Saved in:
Bibliographic Details
Main Author: Schuele, Martin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.05448
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913932045713408
author Schuele, Martin
author_facet Schuele, Martin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_05448
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On the Semantics of Large Language Models
Schuele, Martin
Computation and Language
Artificial Intelligence
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.
title On the Semantics of Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2507.05448