Adaptive auditing of AI systems with anytime-valid guarantees

• URL: http://arxiv.org/abs/2605.07002v1
• Date: Thu, 07 May 2026 22:33:48 GMT
• Title: Adaptive auditing of AI systems with anytime-valid guarantees
• Abstract summary: We introduce a hypothesis testing framework from two 'dueling' perspectives.<n>We formalize the auditor as conducting 'testing by betting', which translates into simultaneous e-processes for testing the dueling null hypotheses.<n>Our proposed testing procedures maintain anytime-valid type-I error control, outperform pre-specified testing methods, and can reach statistically rigorous conclusions sometimes with as few as 20 observations.
• Score: 8.752768302067638
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A major bottleneck in characterizing the failure modes of generative AI systems is the cost and time of annotation and evaluation. Consequently, adaptive testing paradigms have gained popularity, where one opportunistically decides which cases and how many to annotate based on past results. While this framework is highly practical, its extreme flexibility makes it difficult to draw statistically rigorous conclusions, as it violates classical assumptions: the number of observations is typically limited (often 10 to 50 cases) and decisions regarding sampling and stopping are made in the midst of data collection rather than based a pre-specified rule. To characterize what statistical inferences can be drawn from highly adaptive audits, we introduce a hypothesis testing framework from two 'dueling' perspectives: (i) the model's null that asserts there is no failure mode with performance below a target threshold versus (ii) the auditor's null that asserts they have a sampling strategy that will uncover a failure mode. Leveraging Safe Anytime-Valid Inference (SAVI), we formalize the auditor as conducting 'testing by betting', which translates into simultaneous e-processes for testing the dueling null hypotheses. Furthermore, if the auditor is sufficiently powerful, we prove that these two hypotheses are asymptotically inverses of each other, in that passage of a stringent audit does in fact certify the AI system as being globally robust. Empirically, we demonstrate that our proposed testing procedures maintain anytime-valid type-I error control, outperform pre-specified testing methods, and can reach statistically rigorous conclusions sometimes with as few as 20 observations.

Related papers

• CITE: Anytime-Valid Statistical Inference in LLM Self-Consistency [10.34950275095264]
  We study anytime-valid certification of a prespecified target answer as unique mode of the model's response distribution.<n>We propose the Certification by Intersection-union Testing with E-processes (CITE) algorithm, which provably controls false certification at any prescribed level.<n>We also prove an category-set-size-free stopping-time rate, establish matching minimax lower bounds up to constants in the main regime, and extend the construction to confidence-weighted voting.
  arXiv  Detail & Related papers  (2026-05-07T08:41:51Z)
• Sequential Audit Sampling with Statistical Guarantees [6.101839518775968]
  This study formulates audit sampling with additional, sequentially collected items as a sequential testing problem for a finite population under sampling without replacement.<n>We define null and alternative hypotheses in terms of a deviation rate, specify stopping and decision rules, and formulate exact sequential boundary conditions in terms of finite-population error probabilities.<n>The exact design yields ex ante control of decision error probabilities, and the simulation-based implementation approximates that design while allowing the computation of expected stopping times.
  arXiv  Detail & Related papers  (2026-04-07T17:26:23Z)
• Predicting fixed-sample test decisions enables anytime-valid inference [0.3222802562733787]
  We introduce a simple procedure that transforms any fixed-sample hypothesis test into an anytime-valid test.<n>We ensure Type-I error control and near-optimal power with substantial sample savings when the null hypothesis is false.<n>In areas such as clinical trials, stopping early and safely can ensure that subjects receive the best treatments and accelerate the development of effective therapies.
  arXiv  Detail & Related papers  (2026-02-14T20:17:51Z)
• COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees [51.5976496056012]
  COIN is an uncertainty-guarding selection framework that calibrates statistically valid thresholds to filter a single generated answer per question.<n>COIN estimates the empirical error rate on a calibration set and applies confidence interval methods to establish a high-probability upper bound on the true error rate.<n>We demonstrate COIN's robustness in risk control, strong test-time power in retaining admissible answers, and predictive efficiency under limited calibration data.
  arXiv  Detail & Related papers  (2025-06-25T07:04:49Z)
• Internal Incoherency Scores for Constraint-based Causal Discovery Algorithms [12.524536193679124]
  We propose internal coherency scores that allow testing for assumption violations and finite sample errors.<n>We illustrate our coherency scores on the PC algorithm with simulated and real-world datasets.
  arXiv  Detail & Related papers  (2025-02-20T16:44:54Z)
• Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting [65.21599711087538]
  Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and test data by adapting a given model w.r.t. any test sample.<n>Prior methods perform backpropagation for each test sample, resulting in unbearable optimization costs to many applications.<n>We propose an Efficient Anti-Forgetting Test-Time Adaptation (EATA) method which develops an active sample selection criterion to identify reliable and non-redundant samples.
  arXiv  Detail & Related papers  (2024-03-18T05:49:45Z)
• Deep anytime-valid hypothesis testing [29.273915933729057]
  We propose a general framework for constructing powerful, sequential hypothesis tests for nonparametric testing problems. We develop a principled approach of leveraging the representation capability of machine learning models within the testing-by-betting framework. Empirical results on synthetic and real-world datasets demonstrate that tests instantiated using our general framework are competitive against specialized baselines.
  arXiv  Detail & Related papers  (2023-10-30T09:46:19Z)
• When Does Confidence-Based Cascade Deferral Suffice? [69.28314307469381]
  Cascades are a classical strategy to enable inference cost to vary adaptively across samples. A deferral rule determines whether to invoke the next classifier in the sequence, or to terminate prediction. Despite being oblivious to the structure of the cascade, confidence-based deferral often works remarkably well in practice.
  arXiv  Detail & Related papers  (2023-07-06T04:13:57Z)
• Sequential Predictive Two-Sample and Independence Testing [114.4130718687858]
  We study the problems of sequential nonparametric two-sample and independence testing. We build upon the principle of (nonparametric) testing by betting.
  arXiv  Detail & Related papers  (2023-04-29T01:30:33Z)
• DELTA: degradation-free fully test-time adaptation [59.74287982885375]
  We find that two unfavorable defects are concealed in the prevalent adaptation methodologies like test-time batch normalization (BN) and self-learning. First, we reveal that the normalization statistics in test-time BN are completely affected by the currently received test samples, resulting in inaccurate estimates. Second, we show that during test-time adaptation, the parameter update is biased towards some dominant classes.
  arXiv  Detail & Related papers  (2023-01-30T15:54:00Z)
• 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.