探究大模型如何通过相似性推断属性，发现分类与相似度共同作用。
Characterizing the Role of Similarity in the Property Inferences of Language Models
- 结合行为实验与表征分析，研究大模型的属性继承机制。
- 分类相关且语义相似的类别更易传递新属性，二者协同作用。
- 为理解模型概念结构提供依据，适合认知科学与NLP交叉研究者。
属性继承——即从高级类别（如鸟类）向低级类别（如麻雀）投射新属性的现象——为人类概念知识的组织与运用提供了独特视角。该能力是源于显式存储的分类知识，还是基于心理表征间相似性的简单计算，仍存在争议。本研究通过行为实验与因果表征分析，考察大模型在属性继承中的表现。结果表明，分类关系与类别相似性在大模型的属性继承行为中并非互斥，当类别既具有分类关联又语义高度相似时，模型更倾向于将新属性从一类传递到另一类。研究揭示了语言模型的概念结构特征，或可启发针对人类被试的新心理语言学实验。
原文摘要 · Abstract (English)
Property inheritance -- a phenomenon where novel properties are projected from higher level categories (e.g., birds) to lower level ones (e.g., sparrows) -- provides a unique window into how humans organize and deploy conceptual knowledge. It is debated whether this ability arises due to explicitly stored taxonomic knowledge vs. simple computations of similarity between mental representations. How are these mechanistic hypotheses manifested in contemporary language models? In this work, we investigate how LMs perform property inheritance with behavioral and causal representational analysis experiments. We find that taxonomy and categorical similarities are not mutually exclusive in LMs' property inheritance behavior. That is, LMs are more likely to project novel properties from one category to the other when they are taxonomically related and at the same time, highly similar. Our findings provide insight into the conceptual structure of language models and may suggest new psycholinguistic experiments for human subjects.
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。