Understanding the similarity of the numerous released large language models (LLMs) 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.
@article{arxiv.2312.02730,
title = {Towards Measuring Representational Similarity of Large Language Models},
author = {Max Klabunde and Mehdi Ben Amor and Michael Granitzer and Florian Lemmerich},
journal= {arXiv preprint arXiv:2312.02730},
year = {2023}
}
Comments
Extended abstract in UniReps Workshop @ NeurIPS 2023