发表机构
University of Illinois Urbana-Champaign; Nanyang Technological University（伊利诺伊大学厄巴纳-香槟分校; 南洋理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过算法审计和用户访谈，揭示AI伴侣的种族编码呈现存在系统性偏见，并探讨了用户对种族表征的复杂感知，强调个性化评估需超越满意度以应对表征危害。
AI 中文摘要
AI伴侣据称可以采用种族化的人格，这引发了关于它们如何表征身份以及用户如何解读这些呈现的问题。我们将对种族编码的AI人格的算法审计与对12位与探针交互的伴侣用户的访谈相结合。我们的审计揭示了系统性差异，例如在开放权重模型中，亚裔编码的男性人格比白人对应者获得更高的顺从性评分，而黑人、西班牙裔和原住民男性人格比白人对应者获得更高的攻击性评分。访谈显示，参与者设想AI伴侣提供文化熟悉感和外部视角，但在哪些呈现被视为有意义或刻板印象方面存在分歧。一些人拒绝明显的种族信号，但仍期望具有文化特色的回应。将这些发现与理论进行三角验证，我们强调了社会规范和文化期望如何使支持有意义的种族表征而不复制刻板印象的努力复杂化。我们讨论了伴侣个性化应超越用户满意度进行评估，以考虑更广泛的表征危害。
英文摘要
AI companions can purportedly adopt racial personas, raising questions about how they represent identity and how users interpret these portrayals. We combined an algorithmic audit of race-coded AI personas with interviews with 12 companion users who interacted with a probe. Our audit revealed systematic differences, such as Asian-coded male personas receiving higher submissiveness scores than White counterparts, and Black, Hispanic, and Indigenous male personas receiving higher aggression scores than their White counterparts in open-weight models. Interviews revealed that participants envisioned AI companions as offering cultural familiarity and outside perspectives, but differed in which portrayals they considered meaningful or stereotypical. Some rejected overt racial signaling while still expecting culturally distinctive responses. Triangulating these findings with theory, we highlight how social norms and cultural expectations complicate efforts to support meaningful racial representation without reproducing stereotypes. We discuss how companion personalization should be evaluated beyond user satisfaction to account for broader representational harms.
Comments27 pages, 2 figures, 7 tables
