Sima AIunty: LLM驱动的匹配中阶级审计
Sima AIunty: Caste Audit in LLM-Driven Matchmaking
AI总结：
研究通过实世界婚姻资料审计LLM在匹配中的阶级偏见，发现同阶级匹配评分更高，揭示现有阶级体系在AI决策中的再现，需制定文化导向的评估与干预策略。
摘要：
社交和个人决策在匹配等领域与文化规范和历史等级紧密交织，可能受算法和AI中介的兼容性、接受度和稳定性评估影响。在南亚背景下，种姓是婚姻决策的核心，但现有大型语言模型（LLM）如何再现或打破种姓阶层化尚不清楚。本文通过真实婚姻资料对LLM驱动的匹配评估中的种姓偏见进行受控审计，变化种姓身份（婆罗门、刹那利、吠舍、首陀罗、达罗特）和收入等级，并评估五种LLM家族（GPT、Gemini、Llama、Qwen和BharatGPT）。模型被提示评估资料在社会接受度、婚姻稳定性和文化兼容性维度上的表现。分析显示模型间一致存在层级模式：同种姓匹配评分最高，平均评分比跨种姓匹配高25%（在10分制上），后者又按传统种姓层级排序。这些发现凸显了现有种姓体系在LLM决策中的再现，强调了在社会敏感领域部署的AI系统中，需制定基于文化的评估和干预策略，以避免强化历史排斥形式。
英文摘要：
Social and personal decisions in relational domains such as matchmaking are deeply entwined with cultural norms and historical hierarchies, and can potentially be shaped by algorithmic and AI-mediated assessments of compatibility, acceptance, and stability. In South Asian contexts, caste remains a central aspect of marital decision-making, yet little is known about how contemporary large language models (LLMs) reproduce or disrupt caste-based stratification in such settings. In this work, we conduct a controlled audit of caste bias in LLM-mediated matchmaking evaluations using real-world matrimonial profiles. We vary caste identity across Brahmin, Kshatriya, Vaishya, Shudra, and Dalit, and income across five buckets, and evaluate five LLM families (GPT, Gemini, Llama, Qwen, and BharatGPT). Models are prompted to assess profiles along dimensions of social acceptance, marital stability, and cultural compatibility. Our analysis reveals consistent hierarchical patterns across models: same-caste matches are rated most favorably, with average ratings up to 25% higher (on a 10-point scale) than inter-caste matches, which are further ordered according to traditional caste hierarchy. These findings highlight how existing caste hierarchies are reproduced in LLM decision-making and underscore the need for culturally grounded evaluation and intervention strategies in AI systems deployed in socially sensitive domains, where such systems risk reinforcing historical forms of exclusion.
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。
