注意鸿沟：LLM对齐与亚洲公众意见的陷阱
Mind the Gap: Pitfalls of LLM Alignment with Asian Public Opinion
AI总结：
本文研究了LLM在多语言多文化环境中的对齐问题，发现其在宗教观点尤其是少数群体方面存在偏差，提出轻量干预无法消除文化鸿沟，强调需系统性地区审计确保公平部署。
摘要：
大型语言模型（LLMs）在多语言、多文化环境中日益普及，但其依赖以英语为中心的训练数据可能与不同社会的文化价值观不一致。本文对包括GPT-4o-Mini、Gemini-2.5-Flash、Llama 3.2、Mistral和Gemma 3在内的当代LLM在印度、东亚和东南亚的文化对齐情况进行了全面多语言审计。研究聚焦于宗教这一敏感领域作为更广泛对齐的棱镜。我们通过日志概率/日志几率分析每个LLM的内部表示，将模型观点分布与真实公众态度进行比较。发现尽管流行模型在广泛社会问题上与公众意见一致，但在宗教观点，尤其是少数群体观点上表现不佳，常放大负面刻板印象。轻量干预如人口特征提示和本地语言提示部分缓解但无法消除这些文化鸿沟。进一步通过偏见基准测试（如CrowS-Pairs、IndiBias、ThaiCLI、KoBBQ）显示在敏感情境中存在持续的伤害和代表性不足。我们的发现强调了系统性、地区性审计的紧迫性，以确保LLM的全球公平部署。
英文摘要：
Large Language Models (LLMs) are increasingly being deployed in multilingual, multicultural settings, yet their reliance on predominantly English-centric training data risks misalignment with the diverse cultural values of different societies. In this paper, we present a comprehensive, multilingual audit of the cultural alignment of contemporary LLMs including GPT-4o-Mini, Gemini-2.5-Flash, Llama 3.2, Mistral and Gemma 3 across India, East Asia and Southeast Asia. Our study specifically focuses on the sensitive domain of religion as the prism for broader alignment. To facilitate this, we conduct a multi-faceted analysis of every LLM's internal representations, using log-probs/logits, to compare the model's opinion distributions against ground-truth public attitudes. We find that while the popular models generally align with public opinion on broad social issues, they consistently fail to accurately represent religious viewpoints, especially those of minority groups, often amplifying negative stereotypes. Lightweight interventions, such as demographic priming and native language prompting, partially mitigate but do not eliminate these cultural gaps. We further show that downstream evaluations on bias benchmarks (such as CrowS-Pairs, IndiBias, ThaiCLI, KoBBQ) reveal persistent harms and under-representation in sensitive contexts. Our findings underscore the urgent need for systematic, regionally grounded audits to ensure equitable global deployment of LLMs.
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。
