Metraipolis › archive › dc_159385e658eb
How Humans and LLMs Read Gender into "Gender-Neutral" Physical Descriptions — arXiv:2609.16366
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.16366
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T18:34:52.365Z
- SHA-256 of the archived text
3a2c010f0cc3fc6ca0ce66ea5a66de3f92badaba42988dc0ff2459c0dc3107b5- Stable URL of this page
https://metraipolis.com/documento/dc_159385e658eb
How to cite
How Humans and LLMs Read Gender into "Gender-Neutral" Physical Descriptions — arXiv:2609.16366 — arXiv (en), https://arxiv.org/abs/2609.16366 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_159385e658eb (Metraipolis archive dc_159385e658eb, sha256 3a2c010f0cc3fc6ca0ce66ea5a66de3f92badaba42988dc0ff2459c0dc3107b5)
BibTeX
@misc{dc159385e658eb,
title = {How Humans and LLMs Read Gender into "Gender-Neutral" Physical Descriptions — arXiv:2609.16366},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.16366},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_159385e658eb; sha256 3a2c010f0cc3fc6ca0ce66ea5a66de3f92badaba42988dc0ff2459c0dc3107b5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16366. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
When foundation models describe people, recent work in AI fairness, accessibility, and ethics recommends avoiding inferred identity labels (e.g., "she", "his") in favor of seemingly "objective" physical descriptions (e.g., "short hair", "a defined jawline"). Yet whether such descriptive language achieves gender-neutral communication remains an open empirical question. To study this, we introduce GAPA (Gender Associations of Physical Attributes), a dataset of 316 common physical attributes drawn from diverse sources, paired with 14,706 gender-association ratings from 304 US-based annotators. Results show that physical descriptions carry structured and graded gender associations among readers, with more consistent and distinctive associations for women and men than for non-binary identities. Next, we evaluate 16 LLMs across model families, sizes, and post-training variants against human ratings. The models partially recover human associations but exhibit systematic alignment biases, including compressed rating distributions, weaker alignment for associations with men, and asymmetric abstention that disproportionately targets the non-binary category. Finally, we release the best-performing proxy model trained to predict humans' gender associations of descriptive language and demonstrate its utility through a sociolinguistic analysis of character descriptions in LitBank. Together, our findings provide the first empirical evidence that seemingly "objective" physical descriptions can retain systematic gender associations in human interpretation, and uncover systematic patterns of model-human misalignment. This challenges the assumption that replacing explicit gender labels with physical descriptions necessarily yields gender-neutral communication, and highlights downstream challenges in using such descriptions to communicate subjective identity categories in human-AI interaction. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Human-Computer Interaction (cs.HC). Pagina del lavoro: https://arxiv.org/abs/2609.16366 — 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 2026-10-15T18:03:09.624Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).