Score: 2

Language Models Are Implicitly Continuous

Published: April 4, 2025 | arXiv ID: 2504.03933v1

By: Samuele Marro , Davide Evangelista , X. Angelo Huang and more

Potential Business Impact:

Computers see sentences as smooth, flowing ideas.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

Language is typically modelled with discrete sequences. However, the most successful approaches to language modelling, namely neural networks, are continuous and smooth function approximators. In this work, we show that Transformer-based language models implicitly learn to represent sentences as continuous-time functions defined over a continuous input space. This phenomenon occurs in most state-of-the-art Large Language Models (LLMs), including Llama2, Llama3, Phi3, Gemma, Gemma2, and Mistral, and suggests that LLMs reason about language in ways that fundamentally differ from humans. Our work formally extends Transformers to capture the nuances of time and space continuity in both input and output space. Our results challenge the traditional interpretation of how LLMs understand language, with several linguistic and engineering implications.

Country of Origin
🇬🇧 United Kingdom

Repos / Data Links

Page Count
41 pages

Category
Computer Science:
Computation and Language