AI ethics evidence index Search
Source-linked daily record
Evidence record 7371 · automatically gathered

Procedural Fairness via Group Counterfactual Explanation

Fairness in machine learning research has largely focused on outcome-oriented fairness criteria such as Equalized Odds, while comparatively less attention has been given to procedural-oriented fairness, which addresses how a model arrives at its predictions. Neglecting procedural fairness means it is possible for a model to generate different explanations for different protected groups, thereby eroding trust. In this work, we introduce Group Counterfactual Integrated Gradients (GCIG), an in-proc

Record details

Published: 11 March 2026
Source: arXiv
Category: Research
Topics: Bias & fairness
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Same publisher byline · Shared topic: Bias & fairness

MESD: A Risk-Sensitive Metric for Explanation Fairness Across Intersectional Subgroups

arXiv · 13 March 2026

Same publisher byline · Shared topic: Bias & fairness

Fairness of Explanations in Artificial Intelligence (AI): A Unifying Framework, Axioms, and Future Direction toward Responsible AI

arXiv · 11 May 2026

Same publisher byline · Shared topic: Bias & fairness

Do Fair Models Reason Fairly? Counterfactual Explanation Consistency for Procedural Fairness in Credit Decisions

arXiv · 12 May 2026

Same publisher byline · Shared topic: Bias & fairness

GESD: Beyond Outcome-Oriented Fairness

arXiv · 14 May 2026

Shared topic: Bias & fairness

Hindsight-Anchored Policy Optimization: Turning Failure into Feedback in Sparse Reward Settings

arXiv · 11 March 2026

Shared topic: Bias & fairness

The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training

arXiv · 11 March 2026

How to cite this record

ethics.ai (11 March 2026), “Procedural Fairness via Group Counterfactual Explanation,” evidence record 7371, https://ethics.ai/record/7371 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.