|国家预印本平台
首页|Neuron-based Multifractal Analysis of Neuron Interaction Dynamics in Large Models

Neuron-based Multifractal Analysis of Neuron Interaction Dynamics in Large Models

Neuron-based Multifractal Analysis of Neuron Interaction Dynamics in Large Models

来源:Arxiv_logoArxiv
英文摘要

In recent years, there has been increasing attention on the capabilities of large models, particularly in handling complex tasks that small-scale models are unable to perform. Notably, large language models (LLMs) have demonstrated ``intelligent'' abilities such as complex reasoning and abstract language comprehension, reflecting cognitive-like behaviors. However, current research on emergent abilities in large models predominantly focuses on the relationship between model performance and size, leaving a significant gap in the systematic quantitative analysis of the internal structures and mechanisms driving these emergent abilities. Drawing inspiration from neuroscience research on brain network structure and self-organization, we propose (i) a general network representation of large models, (ii) a new analytical framework, called Neuron-based Multifractal Analysis (NeuroMFA), for structural analysis, and (iii) a novel structure-based metric as a proxy for emergent abilities of large models. By linking structural features to the capabilities of large models, NeuroMFA provides a quantitative framework for analyzing emergent phenomena in large models. Our experiments show that the proposed method yields a comprehensive measure of network's evolving heterogeneity and organization, offering theoretical foundations and a new perspective for investigating emergent abilities in large models.

Paul Bogdan、Yi-Zhuo Zhou、Shixuan Li、Nikos Kanakaris、Xiongye Xiao、Heng Ping、Chenyu Zhou、Defu Cao、Yaxing Li

计算技术、计算机技术

Paul Bogdan,Yi-Zhuo Zhou,Shixuan Li,Nikos Kanakaris,Xiongye Xiao,Heng Ping,Chenyu Zhou,Defu Cao,Yaxing Li.Neuron-based Multifractal Analysis of Neuron Interaction Dynamics in Large Models[EB/OL].(2025-08-06)[2025-08-23].https://arxiv.org/abs/2402.09099.点此复制

评论