Despite recent progress, large language models (LLMs) still face the
challenge of appropriately reacting to the intricacies of social and cultural
conventions. This paper presents MANGO, a methodology for distilling
high-accuracy, high-recall assertions of cultural knowledge. We judiciously and
iteratively prompt LLMs for this purpose from two entry points, concepts and
cultures. Outputs are consolidated via clustering and generative summarization.
Running the MANGO method with GPT-3.5 as underlying LLM yields 167K
high-accuracy assertions for 30K concepts and 11K cultures, surpassing prior
resources by a large margin. For extrinsic evaluation, we explore augmenting
dialogue systems with cultural knowledge assertions. We find that adding
knowledge from MANGO improves the overall quality, specificity, and cultural
sensitivity of dialogue responses, as judged by human annotators. Data and code
are available for download.

通过 MANGO 方法，从概念和文化两个入口点逐步指导大型语言模型，提取文化知识，通过聚类和生成式摘要方法合并，最终获得了 167K 个高准确性的关于 30K 个概念和 11K 个文化的表述，达到了非常显著的提升。将 MANGO 的知识应用于对话系统中，增强了对话系统的整体质量、特异性和文化敏感性，经过人工标注员评价证实。提供数据和代码下载。