Metraipolis › archive › dc_005cd204acf8

Calibrating WEAT Against Anisotropy: ZCA Whitening as a Geometric Pre-Processing Step for Embedding Association Tests — arXiv:2608.06908

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.06908
License (as archived): CC0-1.0
Archived: 2026-10-19T09:46:52.397Z
SHA-256 of the archived text: 2b478b3cf5ab62dab6df6cfea9bcdaf734c1dd0cb67ae3c28cb559f66acab5cd
Stable URL of this page: https://metraipolis.com/documento/dc_005cd204acf8

How to cite

Calibrating WEAT Against Anisotropy: ZCA Whitening as a Geometric Pre-Processing Step for Embedding Association Tests — arXiv:2608.06908 — arXiv (en), https://arxiv.org/abs/2608.06908 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_005cd204acf8 (Metraipolis archive dc_005cd204acf8, sha256 2b478b3cf5ab62dab6df6cfea9bcdaf734c1dd0cb67ae3c28cb559f66acab5cd)

BibTeX

@misc{dc005cd204acf8,
  title = {Calibrating WEAT Against Anisotropy: ZCA Whitening as a Geometric Pre-Processing Step for Embedding Association Tests — arXiv:2608.06908},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.06908},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_005cd204acf8; sha256 2b478b3cf5ab62dab6df6cfea9bcdaf734c1dd0cb67ae3c28cb559f66acab5cd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.06908. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 concerns about the reliability of bias measurements. ZCA whitening transforms the covariance of the embedding space into the identity matrix while minimizing perturbation to the original vectors. This transformation restores the isotropy condition on which WEAT relies. We evaluate our approach on ten standard WEAT test suites and seven models spanning three architectural families, yielding 70 model-task combinations. The results show that ZCA whitening substantially reduces the anisotropy of the embedding spaces across all models. Particularly for highly anisotropic models, we further observe improvements on standard semantic similarity benchmarks, indicating that the calibrated space better captures semantic associations. After calibration, over 30% of WEAT results change significance status, and effect sizes shift in both directions depending on bias category. These shifts suggest that uncalibrated measurements may both overestimate and underestimate the associations encoded in the embedding space. These findings indicate that previously reported bias measurements in anisotropic embedding spaces should be interpreted with caution and may benefit from re-evaluation with calibrated methods. Our approach contributes to restoring the measurement foundation of WEAT across both computational social science and AI fairness research.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-10 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.06908 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T09:46:37.226Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).