模型生成的旅行推荐和故事，对穷国更不精准、情感更消极。
Richer Output for Richer Countries: Uncovering Geographical Disparities in Generated Stories and Travel Recommendations
- 用10万条旅行请求和20万条故事测试5个主流模型
- 穷国推荐少地点信息，故事更常表达苦难与悲伤
- 揭示了语言模型在地理偏见上的现实影响，适合关注AI公平性的研究者
尽管已有大量研究关注语言模型在性别、种族、职业和宗教方面的偏见，地理偏见仍较少被探索。一些近期研究评估了大语言模型编码地理空间知识的程度，但其编码知识（或缺乏）对真实应用场景的影响尚未被记录。本文考察了两种需要地理知识的常见场景：(a) 旅行推荐和 (b) 地理锚定的故事生成。我们测试了五个流行的语言模型，在约10万条旅行请求和20万条故事生成中发现，对应较贫穷国家的旅行推荐更缺乏独特性，地点提及较少；来自这些地区的故事情绪更常体现艰难与悲伤，相较富裕国家更为明显。
原文摘要 · Abstract (English)
While a large body of work inspects language models for biases concerning gender, race, occupation and religion, biases of geographical nature are relatively less explored. Some recent studies benchmark the degree to which large language models encode geospatial knowledge. However, the impact of the encoded geographical knowledge (or lack thereof) on real-world applications has not been documented. In this work, we examine large language models for two common scenarios that require geographical knowledge: (a) travel recommendations and (b) geo-anchored story generation. Specifically, we study five popular language models, and across about $100$K travel requests, and $200$K story generations, we observe that travel recommendations corresponding to poorer countries are less unique with fewer location references, and stories from these regions more often convey emotions of hardship and sadness compared to those from wealthier nations.
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。