一个模型，多种道德：揭示计算道德推理中的跨语言错位
One Model, Many Morals: Uncovering Cross-Linguistic Misalignments in Computational Moral Reasoning
AI总结：
本研究通过将道德推理基准翻译成五种语言，系统评估了LLMs的跨语言道德判断，发现显著不一致和文化错位，并提炼出道德推理错误类型学，呼吁更具文化意识的AI。
摘要：
大型语言模型（LLMs）越来越多地部署在需要道德推理以生成合乎伦理的响应的多语言和多文化环境中。然而，LLMs在英语数据上的主导预训练引发了对其在不同语言和文化背景下泛化判断能力的严重担忧。在这项工作中，我们系统地研究了语言如何调节LLMs中的道德决策。我们将两个成熟的道德推理基准翻译成五种文化和类型学上多样的语言，实现了多语言零样本评估。我们的分析揭示了LLMs在不同语言中的道德判断存在显著不一致，通常反映文化错位。通过一系列精心构建的研究问题，我们揭示了这些差异的潜在驱动因素，从分歧到LLMs采用的推理策略。最后，通过一个案例研究，我们将预训练数据在塑造LLM道德指南针中的作用联系起来。通过这项工作，我们将见解提炼为道德推理错误的结构化类型学，呼吁更具文化意识的AI。
英文摘要：
Large Language Models (LLMs) are increasingly deployed across multilingual and multicultural settings, yet it remains unclear whether changing language leads models to adopt community-specific moral reasoning or merely changes how shared learned abstractions are expressed. We conduct a controlled multilingual evaluation across six geographically, culturally, and linguistically diverse languages (Arabic, Chinese, English, Hindi, Russian, and Spanish), using parallel moral reasoning benchmarks with English-origin, Chinese-origin, and natively elicited ground-truth judgments. Across 13 open-weight LLMs spanning 2B-70B parameters, we find substantial cross-lingual divergence in moral judgments, with English generally achieving the highest performance even when ground-truth judgments originate in Chinese or are collected natively in each language. Yet the reasoning underlying these divergent judgments is considerably more convergent: Utilitarianism dominates in five of six languages, reasoning follows broadly shared stages, and language-specific moral-value associations correspond only sparsely and inconsistently to values measured in the corresponding human communities. Finally, a large-scale OLMoTrace analysis of pretraining data sources reveals little direct reproduction of training text across languages, while the corpus composition, training stage, and cultural provenance of retrieved training evidence vary substantially by response language. Thus, similar moral reasoning structures emerge even from heterogeneous and often linguistically localized training evidence. Our findings, collectively, reveal a central disconnect in multilingual moral reasoning: language changes models' moral judgments and the training evidence associated with their reasoning, but does not correspondingly localize the moral abstractions they apply.
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。
