arXiv cs.CL· Mahika Phutane, Hayoung Jung, Matthew Kim, Tanushree Mitra, Aditya Vashistha·· 6 天前AI 评分33
ABLEIST：LLM 招聘场景中的交叉性残障偏见
ABLEIST: Intersectional Disability Bias in LLM-Generated Hiring Scenarios
AI 导读
研究对 6 个 LLM 在 2,820 个招聘场景中展开审计，覆盖残障、性别、国籍与种姓等画像，并提出 ABLEIST 指标集，包含 5 项残障歧视专属指标与 3 项交叉性伤害指标。结果显示，针对残障候选人的 ABLEIST 伤害显著上升，且许多 SOTA 模型未能检出；性别与种姓边缘化的残障候选人还面临 Tokenism 等交叉性伤害加剧。
正文 · 原文
Abstract:Large language models (LLMs) are increasingly under scrutiny for perpetuating identity-based discrimination in high-stakes domains such as hiring, particularly against people with disabilities (PwD). However, existing research remains largely Western-centric, overlooking how intersecting forms of marginalization--such as gender and caste--shape experiences of PwD in the Global South. We conduct a comprehensive audit of six LLMs across 2,820 hiring scenarios spanning diverse disability, gender, nationality, and caste profiles. To capture subtle intersectional harms and biases, we introduce ABLEIST (Ableism, Inspiration, Superhumanization, and Tokenism), a set of five ableism-specific and three intersectional harm metrics grounded in disability studies literature. Our results reveal significant increases in ABLEIST harms towards disabled candidates--harms that many state-of-the-art models failed to detect. These harms were further amplified by sharp increases in intersectional harms (e.g., Tokenism) for gender and caste-marginalized disabled candidates, highlighting critical blind spots in current safety tools and the need for intersectional safety evaluations of frontier models in high-stakes domains like hiring.
| Comments: | To appear at AIES 2026. Please cite AIES version when the proceedings are available |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG) |
| Cite as: | arXiv:2510.10998 [cs.CL] |
| (or arXiv:2510.10998v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2510.10998 arXiv-issued DOI via DataCite |
Submission history
From: Hayoung Jung [view email]
[v1]
Mon, 13 Oct 2025 04:18:23 UTC (1,493 KB)
[v2]
Thu, 8 Oct 2026 22:37:37 UTC (1,389 KB)
来源：arXiv cs.CL · arxiv.org