Towards Measuring Representational Similarity of Large Language Models

Max Klabunde, Mehdi Ben Amor, Michael Granitzer, Florian Lemmerich

Keywords: neural network similarity, large language models, representational similarity

Abstract: Understanding the similarity of the numerous large language models released has many uses, e.g., simplifying model selection, detecting illegal model reuse, and advancing our understanding of what makes LLMs perform well. In this work, we measure the similarity of representations of a set of LLMs with 7B parameters. Our results suggest that some LLMs are substantially different from others. We identify challenges of using representational similarity measures that suggest the need of careful study of similarity scores to avoid false conclusions.

Track: Extended Abstract Track

Submission Number: 29