探索语言模型中神经激活与概念分类的关联性。
Neuropsychology of AI: Relationship Between Activation Proximity and Categorical Proximity Within Neural Categories of Synthetic Cognition
- 用认知心理学的分类概念解析大模型内部表征。
- 发现神经激活距离与语义类别距离存在强相关性。
- 为理解模型内部逻辑提供类脑解释新视角。
人工智能神经科学关注合成神经认知作为认知心理学中的新研究对象。为提升语言模型人工神经网络的可解释性，该方法将认知心理学概念移植到人工神经认知的解释性构建中。此处涉及的人类认知概念是分类，它作为理解合成认知神经向量对现实进行分割与建构过程的启发式工具。
原文摘要 · Abstract (English)
Neuropsychology of artificial intelligence focuses on synthetic neural cog nition as a new type of study object within cognitive psychology. With the goal of making artificial neural networks of language models more explainable, this approach involves transposing concepts from cognitive psychology to the interpretive construction of artificial neural cognition. The human cognitive concept involved here is categorization, serving as a heuristic for thinking about the process of segmentation and construction of reality carried out by the neural vectors of synthetic cognition.
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。