Counterfactual, Per-Decision Bias Auditing for Automated Hiring: Localizing and Explaining Disparate Impact in Applicant Tracking Systems

• URL: http://arxiv.org/abs/2608.21537v1
• Date: Fri, 21 Aug 2026 18:19:20 GMT
• Title: Counterfactual, Per-Decision Bias Auditing for Automated Hiring: Localizing and Explaining Disparate Impact in Applicant Tracking Systems
• Abstract summary: We present the AI Bias Firewall (AIBF), a method that audits an applicant tracking system one decision at a time.<n>AIBF neutralizes a candidate's protected-attribute proxies, re-scores the decision, and measures the resulting counterfactual shift.<n>We evaluate on two real public datasets, Adult and COMPAS, rather than on synthetic data.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Automated applicant tracking systems increasingly decide who advances in hiring, and litigation and regulation now demand that those decisions be auditable. Existing tools sit at two extremes. Group fairness metrics such as the disparate impact ratio summarize a whole population but cannot say which individual decisions were unfair or why, while local explainers such as SHAP attribute a single prediction but are not connected to the legal standard by which hiring bias is judged. We present the AI Bias Firewall (AIBF), a method that audits an applicant tracking system one decision at a time. AIBF neutralizes a candidate's protected-attribute proxies, re-scores the decision, and measures the resulting counterfactual shift, which yields a signed per-decision bias in score points, a flag for decisions the protected attributes changed, and a plain-language explanation naming the responsible factors. We evaluate on two real public datasets, Adult and COMPAS, rather than on synthetic data. The per-decision counterfactual shift is faithful, aggregating to reproduce the known group level disparity, for example a mean shift of +7.5 points for the privileged group and -8.0 for the disadvantaged group on Adult, consistent with the measured statistical parity difference. AIBF identifies the decisions that protected attributes flipped with an area under the ROC curve of 0.963 on Adult, against 0.672 for a baseline that flags by group membership, and it identifies the harmed candidates so precisely that reviewing only five percent of decisions surfaces fifty-five percent of them, against six percent under group based review. We also report a limitation: correcting flagged decisions raises the disparate impact ratio substantially but not to legal parity, because features labeled as merit carry residual proxy correlation. AIBF is released under the Apache 2.0 license with code and experiments.

Related papers

• Using AI Agents to Automate Black-Box Audits of Personalization Algorithms at Scale [76.72846830885882]
  Personalization algorithms determine what content users encounter on online platforms.<n> auditing these systems is difficult because independent auditors have only black-box access to the algorithms.<n>We introduce a framework for black-box audits of personalization algorithms using generative AI agents as behavioral engines for synthetic accounts.
  arXiv  Detail & Related papers  (2026-06-29T18:25:09Z)
• Do Gender Cues Affect LLM Value Trade-offs? Evidence from a Controlled Decision Benchmark [33.25199452418043]
  We construct a benchmark that varies only the role-gender configuration while holding the scenario.<n>We find that explicit gender cues induce bounded but systematic decision flips.<n>Gender effects concentrate near less determinate value boundaries, suggesting that gender cues act as local boundary-shifting factors.
  arXiv  Detail & Related papers  (2026-06-01T13:14:10Z)
• Fairness under uncertainty in sequential decisions [14.392931077157906]
  Algorithmic approaches alone cannot resolve structural inequalities.<n>Many real machine learning applications are online and sequential, with prior decisions informing future ones.<n>This paper introduces a taxonomy of uncertainty in sequential decision-making.
  arXiv  Detail & Related papers  (2026-04-23T14:17:58Z)
• Partial Identification Approach to Counterfactual Fairness Assessment [50.88100567472179]
  We introduce a Bayesian approach to bound unknown counterfactual fairness measures with high confidence.<n>Our results reveal a positive (spurious) effect on the COMPAS score when changing race to African-American (from all others) and a negative (direct causal) effect when transitioning from young to old age.
  arXiv  Detail & Related papers  (2025-09-30T18:35:08Z)
• Mitigating Subgroup Disparities in Multi-Label Speech Emotion Recognition: A Pseudo-Labeling and Unsupervised Learning Approach [53.824673312331626]
  Implicit Demography Inference (IDI) module uses k-means clustering to mitigate bias in Speech Emotion Recognition (SER)<n>Experiments show that pseudo-labeling IDI reduces subgroup disparities, improving fairness metrics by over 28%.<n>Unsupervised IDI yields more than a 4.6% improvement in fairness metrics with a drop of less than 3.6% in SER performance.
  arXiv  Detail & Related papers  (2025-05-20T14:50:44Z)
• When Bias Backfires: The Modulatory Role of Counterfactual Explanations on the Adoption of Algorithmic Bias in XAI-Supported Human Decision-Making [0.0]
  This study simulated hiring decisions to examine how biased AI recommendations influence human judgment over time.<n>Our results indicate that the participants followed the AI recommendations 70% of the time when the qualifications of the given candidates were comparable.<n>In the post-interaction phase, participants' independent decisions aligned with the bias when no counterfactual explanations were provided before, but reversed the bias when explanations were given.
  arXiv  Detail & Related papers  (2025-05-20T14:00:28Z)
• Online Decision Mediation [72.80902932543474]
  Consider learning a decision support assistant to serve as an intermediary between (oracle) expert behavior and (imperfect) human behavior. In clinical diagnosis, fully-autonomous machine behavior is often beyond ethical affordances.
  arXiv  Detail & Related papers  (2023-10-28T05:59:43Z)
• Equal Confusion Fairness: Measuring Group-Based Disparities in Automated Decision Systems [5.076419064097733]
  This paper proposes a new equal confusion fairness test to check an automated decision system for fairness and a new confusion parity error to quantify the extent of any unfairness. Overall, the methods and metrics provided here may assess automated decision systems' fairness as part of a more extensive accountability assessment.
  arXiv  Detail & Related papers  (2023-07-02T04:44:19Z)
• D-BIAS: A Causality-Based Human-in-the-Loop System for Tackling Algorithmic Bias [57.87117733071416]
  We propose D-BIAS, a visual interactive tool that embodies human-in-the-loop AI approach for auditing and mitigating social biases. A user can detect the presence of bias against a group by identifying unfair causal relationships in the causal network. For each interaction, say weakening/deleting a biased causal edge, the system uses a novel method to simulate a new (debiased) dataset.
  arXiv  Detail & Related papers  (2022-08-10T03:41:48Z)
• Delving into Probabilistic Uncertainty for Unsupervised Domain Adaptive Person Re-Identification [54.174146346387204]
  We propose an approach named probabilistic uncertainty guided progressive label refinery (P$2$LR) for domain adaptive person re-identification. A quantitative criterion is established to measure the uncertainty of pseudo labels and facilitate the network training. Our method outperforms the baseline by 6.5% mAP on the Duke2Market task, while surpassing the state-of-the-art method by 2.5% mAP on the Market2MSMT task.
  arXiv  Detail & Related papers  (2021-12-28T07:40:12Z)

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.