发现模型能力可定位，而非个体知识存储于特定参数。
Capability Localization: Capabilities Can be Localized rather than Individual Knowledge
- 提出共性神经元定位方法，识别具备通用能力的神经元。
- 在GSM8K数据集上实现96.42%神经元重叠率。
- 适用于研究模型内部能力分布与可解释性分析。
大规模语言模型在自然语言处理任务中表现优异，但其参数如何影响性能提升仍不明确。以往研究认为个体知识以分散参数、层或链的形式存储，缺乏统一性。通过可靠性与保真度评估实验，我们发现个体知识无法被精确定位。随后构建解耦实验数据集，揭示数据共性具有可定位潜力。本文提出共性神经元定位（CNL）方法，成功定位共性神经元，在GSM8K数据集上达到96.42%的神经元重叠率。跨数据集实验证明，共性神经元是具备提升性能能力的能力神经元集合。代码已开源。
原文摘要 · Abstract (English)
Large scale language models have achieved superior performance in tasks related to natural language processing, however, it is still unclear how model parameters affect performance improvement. Previous studies assumed that individual knowledge is stored in local parameters, and the storage form of individual knowledge is dispersed parameters, parameter layers, or parameter chains, which are not unified. We found through fidelity and reliability evaluation experiments that individual knowledge cannot be localized. Afterwards, we constructed a dataset for decoupling experiments and discovered the potential for localizing data commonalities. To further reveal this phenomenon, this paper proposes a Commonality Neuron Localization (CNL) method, which successfully locates commonality neurons and achieves a neuron overlap rate of 96.42% on the GSM8K dataset. Finally, we have demonstrated through cross data experiments that commonality neurons are a collection of capability neurons that possess the capability to enhance performance. Our code is available at https://github.com/nlpkeg/Capability-Neuron-Localization.
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。