探究大模型如何理解与表达地理知识，揭示其潜在偏见与脆弱性。
Geography According to ChatGPT -- How Generative AI Represents and Reasons about Geography
- 通过三类探针实验考察模型对地理信息的默认认知与语法敏感性。
- 发现微小语句变化可导致地理输出显著差异，体现模型推理脆弱性。
- 适合关注AI地理认知、伦理与可信度的研究者与政策制定者。
理解人工智能如何表征和推理地理信息应成为我们共同关注的重点，因为公众越来越多地通过这些系统与空间场所互动。同时，鉴于基础模型的特性，我们的研究也常依赖预训练模型。因此，理解人工智能系统构建的世界观，与评估其准确性（包括事实回忆）同样重要。为激发此类研究，本文提供三个示例性探针（探索性测试），旨在引发热烈讨论并推动后续工作：(1) 模型是否形成强烈默认假设，其输出对细微语法变化有多脆弱？(2) 当使用人工智能系统生成人物角色时，单个无害任务的组合是否会重现分布偏移？(3) 仅关注系统能否回忆地理事实（如地理原理）时，我们是否忽略了更深层的理解问题？
原文摘要 · Abstract (English)
Understanding how AI will represent and reason about geography should be a key concern for all of us, as the broader public increasingly interacts with spaces and places through these systems. Similarly, in line with the nature of foundation models, our own research often relies on pre-trained models. Hence, understanding what world AI systems construct is as important as evaluating their accuracy, including factual recall. To motivate the need for such studies, we provide three illustrative vignettes, i.e., exploratory probes, in the hope that they will spark lively discussions and follow-up work: (1) Do models form strong defaults, and how brittle are model outputs to minute syntactic variations? (2) Can distributional shifts resurface from the composition of individually benign tasks, e.g., when using AI systems to create personas? (3) Do we overlook deeper questions of understanding when solely focusing on the ability of systems to recall facts such as geographic principles?
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。