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

arXiv:2608.06908 · cs.CL, cs.AI, cs.CY, cs.LG · Submitted 2026-08-07 · Read on arXiv

Seitaro Ono, Senna Ross, Jun Saiki

cs.CL, cs.AI, cs.CY, cs.LG

Submitted: 2026-08-07

Updated: 2026-08-10

Comments: Extended version (with appendices) of a paper accepted at the 9th AAAI/ACM Conference on AI, Ethics, and Society (AIES 2026)

Code: https://github.com/seigit/zca-weat

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Anisotropy — 61× in this paper · explained in 4 episodes
• Embeddings — 42× in this paper · explained in 2 episodes
• Calibration — 35× in this paper · explained in 9 episodes
• Cosine Similarity — 33× in this paper · explained in 3 episodes
• Benchmark — 12× in this paper · explained in 2 episodes
• Transformer — 9× in this paper · explained in 2 episodes
• Papers — 7× in this paper · explained in 3 episodes
• Accountability — 6× in this paper · explained in 2 episodes
• Semantic Similarity — 6× in this paper · explained in 2 episodes
• Transformers — 5× in this paper · explained in 2 episodes
• Word Embedding Association Test — 5× in this paper
• Generator — 3× in this paper · explained in 2 episodes
• Zero-phase Component Analysis — 3× in this paper
• Benchmarking — 2× in this paper · explained in 4 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Contrastive Learning — 2× in this paper · explained in 9 episodes
• Interpretability — 2× in this paper · explained in 15 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Compositionality — 1× in this paper · explained in 2 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Evaluation Framework — 1× in this paper · explained in 3 episodes
• Evaluation Protocol — 1× in this paper · explained in 2 episodes
• Model-Agnostic — 1× in this paper · explained in 2 episodes
• Objective Function — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 6 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transformer Architecture — 1× in this paper · explained in 4 episodes
• Transformer Model — 1× in this paper · explained in 2 episodes
• Transformer Models — 1× in this paper · explained in 3 episodes

Sources

• RoBERTa: A Robustly Optimized BERT Pretraining Approach
• Whitening Sentence Representations for Better Semantics and Faster Retrieval
• VEAT Quantifies Implicit Associations in Text-to-Video Generator Sora and Reveals Challenges in Bias Mitigation

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering