Overview

Algorithmic auditing studies how to test automated decisions and the systems around them, especially when errors or disparities affect people. Common approaches compare subgroup outcomes, use counterfactual or causal tests, probe model behavior under perturbations, and apply statistical methods such as sequential testing and uncertainty analysis. Audits increasingly examine deployed pipelines, data and component interactions, strategic responses, and evidence trails—not just a model’s aggregate accuracy. A central challenge is making conclusions reliable and meaningful despite limited access, shifting conditions, incomplete data, and metrics that can be gamed or fail to capture the harms that matter.

Latest papers

CardsList

159 papers20 papers in the last four weeks, down 9% on the four weeks before. 0.2% of all new papers.

  1. A multimodal slice discovery framework for systematic failure detection and explanation in medical image classification

    Feb 27, 2026Yixuan Liu, Kanwal K. Bhatia, Ahmed E. FetitAlgorithmic AuditingMedical Image Classification

  2. Global Sequential Testing for Multi-Stream Auditing

    Feb 25, 2026Beepul Bharti, Ambar Pal, Jeremias SulamSequential Hypothesis TestingMultiple Hypothesis Testing

  3. Governing AI Forgetting: Auditing for Machine Unlearning Compliance

    Feb 16, 2026Qinqi Lin, Ningning Ding, Lingjie Duan +1Algorithmic AuditingMachine Unlearning

  4. Falsifying Discriminant Validity of Predictive Algorithms

    Jan 23, 2026Amanda CostonAlgorithmic AuditingPsychometric Validation

  5. White-Box Sensitivity Auditing with Steering Vectors

    Jan 23, 2026Hannah Cyberey, Yangfeng Ji, David EvansAlgorithmic AuditingLLM Auditing

  6. A framework for auditing grounding claims

    Dec 5, 2025Daniel Quigley, Eric MaynardAlgorithmic Auditing

  7. A global log for medical AI

    Oct 5, 2025Ayush Noori, Aaron E. Boussina, Hai Ho Bich +48Algorithmic AuditingHealthcare