发表机构
Siebel School of Computing and Data Science; The Grainger College of Engineering; University of Illinois Urbana-Champaign（西贝尔计算与数据科学学院; 格兰杰工程学院; 伊利诺伊大学厄巴纳-香槟分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文综述了线性表示假说（LRH）在各领域的应用，指出其缺乏可证伪性，提出更严谨的形式化定义以明确依赖关系，并指出了若干开放问题。
AI 中文摘要
术语“线性表示假说”（LRH）已出现在人工智能、神经科学和认知科学的多个子领域。但以往的研究并未一致地将LRH视为可证伪的科学假说；我们分析了这些不一致之处，并考察了它们对先前理论和方法学结果应如何解读的影响。基于这一分析，我们认为，关于线性表示的论断只有在仔细考察模型、表示位置、特征定义和评估数据集后才变得明确。因此，我们提出了一个更严谨的LRH形式化定义，该定义使这些依赖关系明确化，并允许将该假说作为可证伪的科学主张进行评估。最后，我们识别了一些值得研究界进一步关注的非平凡开放问题。
英文摘要
The term "linear representation hypothesis" (LRH) has appeared across diverse subfields of artificial intelligence, neuroscience, and cognitive science. But previous works have not consistently treated the LRH as a falsifiable scientific hypothesis; we analyze these inconsistencies and examine their implications for how prior theoretical and methodological results should be interpreted. Based on this analysis, we argue that claims regarding linear representations become well-defined only through careful examination of the model, representation location, feature definition, and evaluation dataset. We therefore propose a more rigorous formalization of the LRH that makes these dependencies explicit and allows the hypothesis to be evaluated as a falsifiable scientific claim. Finally, we identify some non-trivial open problems that warrant further attention from the research community.
