量化评估AI生成故事的文化本地化程度，发现多数内容依赖通用模板。
Characterizing Cultural Localization in AI-Generated Stories
- 通过移除国家差异词汇，比较剩余叙事相似性来测量模板化程度。
- 仅9-17%词汇区分不同国家故事，其余为重复的通用叙事片段。
- 19个全球南方国家的文化标记平均更具刻板印象和冒犯性。
人工智能在全球范围的应用激起了对其生成文化本地化内容能力的关注，尤其是故事生成。文化本地化可分为模板化本地化（仅用文化标识如名字、地点填充通用叙事）和整体化本地化（情节、价值观、主题均调整）。本文提出一种方法，衡量内容由模板化本地化产生的程度：识别在不同国籍故事间具有区分性的词元，并计算去除这些词元后剩余叙事的相似性。在五个模型对125个主题、193个国籍生成的故事中，发现仅9-17%的词汇用于区分国家差异，而剩余部分包含重复的多词序列，表明存在共享的、无文化的通用叙事模板。此外，我们分析了文化标记的刻板印象性和冒犯性，发现来自19个国家（多为全球南方）的标记平均更具冒犯性。
原文摘要 · Abstract (English)
The global use of artificial intelligence has increased interest in assessing the ability to generate culturally localized content, including stories. Cultural localization in stories often occurs through either templated localization -- the use of cultural markers (e.g., names, locations) in a generic narrative -- or holistic localization -- the variation of plots, values, and themes, in addition to cultural markers. We propose a method to measure the degree to which content was generated through templated localization. Specifically, we identify the lexical tokens that distinguish stories across nationalities and measure the similarity of the narratives that remain after removing them. In stories generated by five models on 125 topics for 193 nationalities, our method is able to detect that only a small subset (9-17%) of the vocabulary accounts for the variation across nationalities and that the narratives that remain after removing them contain repeated multi-word sequences, suggesting the presence of a shared culturally-agnostic narrative template. Finally, we characterize the cultural markers for their stereotypicality and offensiveness, finding that markers from 19 countries, mostly located in the Global South, are on average offensive.
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。