相同的价值观，不同的语言？从多语言探针到引导大语言模型趋向中国社会价值观

中文摘要 AI 辅助

随着大语言模型（LLMs）日益融入人类社会，使其与多元社会价值观对齐已成为一个关键优先事项。然而，LLMs在不同语言中是否表现出一致的价值观偏好仍未得到充分探索，尤其是对于文化根基深厚的价值观，这些价值观比以安全为中心的原则更为抽象，难以评估和对齐。我们通过中国社会价值观（CSV）来研究这一问题，CSV是一个根植于中国文化、包含国家、社会和个人三个层面的12个维度的价值体系。我们构建了C-Voices，这是首个针对CSV的全面多语言对比探针数据集，包含六种语言、86,400个基于困境的实例，每个实例将一个符合CSV的行为与一个冲突的替代行为配对。基于C-Voices的对比探针，我们进一步提出了一种无需微调的价值观向量引导方法，该方法从隐藏状态差异中推导价值观方向，并在推理过程中选择性地干预对价值观敏感的层。在六种语言上的实验表明，CSV导向的偏好是模型依赖且语言敏感的，同一困境在不同语言中引发不同的反应。我们的方法实现了有效的CSV引导，支持价值观向量的跨语言迁移，并推广到现有的FLAMES和ValuePrism。

英文摘要

As Large Language Models (LLMs) are increasingly integrated into human society, aligning them with pluralistic social values has become a critical priority. However, whether LLMs exhibit consistent value preferences across languages remains underexplored, particularly for culturally grounded values, which are more abstract and difficult to evaluate and align than safety-centric principles. We investigate this issue through Chinese Social Values (CSV), a value system rooted in Chinese culture and comprising $12$ dimensions across national, societal, and personal levels. We construct C-Voices, the first comprehensive multilingual contrastive probe dataset for CSV, with 86,400 dilemma-based instances in six languages, each pairing a CSV-aligned action with a value-conflicting alternative. Building on the contrastive probes of C-Voices, we then propose a fine-tuning-free value vector steering method that derives value directions from hidden-state discrepancies and selectively intervenes on value-sensitive layers during inference. Experiments on six languages show that CSV-oriented preferences are model-dependent and language-sensitive, with the same dilemma eliciting divergent responses across languages. Our method achieves effective CSV steering, supports cross-lingual transfer of value vectors, and generalizes to existing FLAMES and ValuePrism.

发表机构

• School of Information Science and Technology, Beijing Foreign Studies University（北京外国语大学信息科学与技术学院）
• Beijing Academy of Artificial Intelligence（北京人工智能研究院）
• Beihang University（北京航空航天大学）

机构由 AI 辅助整理，请以论文原文为准。