谁的规范？解开大语言模型中的文化与个人对齐
Whose Norms? Disentangling Cultural and Personal Alignment in Large Language Models
AI总结：
提出PACT框架评估大语言模型在文化规范与个人偏好间的权衡，发现模型受国家背景影响大于年龄和性别，且人类对齐未能捕捉文化多元性。
摘要：
大语言模型越来越多地用于需要平衡文化规范与个人偏好的社会决策情境。例如，偏好诚实的用户可能会询问是否应在当地规范倾向于间接反馈时公开纠正同事。然而，现有研究大多将文化对齐和个性化分开研究。我们引入了PACT（个人偏好与文化规范权衡）框架，该框架评估模型是选择遵循文化规范还是允许个人偏好。我们发现，LLMs在强制执行文化规范的刚性程度上有所不同，行为受国家背景（7.8%）的影响大于年龄（1%）和性别（0.7%），并且在指令微调后非均匀地变化。此外，我们在五个国家进行的关于PACT的人类研究表明，人类遵循文化主要受情境国家驱动，当参与者判断自己的文化背景时一致性最低，显示出文化内部的多元性。最后，人类-LLM对齐实验表明，模型可以匹配多数选择，但未能捕捉响应分布和不确定性（最佳相关性仅为0.24）。总之，这些发现激励了超越多数、捕捉社会判断中文化多元性和分歧的对齐评估。
英文摘要：
Large language models are increasingly used for social decision-making situations that require balancing cultural norms with personal preferences. For example, a user preferring honesty might ask whether to correct a coworker publicly when local norms favor indirect feedback. Yet existing research studies cultural alignment and personalization largely separately. We introduce PACT, the Personal-Preference and Cultural-Norm Trade-off framework, which evaluates whether models choose to follow a cultural norm or allow personal preferences. We find that LLMs vary in how rigidly they enforce cultural norms, with behavior shifted more by country context (7.8%) than age (1%) and gender (0.7%) and shifting non-uniformly after instruction tuning. Furthermore, our five-country human study on PACT shows that culture-following in humans is mainly driven by scenario country, with the lowest agreement when participants judge their own cultural contexts, showing within-culture pluralism. Finally, human-LLM alignment experiments show that models can match majority choices, but fail to capture response distributions and uncertainty (with best correlations reaching only 0.24). Together, these findings motivate alignment evaluations that go beyond majority to capture cultural pluralism and disagreement in social judgment.
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。
