ValuesRAG：通过检索增强的上下文学习提升文化对齐
ValuesRAG: Enhancing Cultural Alignment Through Retrieval-Augmented Contextual Learning
AI总结：
ValuesRAG框架通过将检索增强生成与上下文学习相结合，利用世界价值观调查数据集动态整合文化知识，在多个区域数据集上一致优于零样本、少样本等基线方法，有效提升了大语言模型的文化对齐能力。
摘要：
确保大语言模型（LLMs）中的文化价值观对齐仍然是一个关键挑战，因为这些模型往往在其训练数据中嵌入以西方为中心的偏见，导致在跨文化应用中产生误表征和公平性问题。现有方法如角色分配和少样本学习由于依赖预训练知识、可扩展性有限以及无法捕捉细微的文化价值观，难以有效解决这些局限性。为了解决这些问题，我们提出了ValuesRAG，这是一个新颖且有效的框架，它将检索增强生成（RAG）与上下文学习（ICL）相结合，在文本生成过程中动态整合文化和人口统计知识。利用世界价值观调查（WVS）数据集，ValuesRAG首先为每个个体生成价值观摘要。随后，我们构建了多个具有代表性的区域数据集作为测试数据集，并根据人口统计特征检索相关的价值观摘要，接着通过重排序步骤选择top-k个最相关的摘要。我们使用6个多样化的区域数据集对ValuesRAG进行评估，结果表明它在主实验和消融设置中均一致优于基线方法，包括零样本、角色分配、少样本和混合方法。值得注意的是，ValuesRAG取得了优于先前方法的最佳整体性能，证明了其在促进文化对齐和包容性AI系统方面的有效性。我们的发现强调了基于动态检索的方法在弥合全球LLM能力与本地化文化价值观之间差距方面的潜力。
英文摘要：
Ensuring cultural values alignment in Large Language Models (LLMs) remains a critical challenge, as these models often embed Western-centric biases from their training data, leading to misrepresentations and fairness concerns in cross-cultural applications. Existing approaches such as role assignment and few-shot learning struggle to address these limitations effectively due to their reliance on pre-trained knowledge, limited scalability, and inability to capture nuanced cultural values. To address these issues, we propose ValuesRAG, a novel and effective framework that applies Retrieval-Augmented Generation (RAG) with In-Context Learning (ICL) to integrate cultural and demographic knowledge dynamically during text generation. Leveraging the World Values Survey (WVS) dataset, ValuesRAG first generates summaries of values for each individual. We subsequently curate several representative regional datasets to serve as test datasets and retrieve relevant summaries of values based on demographic features, followed by a reranking step to select the top-k relevant summaries. We evaluate ValuesRAG using 6 diverse regional datasets and show that it consistently outperforms baselines: including zero-shot, role-assignment, few-shot, and hybrid methods, both in main experiments and ablation settings. Notably, ValuesRAG achieves the best overall performance over prior methods, demonstrating its effectiveness in fostering culturally aligned and inclusive AI systems. Our findings underscore the potential of dynamic retrieval-based methods to bridge the gap between global LLM capabilities and localized cultural values.
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。
