多语言大模型的政治观点在西语间高度一致，跨语言迁移明显。
Do Political Opinions Transfer Between Western Languages? An Analysis of Unaligned and Aligned Multilingual LLMs
- 用投票建议语料提示模型，测试五种西语的政治立场。
- 未对齐模型跨语言观点差异极小，对齐后全语言统一偏移。
- 适合关注多语言模型文化偏见与对齐策略的研究者。
民意调查显示不同社会文化背景下政治观点存在跨文化差异。然而，这些差异是否体现在多语言大模型（MLLMs）的跨语言表现中尚不明确。本文分析了不同规模的多语言大模型在五种西方语言中政治观点的传递性，通过提示模型对投票建议应用中的政治陈述表达同意或反对。为理解语言间的交互机制，我们在仅使用英文对齐数据的情况下，采用直接偏好优化对模型进行左倾或右倾对齐，并对比对齐前后的表现。结果表明，未对齐模型反映的政治观点在跨语言间仅有极少显著差异；而对齐后，政治立场几乎在所有语言中同步发生偏移。结论是：在西方语言语境下，政治观点具有跨语言传递性，这凸显了实现多语言模型显式社会-语言-文化-政治对齐的挑战。
原文摘要 · Abstract (English)
Public opinion surveys show cross-cultural differences in political opinions between socio-cultural contexts. However, there is no clear evidence whether these differences translate to cross-lingual differences in multilingual large language models (MLLMs). We analyze whether opinions transfer between languages or whether there are separate opinions for each language in MLLMs of various sizes across five Western languages. We evaluate MLLMs' opinions by prompting them to report their (dis)agreement with political statements from voting advice applications. To better understand the interaction between languages in the models, we evaluate them both before and after aligning them with more left or right views using direct preference optimization and English alignment data only. Our findings reveal that unaligned models show only very few significant cross-lingual differences in the political opinions they reflect. The political alignment shifts opinions almost uniformly across all five languages. We conclude that in Western language contexts, political opinions transfer between languages, demonstrating the challenges in achieving explicit socio-linguistic, cultural, and political alignment of MLLMs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。