Reasoning in Large Language Models: A Geometric Perspective
This work addresses the problem of enhancing reasoning capabilities in LLMs for real-world applications, but it appears incremental as it builds on existing geometric frameworks without introducing a new method.
The paper investigates the reasoning abilities of large language models by connecting their expressive power to the density of self-attention graphs, showing that higher intrinsic dimensions correlate with greater expressive capacity through theoretical analysis and toy examples.
The advancement of large language models (LLMs) for real-world applications hinges critically on enhancing their reasoning capabilities. In this work, we explore the reasoning abilities of large language models (LLMs) through their geometrical understanding. We establish a connection between the expressive power of LLMs and the density of their self-attention graphs. Our analysis demonstrates that the density of these graphs defines the intrinsic dimension of the inputs to the MLP blocks. We demonstrate through theoretical analysis and toy examples that a higher intrinsic dimension implies a greater expressive capacity of the LLM. We further provide empirical evidence linking this geometric framework to recent advancements in methods aimed at enhancing the reasoning capabilities of LLMs.