Sequential Fairness Auditing with Limited Output Access

• URL: http://arxiv.org/abs/2606.30338v1
• Date: Mon, 29 Jun 2026 14:17:33 GMT
• Title: Sequential Fairness Auditing with Limited Output Access
• Abstract summary: External evaluations are becoming increasingly central to the governance of AI systems.<n>In practice, independent auditors often have limited access to deployed models and must rely on query-based interactions.<n>Most existing fairness evaluation methods assume static datasets and fixed-sample statistical tests.<n>We formulate fairness auditing as a tolerance-aware sequential hypothesis-testing problem under limited model output access.
• Score: 6.933020649563105
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: External evaluations are becoming increasingly central to the governance of AI systems. In practice, however, independent auditors often have limited access to deployed models and must rely on query-based interactions. Most existing fairness evaluation methods assume static datasets and fixed-sample statistical tests, making them poorly suited to real-world auditing scenarios in which evidence must be collected sequentially under query constraints. In this work, we formulate fairness auditing as a tolerance-aware sequential hypothesis-testing problem under limited model output access. We develop a sequential generalized likelihood-ratio framework that allows auditors to accumulate evidence from a finite audit pool and stop once sufficient support for compliance or violation has been obtained. The framework is instantiated for decision-based Statistical Parity and Equal Opportunity audits, and extended to score- and logit-based proxy audits when richer observables are available. Our results show that both the fairness metric and the level of model access significantly affect audit efficiency, and that the benefits of richer output information are not uniform across auditing settings. In particular, richer outputs can substantially reduce the number of queries required for some fairness metrics and operating regimes, while offering limited gains in near-threshold cases. This work provides a practical statistical framework for sequential fairness auditing under realistic deployment constraints.

Related papers

• Manipulation-Proof Oblivious Audits against Deceptive Model Providers [4.614773550999029]
  In regulatory contexts, audits are typically declared or easily detected, enabling model providers to manipulate the process.<n>This vulnerability is particularly acute in the context of fairness evaluations.<n>We introduce a novel audit protocol designed to significantly increase the post-audit detectability of such manipulations.
  arXiv  Detail & Related papers  (2026-08-05T02:12:54Z)
• Fairness Auditing: Lower Bounds on Company Manipulation [4.867679624126028]
  Fairness audits are increasingly mandated in high-stakes applications such as hiring, lending, and automated decision-making.<n>Recent work has established fundamental impossibility results for black-box fairness auditing.<n>We quantify the extent of unavoidable post-audit manipulation under finite audit resources.
  arXiv  Detail & Related papers  (2026-08-01T10:11:20Z)
• Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents? [61.49434544687523]
  We introduce REFLECT, a meta-evaluation benchmark targeting fine-grained failure detection in agentic environments.<n> REFLECT defines a detailed taxonomy of process- and outcome-level failure modes, instantiated by performing controlled and localized interventions.<n>Our experiments show that even the best-performing models achieve overall accuracies below 55% across reasoning, tool-use, and report-quality failures.
  arXiv  Detail & Related papers  (2026-05-18T23:55:08Z)
• Adaptive auditing of AI systems with anytime-valid guarantees [8.752768302067638]
  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.
  arXiv  Detail & Related papers  (2026-05-07T22:33:48Z)
• 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)
• IMMACULATE: A Practical LLM Auditing Framework via Verifiable Computation [49.796717294455796]
  We present IMMACULATE, a practical auditing framework that detects economically motivated deviations.<n>IMMACULATE selectively audits a small fraction of requests using verifiable computation, achieving strong detection guarantees while amortizing cryptographic overhead.
  arXiv  Detail & Related papers  (2026-02-26T07:21:02Z)
• 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)
• Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs [71.7892165868749]
  Commercial Large Language Model (LLM) APIs create a fundamental trust problem.<n>Users pay for specific models but have no guarantee that providers deliver them faithfully.<n>We formalize this model substitution problem and evaluate detection methods under realistic adversarial conditions.<n>We propose and evaluate the use of Trusted Execution Environments (TEEs) as one practical and robust solution.
  arXiv  Detail & Related papers  (2025-04-07T03:57:41Z)
• FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Models [79.41859481668618]
  Large Language Models (LLMs) have significantly advanced the fact-checking studies.<n>Existing automated fact-checking evaluation methods rely on static datasets and classification metrics.<n>We introduce FACT-AUDIT, an agent-driven framework that adaptively and dynamically assesses LLMs' fact-checking capabilities.
  arXiv  Detail & Related papers  (2025-02-25T07:44:22Z)
• Access Denied: Meaningful Data Access for Quantitative Algorithm Audits [4.182284365432724]
  Third-party audits are often hindered by access restrictions, forcing auditors to rely on limited, low-quality data.<n>We conduct audit simulations on two realistic case studies for recidivism and healthcare coverage prediction.<n>We find that data minimization and anonymization practices can strongly increase error rates on individual-level data, leading to unreliable assessments.
  arXiv  Detail & Related papers  (2025-02-01T13:33:45Z)
• Under manipulations, are some AI models harder to audit? [2.699900017799093]
  We study the feasibility of robust audits in realistic settings, in which models exhibit large capacities. We first prove a constraining result: if a web platform uses models that may fit any data, no audit strategy can outperform random sampling. We then relate the manipulability of audits to the capacity of the targeted models, using the Rademacher complexity.
  arXiv  Detail & Related papers  (2024-02-14T09:38:09Z)
• The Decisive Power of Indecision: Low-Variance Risk-Limiting Audits and Election Contestation via Marginal Mark Recording [51.82772358241505]
  Risk-limiting audits (RLAs) are techniques for verifying the outcomes of large elections. We define new families of audits that improve efficiency and offer advances in statistical power. New audits are enabled by revisiting the standard notion of a cast-vote record so that it can declare multiple possible mark interpretations.
  arXiv  Detail & Related papers  (2024-02-09T16:23:54Z)
• A Brief Tutorial on Sample Size Calculations for Fairness Audits [6.66743248310448]
  This tutorial provides guidance on how to determine the required subgroup sample sizes for a fairness audit. Our findings are applicable to audits of binary classification models and multiple fairness metrics derived as summaries of the confusion matrix.
  arXiv  Detail & Related papers  (2023-12-07T22:59:12Z)
• Algorithmic Fairness and Vertical Equity: Income Fairness with IRS Tax Audit Models [73.24381010980606]
  This study examines issues of algorithmic fairness in the context of systems that inform tax audit selection by the IRS. We show how the use of more flexible machine learning methods for selecting audits may affect vertical equity. Our results have implications for the design of algorithmic tools across the public sector.
  arXiv  Detail & Related papers  (2022-06-20T16:27:06Z)

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.