LLMs作为文化档案：文化常识知识图谱提取
LLMs as Cultural Archives: Cultural Commonsense Knowledge Graph Extraction
AI总结：
本文提出一种基于提示的框架，用于构建文化常识知识图谱，通过LLMs作为文化档案提取文化特定知识，提升文化推理和故事生成性能。
摘要：
大型语言模型（LLMs）编码了从多样化网络级数据中学习到的丰富文化知识，为大规模建模文化常识提供了前所未有的机会。然而，这种知识大多仍隐含且无结构，限制了其可解释性和使用。我们提出了一种迭代的、基于提示的框架，用于构建文化常识知识图谱（CCKG），将LLMs视为文化档案，系统地提取文化特定的实体、关系和实践，并将它们组合成跨语言的多步骤推断链。我们在五个国家上评估CCKG，使用人类对文化相关性、正确性和路径连贯性的判断。我们发现，文化知识图谱在英语中实现得更好，即使目标文化不是英语（例如中文、印度尼西亚语、阿拉伯语），这表明当前LLMs在文化编码上存在不均衡。通过将较小的LLMs与CCKG增强，可以提高文化推理和故事生成的性能，其中英语链带来的最大收益最为显著。我们的结果表明了LLMs作为文化技术的潜力和局限性，并且链式结构的文化知识是文化导向NLP的实用基础。
英文摘要：
Large language models (LLMs) encode rich cultural knowledge learned from diverse web-scale data, offering an unprecedented opportunity to model cultural commonsense at scale. Yet this knowledge remains mostly implicit and unstructured, limiting its interpretability and use. We present an iterative, prompt-based framework for constructing a Cultural Commonsense Knowledge Graph (CCKG) that treats LLMs as cultural archives, systematically eliciting culture-specific entities, relations, and practices and composing them into multi-step inferential chains across languages. We evaluate CCKG on five countries with human judgments of cultural relevance, correctness, and path coherence. We find that the cultural knowledge graphs are better realized in English, even when the target culture is non-English (e.g., Chinese, Indonesian, Arabic), indicating uneven cultural encoding in current LLMs. Augmenting smaller LLMs with CCKG improves performance on cultural reasoning and story generation, with the largest gains from English chains. Our results show both the promise and limits of LLMs as cultural technologies and that chain-structured cultural knowledge is a practical substrate for culturally grounded NLP.
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。
