# DOCS: Quantifying Weight Similarity for Deeper Insights into Large Language Models

arXiv: https://arxiv.org/abs/2501.16650 · HTML: https://mlsanity.com/paper/2501.16650/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jan 2025.

## Built on by (most cited first, 4 of 4)

- [Low-Rank Adaptation Redux for Large Models](https://mlsanity.com/paper/2604.21905/) (2026)
- [Addressing the Collaboration Dilemma in Low-Data Federated Learning via Transient Sparsity](https://mlsanity.com/paper/2506.00932/) (2025)
- [Why Geometric Continuity Emerges in Deep Neural Networks: Residual Connections and Rotational Symmetry Breaking](https://mlsanity.com/paper/2605.04971/) (2026)
- [Gradient-free Task-Conditioned Retrieval for On-Device In-Context Learning](https://mlsanity.com/paper/2607.27766/) (2026)

## Abstract (arXiv)

We introduce a novel index, the Distribution of Cosine Similarity (DOCS), for quantitatively assessing the similarity between weight matrices in Large Language Models (LLMs), aiming to facilitate the analysis of their complex architectures. Leveraging DOCS, our analysis uncovers intriguing patterns in the latest open-source LLMs: adjacent layers frequently exhibit high weight similarity and tend to form clusters, suggesting depth-wise functional specialization. Additionally, we prove that DOCS is theoretically effective in quantifying similarity for orthogonal matrices, a crucial aspect given the prevalence of orthogonal initializations in LLMs. This research contributes to a deeper understanding of LLM architecture and behavior, offering tools with potential implications for developing more efficient and interpretable models.