Alignment Imprint: Zero-Shot AI-Generated Text Detection via Provable Preference Discrepancy

• URL: http://arxiv.org/abs/2604.16923v1
• Date: Sat, 18 Apr 2026 09:12:24 GMT
• Title: Alignment Imprint: Zero-Shot AI-Generated Text Detection via Provable Preference Discrepancy
• Abstract summary: We show that modern Large Language Models (LLMs) undergo alignment, leaving a measurable distributional imprint.<n>To mitigate the instability in high-entropy regions, we introduce Log-likelihood Alignment Preference Discrepancy (LAPD)<n>LAPD is a standardized information-weighted statistic based on alignment imprint.
• Score: 51.887915969023965
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Detecting AI-generated text is an important but challenging problem. Existing likelihood-based detection methods are often sensitive to content complexity and may exhibit unstable performance. In this paper, our key insight is that modern Large Language Models (LLMs) undergo alignment (including fine-tuning and preference tuning), leaving a measurable distributional imprint. We theoretically derive this imprint by abstracting the alignment process as a sequence of constrained optimization steps, showing that the log-likelihood ratio can naturally decompose into implicit instructional biases and preference rewards. We refer to this quantity as the Alignment Imprint. Furthermore, to mitigate the instability in high-entropy regions, we introduce Log-likelihood Alignment Preference Discrepancy (LAPD), a standardized information-weighted statistic based on alignment imprint. We provide statistical guarantee that alignment-based statistics dominate Fast-DetectGPT in performance. We also theoretically show that LAPD strictly improves the unweighted alignment scores when the aligned and base models are close in distribution. Extensive experiments show that LAPD achieves an improvement 45.82% relative to the strongest existing baselines, yielding large and consistent gains across all settings.

Related papers

• PURA: Provably Unbiased and Robust Multi-Bit Watermarking for AI-Generated Text Attribution [83.66032773976904]
  We present PURA, a provably unbiased and robust multi-bit watermarking method for text attribution.<n>Instead of perturbing token probabilities directly, PURA embeds payloads in the latent sampling space via keyed inverse transform sampling.<n>We show that PURA substantially outperforms existing unbiased baselines in the high-payload regime.
  arXiv  Detail & Related papers  (2026-08-23T04:44:27Z)
• Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints [12.090394120714402]
  We propose textitDistribution Provenance Audit (DPA), a post-hoc framework for auditing data IP infringement in Large Language Models (LLMs)<n>DPA is grounded in a critical insight: regardless of fine-tuning tactics to evade provenance, the practical necessity of maintaining utility constrains the model to preserve the fundamental intersection of semantic substance and lexical form.
  arXiv  Detail & Related papers  (2026-08-03T12:35:51Z)
• DRIFT: Refining Instruction Data via On-Policy Data Attribution [24.426971578185633]
  Supervised Fine-Tuning (SFT) dictates the capability of Large Language Models (LLMs)<n>Existing data curation methods excel at accelerating training under constrained budgets, but are less suited to elevating the capability upper bound.<n>We propose DRIFT to refine the data distribution toward instances most capable of improving the final model.
  arXiv  Detail & Related papers  (2026-06-16T07:21:49Z)
• Hybrid Robustness Verification for Spatio-Temporal Neural Networks [19.026662893450425]
  Existing verification methods rely on overly conservative approximations or incur prohibitive computational costs.<n>In practice, adversarial perturbations exhibit structured spatial and temporal correlations, constrained to lower-dimensional, semantically meaningful subspaces.<n>We study robustness verification 3D CNNs processing video inputs, targeting applications in action recognition (UCF-101), autonomous driving (Udacity), medical imaging (MedMNIST)
  arXiv  Detail & Related papers  (2026-06-08T17:06:51Z)
• Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data [55.84428098924793]
  We propose Constrained Uniform Top-K Sampling (CUTS), a parameter-free decoding strategy enforcing structure-preserving exploration.<n>We integrate this into Mixed-CUTS, a training framework synergizing exploitative and exploratory rollouts to amplify intra-group advantage variance.<n> Notably, Mixed-CUTS improves Pass@1 accuracy on the challenging AIME25 benchmark by up to 15.1% over standard GRPO.
  arXiv  Detail & Related papers  (2026-04-20T16:43:28Z)
• Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment [13.463606100715504]
  Large language models are vulnerable to attacks that disguise harmful intent.<n>This vulnerability stems from shallow alignment mechanisms that lack deep reasoning.<n>We propose enhancing alignment through reasoning-aware post-training.
  arXiv  Detail & Related papers  (2026-02-24T20:30:51Z)
• Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignment [16.352863226512984]
  Test-time adaptation (TTA) enhances the zero-shot robustness under distribution shifts by leveraging unlabeled test data during inference.<n>Most methods rely on backpropagation or iterative optimization, which limits scalability and hinders real-time deployment.<n>We propose ADAPT, an Advanced Distribution-Aware and back propagation-free Test-time adaptation method.
  arXiv  Detail & Related papers  (2025-08-21T13:42:49Z)
• Normalized Attention Guidance: Universal Negative Guidance for Diffusion Models [57.20761595019967]
  We present Normalized Attention Guidance (NAG), an efficient, training-free mechanism that applies extrapolation in attention space with L1-based normalization and refinement.<n>NAG restores effective negative guidance where CFG collapses while maintaining fidelity.<n>NAG generalizes across architectures (UNet, DiT), sampling regimes (few-step, multi-step), and modalities (image, video)
  arXiv  Detail & Related papers  (2025-05-27T13:30:46Z)
• PIPA: Preference Alignment as Prior-Informed Statistical Estimation [57.24096291517857]
  We introduce Pior-Informed Preference Alignment (PIPA), a unified, RL-free probabilistic framework.<n> PIPA accommodates both paired and unpaired data, as well as answer and step-level annotations.<n>By integrating different types of prior information, we developed two variations of PIPA: PIPA-M and PIPA-N.
  arXiv  Detail & Related papers  (2025-02-09T04:31:30Z)
• Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization [78.82586283794886]
  $chi2$-Preference Optimization ($chi$PO) is an efficient offline alignment algorithm provably robust to overoptimization.<n>$chi$PO implements the principle of pessimism in the face of uncertainty via regularization.<n>$chi$PO's simplicity and strong guarantees make it the first practical and general-purpose offline alignment algorithm provably robust to overoptimization.
  arXiv  Detail & Related papers  (2024-07-18T11:08:40Z)
• Uncertainty Aware Learning for Language Model Alignment [97.36361196793929]
  We propose uncertainty-aware learning (UAL) to improve the model alignment of different task scenarios. We implement UAL in a simple fashion -- adaptively setting the label smoothing value of training according to the uncertainty of individual samples. Experiments on widely used benchmarks demonstrate that our UAL significantly and consistently outperforms standard supervised fine-tuning.
  arXiv  Detail & Related papers  (2024-06-07T11:37:45Z)
• Sequential Kernelized Independence Testing [77.237958592189]
  We design sequential kernelized independence tests inspired by kernelized dependence measures.<n>We demonstrate the power of our approaches on both simulated and real data.
  arXiv  Detail & Related papers  (2022-12-14T18:08:42Z)

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.