大模型可能具备隐性知识，能解释其推理与行为机制。
What Do Large Language Models Know? Tacit Knowledge as a Potential Causal-Explanatory Structure
- 用隐性知识框架分析大模型的认知结构
- 发现大模型满足语义描述与因果系统性约束
- 为理解模型行为提供新视角，适合认知科学与AI研究者
有观点认为大型语言模型（LLMs）掌握语言，例如知道巴黎是法国首都。但它们究竟知道什么？本文提出，尽管马丁·戴维斯（Martin Davies, 1990）认为神经网络无法获得隐性知识，但某些大模型的架构特征符合隐性知识的语义描述、句法结构和因果系统性要求。因此，隐性知识可作为描述、解释并干预大模型行为的概念框架。这一视角有助于深入理解模型内部运作机制。
原文摘要 · Abstract (English)
It is sometimes assumed that Large Language Models (LLMs) know language, or for example that they know that Paris is the capital of France. But what -- if anything -- do LLMs actually know? In this paper, I argue that LLMs can acquire tacit knowledge as defined by Martin Davies (1990). Whereas Davies himself denies that neural networks can acquire tacit knowledge, I demonstrate that certain architectural features of LLMs satisfy the constraints of semantic description, syntactic structure, and causal systematicity. Thus, tacit knowledge may serve as a conceptual framework for describing, explaining, and intervening on LLMs and their behavior.
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。