On the Semantics of Large Language Models
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 42 references that are in the map. First posted on arXiv 7 Jul 2025.
Builds on
13 of 42 references.
References · 13
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
- 2020Scaling Laws for Neural Language Modelscited by 6,586
- 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
- 2017Deep reinforcement learning from human preferencescited by 3,912
- 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
- 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
- 2023A Survey on Evaluation of Large Language Modelscited by 1,242
- 2020A Primer in BERTology: What we know about how BERT workscited by 815
- 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 767
- 2022Meaning without reference in large language modelscited by 76
- 2023Break It Down: Evidence for Structural Compositionality in Neural Networkscited by 44
1 more
- 2023The Vector Grounding Problemcited by 39
Built on by
Not cited yet.