通过矩阵分析检测大模型权重相似性，支持低资源设备高效识别模型复用。
Matrix-Driven Identification and Reconstruction of LLM Weight Homology
- 基于矩阵分析与极分解，逐对比较权重矩阵识别对应关系。
- 在LeaFBench上实现AUC与准确率双满分，显著优于现有方法。
- 无需推理，适合检测模型抄袭或未授权复用，适用于边缘设备。
我们提出矩阵驱动的识别与重构方法（MDIR），一种先进的大语言模型同源性检测技术，可精确识别模型间的权重对应关系，并提供严格的统计显著性检验（$p$-值）。该方法无需模型推理，仅需逐对比较单个矩阵，可在低资源设备上检测未标注的权重复用或复制行为。通过结合矩阵分析、极分解和大偏差理论（LDT），MDIR实现了模型权重关系的精准重建。值得注意的是，MDIR是首个在LeaFBench数据集上对不同源模型均实现AUC与准确率双满分的方法。
原文摘要 · Abstract (English)
We propose Matrix-Driven Identification and Reconstruction (MDIR), a SOTA large language model homology method that accurately detects weight correspondences between models and provides rigorous $p$-value estimation of the statistical significance of these correspondences. Our method does not require model inference, and allows the detection of unattributed reuse or replication of model weights even on low-resource devices as it compares only a single pair of matrices at a time. We leverage matrix analysis, polar decomposition, and Large Deviation Theory (LDT) to achieve accurate reconstruction of weight relationships between models. Notably, MDIR is the first method to achieve perfect scores on both Area-Under-Curve (AUC) and accuracy metrics across different source models on LeaFBench.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。