce a measure of watermark strength that governs statistical detectability and is maximized when tokens are deterministic functions of pseudorandom numbers.
  arXiv  Detail & Related papers  (2026-02-01T20:30:59Z)
• Conformal Prediction Algorithms for Time Series Forecasting: Methods and Benchmarking [0.0]
  Time series temporal dependencies violate the core assumption of data exchangeability.<n>This paper critically examines the main categories of algorithmic solutions designed to address this conflict.<n>We use AutoARIMA as the base forecaster on a large-scale monthly sales dataset.
  arXiv  Detail & Related papers  (2026-01-26T14:15:08Z)
• Optimal Detection for Language Watermarks with Pseudorandom Collision [28.84134119819056]
  We introduce a statistical framework that captures structure through a hierarchical two-layer partition.<n>At its core is the concept of minimal units -- the smallest groups treatable as independent across units while permitting dependence within.<n>Applying to Gumbel-max and inverse-transform watermarks, our framework produces closed-form optimal rules.
  arXiv  Detail & Related papers  (2025-10-24T20:21:52Z)
• Analyzing and Evaluating Unbiased Language Model Watermark [62.982950935139534]
  We introduce UWbench, the first open-source benchmark dedicated to the principled evaluation of unbiased watermarking methods.<n>Our framework combines theoretical and empirical contributions.<n>We establish a three-axis evaluation protocol: unbiasedness, detectability, and robustness, and show that token modification attacks provide more stable robustness assessments than paraphrasing-based methods.
  arXiv  Detail & Related papers  (2025-09-28T19:46:01Z)
• Principled Input-Output-Conditioned Post-Hoc Uncertainty Estimation for Regression Networks [1.4671424999873808]
  Uncertainty is critical in safety-sensitive applications but is often omitted from off-the-shelf neural networks due to adverse effects on predictive performance.<n>We propose a theoretically grounded framework for post-hoc uncertainty estimation in regression tasks by fitting an auxiliary model to both original inputs and frozen model outputs.
  arXiv  Detail & Related papers  (2025-06-01T09:13:27Z)
• Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approach [53.32564762183639]
  We introduce a novel, unified theoretical framework for watermarking Large Language Models (LLMs)<n>Our approach aims to maximize detection performance while maintaining control over the worst-case false positive rate (FPR) and distortion on text quality.<n>We propose a distortion-free, distribution-adaptive watermarking algorithm (DAWA) that leverages a surrogate model for model-agnosticism and efficiency.
  arXiv  Detail & Related papers  (2024-10-03T18:28:10Z)
• Conformal Generative Modeling with Improved Sample Efficiency through Sequential Greedy Filtering [55.15192437680943]
  Generative models lack rigorous statistical guarantees for their outputs.<n>We propose a sequential conformal prediction method producing prediction sets that satisfy a rigorous statistical guarantee.<n>This guarantee states that with high probability, the prediction sets contain at least one admissible (or valid) example.
  arXiv  Detail & Related papers  (2024-10-02T15:26:52Z)
• Leveraging Unlabeled Data to Predict Out-of-Distribution Performance [63.740181251997306]
  Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions. In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data. We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples.
  arXiv  Detail & Related papers  (2022-01-11T23:01:12Z)
• A Distributionally Robust Approach to Fair Classification [17.759493152879013]
  We propose a robust logistic regression model with an unfairness penalty that prevents discrimination with respect to sensitive attributes such as gender or ethnicity. This model is equivalent to a tractable convex optimization problem if a Wasserstein ball centered at the empirical distribution on the training data is used to model distributional uncertainty. We demonstrate that the resulting classifier improves fairness at a marginal loss of predictive accuracy on both synthetic and real datasets.
  arXiv  Detail & Related papers  (2020-07-18T22:34:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.