通过模拟社会互动训练大模型理解不同文化，提升其价值观对齐能力。
Cultural Learning-Based Culture Adaptation of Language Models
- 用角色扮演模拟跨文化社交场景生成训练数据
- 在世界价值观调查数据上验证了多架构模型的对齐提升
- 适合关注AI伦理与跨文化适配的研究者
将大型语言模型（LLMs）适配至多元文化价值观是一项挑战，因现有模型默认反映特定群体的价值观，可能对其他群体造成伤害。本文提出基于文化学习的CLCA框架，通过模拟社会互动生成大模型在文化适应性社会情境中进行角色扮演的对话，捕捉隐含的文化规范用于模型微调。该方法在多种模型架构上提升了文化价值观对齐效果，使用世界价值观调查（World Value Survey）数据进行评估，证明了文化学习训练策略的有效性。结果表明，理解意图与社会互动有助于增强大模型的文化价值适应能力，展示了基于文化学习的训练路径的潜力。
原文摘要 · Abstract (English)
Adapting large language models (LLMs) to diverse cultural values is a challenging task, as existing LLMs often reflect the values of specific groups by default, and potentially causing harm to others. In this paper, we present CLCA, a novel framework for enhancing LLM alignment with cultural values based on cultural learning. The framework leverages simulated social interactions to generate conversations in which LLMs engage in role-playing within culturally adapted social scenarios, capturing implicit cultural norms for model fine-tuning. CLCA improves cultural value alignment across various model architectures measured using World Value Survey data, demonstrating the effectiveness of our proposed approach. Our results provide early evidence that understanding intent and social interactions can enhance cultural value adaptation in LLMs, highlighting the promise of training approaches based on cultural learning.
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。