挑战世界模型是否真能代表人工智能理解，揭示其与人类认知的差距
Beyond World Models: Rethinking Understanding in AI Models
- 用科学哲学案例分析世界模型与人类理解的本质区别
- 指出世界模型无法捕捉人类理解中的因果深度与情境依赖
- 适合对AI认知本质感兴趣的学者和研究者
世界模型在人工智能领域备受关注，这类内部表征可模拟外部世界、追踪实体与状态、捕捉因果关系，并预测后果，与仅基于统计相关性的表征形成对比。该研究方向的核心动机是：人类拥有此类心理世界模型，若能在AI模型中发现类似表征，或可表明其具备类人理解能力。本文借助科学哲学文献中的典型案例，批判性审视世界模型框架是否足以刻画人类水平的理解。聚焦于人类理解与世界模型能力差异最显著的哲学分析，尽管这些观点并非普遍定义，但有助于揭示世界模型的局限性。
原文摘要 · Abstract (English)
World models have garnered substantial interest in the AI community. These are internal representations that simulate aspects of the external world, track entities and states, capture causal relationships, and enable prediction of consequences. This contrasts with representations based solely on statistical correlations. A key motivation behind this research direction is that humans possess such mental world models, and finding evidence of similar representations in AI models might indicate that these models "understand" the world in a human-like way. In this paper, we use case studies from the philosophy of science literature to critically examine whether the world model framework adequately characterizes human-level understanding. We focus on specific philosophical analyses where the distinction between world model capabilities and human understanding is most pronounced. While these represent particular views of understanding rather than universal definitions, they help us explore the limits of world models.
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。