AI ethics evidence index Search
Source-linked daily record
Evidence record 17819 · automatically gathered

Calibrating WEAT Against Anisotropy: ZCA Whitening as a Geometric Pre-Processing Step for Embedding Association Tests

We propose Zero-phase Component Analysis (ZCA) whitening as a geometric pre-processing step for the Word Embedding Association Test (WEAT). WEAT is a bias measurement method widely used in both computational social science and AI fairness research. It relies on cosine similarity as a measure of semantic association, which assumes that the embedding space is approximately isotropic. However, prior work has reported that many widely used language models do not satisfy this assumption, raising conc

Record details

Published: 7 August 2026
Source: arXiv
Category: Research
Topics: Bias & fairness
Retrieved: 10 August 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

Calibrating WEAT Against Anisotropy: ZCA Whitening as a Geometric Pre-Processing Step for Embedding Association Tests

arXiv cs.CY · 10 August 2026

Shared topic: Bias & fairness

Stream Learning: Partition-Fair Gossip Learning Without Tokens

arXiv fairness query · 7 August 2026

Shared topic: Bias & fairness

Conditional Cognitive Biases in LLMs: How Biased User Turns Modulate In-Context Reasoning

arXiv cs.CY · 7 August 2026

Shared topic: Bias & fairness

Who Gets Access? Global Region and Academic Status Bias in AI-Generated Academic Gatekeeping Scenarios

arXiv cs.CY · 7 August 2026

Shared topic: Bias & fairness

H2AL: Hyperbolic Hierarchy-aware Aggregative Learning for Registration-based Few-shot Medical Image Segmentation

arXiv cs.AI · 7 August 2026

Shared topic: Bias & fairness

Fairis: Fairness-Aware Aggregation with Provable Influence Containment against Fairness Poisoning Attacks in Collaborative Machine Learning

arXiv cs.CR (AI security) · 6 August 2026

How to cite this record

ethics.ai (7 August 2026), “Calibrating WEAT Against Anisotropy: ZCA Whitening as a Geometric Pre-Processing Step for Embedding Association Tests,” evidence record 17819, https://ethics.ai/record/17819 (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.