Metraipolis › archive › dc_53610b71cf7e
Gender bias across LLMs is common and highly heterogeneous — arXiv:2609.38036
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38036
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T16:28:03.533Z
- SHA-256 of the archived text
b6311286eba1e2198e3d6f03348d9c893cfe31ead50c1814c235fc8b5cc69bf2- Stable URL of this page
https://metraipolis.com/documento/dc_53610b71cf7e
How to cite
Gender bias across LLMs is common and highly heterogeneous — arXiv:2609.38036 — arXiv (en), https://arxiv.org/abs/2609.38036 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_53610b71cf7e (Metraipolis archive dc_53610b71cf7e, sha256 b6311286eba1e2198e3d6f03348d9c893cfe31ead50c1814c235fc8b5cc69bf2)
BibTeX
@misc{dc53610b71cf7e,
title = {Gender bias across LLMs is common and highly heterogeneous — arXiv:2609.38036},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38036},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_53610b71cf7e; sha256 b6311286eba1e2198e3d6f03348d9c893cfe31ead50c1814c235fc8b5cc69bf2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38036. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Understanding gender biases in large language models (LLMs) is increasingly important as these systems become embedded in decision-support tools with real consequences. Prior research has focused only on a small set of models, leaving open the extent to which gender biases are common and heterogeneous across LLMs. We address this gap across ten models released between April 2025 and June 2026, spanning nine vendors, using two paradigms: gender attribution to stereotyped phrases (Study 1) and moral judgment of abuse or torture against a woman or a man to prevent a catastrophic outcome (Study 2). In Study 1, two of ten models attributed masculine-stereotyped phrases to female writers more often than the reverse, while three models showed the opposite pattern. In Study 2, several models converged on a male-disadvantaging asymmetry that was directionally consistent with a documented human tendency to protect female targets from harm, though the specific conditions under which this asymmetry emerged varied by model; three other models, by contrast, showed no variation across conditions. These results indicate that gender-related biases are common in LLMs. Their direction and magnitude, however, are highly heterogeneous, to the point that some models behave in diametrically opposite ways to others. Bias auditing should therefore be treated as an ongoing, multi-vendor process, rather than a one-time assessment. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 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/2609.38036 — 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 2026-10-07T15:54:54.065Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).