arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.13253cs.CYcs.AI
收藏

LLMs对跨性别人群的隐性偏见

Implicit Bias in LLMs for Transgender Populations

Instituto de Ciencias de la Computación (UBA-CONICET)(计算机科学研究所(UBA-CONICET));Hospital Dr. Lucio Melendez(Lucio Melendez医院);Universidad de Buenos Aires(布宜诺斯艾利斯大学);Universidad Católica de Chile(智利天主大学);MICS, CentraleSupélec - Université Paris-Saclay(MICS,CentraleSupélec-巴黎萨克雷大学);Universidad Nacional de Córdoba(科迪利亚国家大学);Fundación Vía Libre(自由之路基金会);CIECTI

Micaela Hirsch, Marina Elichiry, Blas Radi, Tamara Quiroga, David Restrepo, Luciana Benotti, Veronica Xhardez, Jocelyn Dunstan, Enzo Ferrante

AI总结:

本研究揭示了LLMs对跨性别人群的隐性偏见,通过词语关联测试和医疗预约分配任务发现LLMs在多个类别中存在负面关联,并指出需研究以减少LLMs中的刻板印象偏见,确保医疗应用中的公平性。

摘要:

大型语言模型(LLMs)已被证明会对LGBTQ+人群表现出偏见。尽管安全训练可能减少显性偏见的表达,但先前的研究表明,由隐性刻板印象驱动的关联往往仍然存在。在本研究中,我们考察了LLMs对跨性别人群的隐性偏见,在两个主要场景中进行。首先,我们将词语关联测试适应化,以测量LLMs是否倾向于将负面概念与“跨性别”关联,而将正面概念与“性别认同”关联。其次,考虑到跨性别人在现实世界医疗环境中所面临的系统性挑战,我们研究当LLMs应用于医疗决策时可能产生的隐性偏见。为此,我们设计了一个医疗预约分配任务,其中模型充当调度代理,在易产生刻板印象的医疗专业领域中选择跨性别或性别认同的候选人。我们评估了七种英语和西班牙语的LLMs。我们的结果表明,在外观、风险和真实性等类别中存在一致的偏见,表明对跨性别个体有更强的负面关联。在分配任务中,跨性别候选人更倾向于获得性传播疾病和心理健康服务,而性别认同候选人则在妇科和乳腺护理中更受青睐。这些发现强调了研究解决LLMs中微妙刻板印象驱动偏见的必要性,以确保医疗应用中对跨性别人群的公平对待。

英文摘要:

Large language models (LLMs) have been shown to exhibit biases against LGBTQ+ populations. While safety training may lessen explicit expressions of bias, previous work has shown that implicit stereotype-driven associations often persist. In this work, we examine implicit bias toward transgender people in two main scenarios. First, we adapt word association tests to measure whether LLMs disproportionately pair negative concepts with "transgender" and positive concepts with "cisgender". Second, acknowledging the well-documented systemic challenges that transgender people encounter in real-world healthcare settings, we examine implicit biases that may emerge when LLMs are applied to healthcare decision-making. To this end, we design a healthcare appointment allocation task where models act as scheduling agents choosing between cisgender and transgender candidates across medical specialties prone to stereotyping. We evaluate seven LLMs in English and Spanish. Our results show consistent bias in categories such as appearance, risk, and veracity, indicating stronger negative associations with transgender individuals. In the allocation task, transgender candidates are favored for STI and mental health services, while cisgender candidates are preferred in gynecology and breast care. These findings underscore the need for research that address subtle stereotype-driven biases in LLMs to ensure equitable treatment of transgender people in healthcare applications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑