披露残疾信息会影响LLM招聘公平性，不披露者更易被忽视
The Impact of Disability Disclosure on Fairness and Bias in LLM-Driven Candidate Selection
- 对比相同资质候选人，披露无残疾者获选概率更高
- 未披露残疾状态者被选中概率低于明确声明无残疾者
- 揭示了数据披露对算法偏见的隐蔽影响，适合关注AI公平性研究者
随着大型语言模型（LLMs）越来越多地应用于招聘流程，公平性问题日益突出。企业在招聘中常要求提供性别、种族及残疾或退伍军人身份等人口统计信息，用于支持多元化与包容性举措。然而，当这些信息尤其是残疾相关信息被输入到LLMs中时，可能引发候选人筛选结果中的潜在偏见。尽管已有研究指出残疾可能影响简历筛选，但关于自愿披露信息在LLM驱动招聘中的具体影响仍缺乏探索。本研究发现，在性别、种族、资历、经验及背景完全相同的条件下，应聘现金出纳员或软件开发岗位（此类岗位残障人士就业率差距较小）时，LLMs始终更倾向于选择声明无残疾的候选人。即使候选人未主动披露残疾状态，其被选中的概率也低于明确表示无残疾者。
原文摘要 · Abstract (English)
As large language models (LLMs) become increasingly integrated into hiring processes, concerns about fairness have gained prominence. When applying for jobs, companies often request/require demographic information, including gender, race, and disability or veteran status. This data is collected to support diversity and inclusion initiatives, but when provided to LLMs, especially disability-related information, it raises concerns about potential biases in candidate selection outcomes. Many studies have highlighted how disability can impact CV screening, yet little research has explored the specific effect of voluntarily disclosed information on LLM-driven candidate selection. This study seeks to bridge that gap. When candidates shared identical gender, race, qualifications, experience, and backgrounds, and sought jobs with minimal employment rate gaps between individuals with and without disabilities (e.g., Cashier, Software Developer), LLMs consistently favored candidates who disclosed that they had no disability. Even in cases where candidates chose not to disclose their disability status, the LLMs were less likely to select them compared to those who explicitly stated they did not have a disability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。