Abstract
Large Language Models (LLMs) such as ChatGPT demonstrated the potential to replicate human language abilities through technology, ranging from text generation to engaging in conversations. However, it remains controversial to what extent these systems truly understand language. We examine this issue by narrowing the question down to the semantics of LLMs at the word and sentence level. By examining the inner workings of LLMs and their generated representation of language and by drawing on classical semantic theories by Frege and Russell, we get a more nuanced picture of the potential semantic capabilities of LLMs.
Abstract (translated)
大型语言模型（LLM），如ChatGPT，通过技术展现了复制人类语言能力的潜力，从文本生成到参与对话无所不包。然而，这些系统在多大程度上真正理解语言仍然是一个有争议的问题。我们通过对LLM语义进行细化研究——聚焦于单词和句子层面——来探讨这一问题。通过考察LLM内部工作机制及其对语言的表示方式，并借鉴弗雷格（Frege）和罗素（Russell）的经典语义理论，我们可以获得关于LLM潜在语义能力的一个更为细致的理解。
URL
https://arxiv.org/abs/2507.05448
