Beyond Heuristic Tuning: Power-Calibrated LLM Watermarking

• URL: http://arxiv.org/abs/2607.05694v1
• Date: Mon, 06 Jul 2026 23:23:14 GMT
• Title: Beyond Heuristic Tuning: Power-Calibrated LLM Watermarking
• Abstract summary: We develop a power-calibrated statistical framework that transforms watermark design into a guided optimization problem.<n>We derive practical parameter selection procedures that achieve optimal tradeoffs under constraints.
• Score: 9.521540932142498
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Logit-based watermarking is a widely used mechanism for identifying LLM generated content, yet its effectiveness is governed by a fundamental trade-off between detectability and semantic distortion. Existing analyses provide limited guidance for principled hyperparameter selection, leaving practical deployments reliant on heuristic tuning. In this work, we develop a power-calibrated statistical framework that establishes explicit quantitative relationships between watermark hyperparameters, detection power, and distortion. This characterization transforms watermark design into a guided optimization problem. Building on these results, we derive practical parameter selection procedures that achieve optimal tradeoffs under constraints. Extensive experiments across multiple language models and datasets validate the theory and demonstrate that the proposed framework consistently identifies Pareto-optimal points.

Related papers

• Preference Data Selection for Mitigating the Alignment Tax in Large Language Models [52.18310687523229]
  BALIGN is a balanced data selection strategy that mitigates catastrophic forgetting while optimizing alignment efficacy.<n>By aggregating three key data-centric features into a unified composite risk score, BALIGN systematically filters out high-risk preference samples.<n>Experiments on standard human preference datasets demonstrate that BALIGN strongly preserves foundational capabilities without compromising alignment gains.
  arXiv  Detail & Related papers  (2026-08-25T07:58:42Z)
• Evolution-Aware MSA Reasoning for Subsampling via Factor Graphs [55.715754117956514]
  Multiple Sequence Alignments provide protein language models with explicit evolutionary context.<n>MSA subsampling is unavoidable under limited token budgets.<n>We introduce AP-REASONER, which infers a fixed-budget MSA subset using factor-graph reasoning.
  arXiv  Detail & Related papers  (2026-07-24T13:55:21Z)
• PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks [3.815798234276803]
  PASA is a principled, robust, and distortion-free watermarking algorithm.<n>It embeds and detects a watermark at the semantic level.
  arXiv  Detail & Related papers  (2026-05-09T01:09:01Z)
• Functional Subspace Watermarking for Large Language Models [10.606696096012291]
  We propose a framework that anchors ownership signals into a low-dimensional functional backbone.<n>Our method achieves superior detection accuracy and statistical verifiability under multiple model attacks.
  arXiv  Detail & Related papers  (2026-03-19T11:44:34Z)
• Score-Guided Proximal Projection: A Unified Geometric Framework for Rectified Flow Editing [1.0312968200748118]
  Rectified Flow models achieve state-of-the-art generation quality, yet controlling them for precise tasks remains a challenge.<n>Current approaches bifurcate into inversion-based guidance, which suffers from "geometric locking"<n>We propose Score-Guided Proximal Projection, a unified framework that bridges the gap between deterministic optimization and contraction sampling.
  arXiv  Detail & Related papers  (2026-03-05T23:44:45Z)
• Optimizing Multi-Modal Trackers via Sensitivity-aware Regularized Tuning [112.12667472919723]
  This paper tackles the challenge of optimizing multi-modal trackers by effectively adapting the pre-trained models for RGB data.<n>Existing fine-tuning paradigms oscillate between excessive freedom and over-restriction, leading to a suboptimal plasticity-stability trade-off.<n>We propose a novel sensitivity-aware regularized tuning framework, which delicately refines the learning process by incorporating intrinsic parameter sensitivities.
  arXiv  Detail & Related papers  (2025-08-24T18:42:47Z)
• Continual Adaptation: Environment-Conditional Parameter Generation for Object Detection in Dynamic Scenarios [54.58186816693791]
  environments constantly change over time and space, posing significant challenges for object detectors trained based on a closed-set assumption.<n>We propose a new mechanism, converting the fine-tuning process to a specific- parameter generation.<n>In particular, we first design a dual-path LoRA-based domain-aware adapter that disentangles features into domain-invariant and domain-specific components.
  arXiv  Detail & Related papers  (2025-06-30T17:14:12Z)
• On the Convergence of DP-SGD with Adaptive Clipping [56.24689348875711]
  Gradient Descent with gradient clipping is a powerful technique for enabling differentially private optimization.<n>This paper provides the first comprehensive convergence analysis of SGD with quantile clipping (QC-SGD)<n>We show how QC-SGD suffers from a bias problem similar to constant-threshold clipped SGD but can be mitigated through a carefully designed quantile and step size schedule.
  arXiv  Detail & Related papers  (2024-12-27T20:29:47Z)
• 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)
• Towards Better Statistical Understanding of Watermarking LLMs [7.68488211412916]
  In this paper, we study the problem of watermarking large language models (LLMs) We consider the trade-off between model distortion and detection ability and it as a constrained optimization problem based on the green-red list of Kirchenbauer et al. We develop an online dual gradient ascent watermarking algorithm in light of this optimization formulation and prove its optimality between model distortion and detection ability.
  arXiv  Detail & Related papers  (2024-03-19T01:57:09Z)
• Ensemble Kalman Filtering Meets Gaussian Process SSM for Non-Mean-Field and Online Inference [47.460898983429374]
  We introduce an ensemble Kalman filter (EnKF) into the non-mean-field (NMF) variational inference framework to approximate the posterior distribution of the latent states. This novel marriage between EnKF and GPSSM not only eliminates the need for extensive parameterization in learning variational distributions, but also enables an interpretable, closed-form approximation of the evidence lower bound (ELBO) We demonstrate that the resulting EnKF-aided online algorithm embodies a principled objective function by ensuring data-fitting accuracy while incorporating model regularizations to mitigate overfitting.
  arXiv  Detail & Related papers  (2023-12-10T15:22:30Z)

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.