基于场景的大型语言模型文化价值观探测与引导——扩展版
Scenario-based Probing and Steering Cultural Values in Large Language Models--Extended Version
AI总结：
提出基于场景的行为困境方法，通过令牌级概率和激活引导探测并调整LLM在英格尔哈特-韦尔泽尔文化轴上的潜在价值观，发现不同文化维度的引导存在耦合效应。
摘要：
大型语言模型（LLM）被部署在不同文化背景下，但往往反映出从训练数据中继承的同质化价值观。对文化一致性的评估通常依赖于直接提示调查式问题，这常常引发中性或安全对齐的回应，无法捕捉模型的潜在偏好。我们提出了一个框架，用于沿着世界价值观调查（WVS）的英格尔哈特-韦尔泽尔两个轴探测和引导LLM中的潜在文化表征。通过将社会价值观问题转化为基于场景的行为困境，我们提取令牌级概率来测量隐含价值观，并应用激活引导（可选地与基于国家的提示结合），无需重新训练即可改变模型行为。在三个开源LLM和四种目标文化中，我们发现引导能力存在显著差异，并识别出潜在纠缠，即沿着一个文化维度的干预会引发另一个维度的变化。这种耦合反映了人类WVS数据中的相关性，并在激活、提示和混合引导中持续存在。它限制了轴独立的对齐，尽管一般任务性能基本保持。
英文摘要：
Large Language Models (LLMs) are deployed across cultural contexts but often reflect homogenized values inherited from training data. Evaluations of cultural alignment typically rely on direct prompting with survey-style questions, which frequently elicit neutral or safety-aligned responses and fail to capture underlying model preferences. We propose a framework for probing and steering latent cultural representations in LLMs along the two Inglehart--Welzel axes of the World Values Survey (WVS). By translating social value questions into scenario-based behavioral dilemmas, we extract token-level probabilities to measure implicit values and apply activation steering, optionally combined with country-conditioned prompting, to shift model behavior without retraining. Across three open-source LLMs and four target cultures, we find substantial variation in steerability and identify latent entanglement, where interventions along one cultural dimension induce shifts along another. This coupling mirrors correlations in human WVS data and persists across activation, prompt, and hybrid steering. It constrains axis-independent alignment, though general task performance is largely preserved.
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。
