发现大模型中类似人类脑区的语法神经元，能精准预测词性。
On the Analogy between Human Brain and LLMs: Spotting Key Neurons in Grammar Perception
- 通过激活模式分析，在Llama 3中定位关键词性预测神经元。
- 这些神经元激活模式可准确分类新数据的词性标签。
- 揭示大模型存在类脑的词性概念子空间，适用于语言机制研究。
人工神经网络源于人脑神经元网络，近年来已具备图像与语言处理等复杂能力。在大语言模型领域，研究者希望让语言学习更接近人类。神经科学研究表明，大脑不同语法类别由不同神经元处理；本研究发现大语言模型也呈现类似机制。利用Llama 3，我们识别出对词性标签预测最关键的神经元，并基于其激活模式训练分类器，该分类器在新数据上表现可靠。结果表明，大模型中存在一个专门捕捉词性概念的子空间，其特征与神经科学中的脑损伤研究结果相似。
原文摘要 · Abstract (English)
Artificial Neural Networks, the building blocks of AI, were inspired by the human brain's network of neurons. Over the years, these networks have evolved to replicate the complex capabilities of the brain, allowing them to handle tasks such as image and language processing. In the realm of Large Language Models, there has been a keen interest in making the language learning process more akin to that of humans. While neuroscientific research has shown that different grammatical categories are processed by different neurons in the brain, we show that LLMs operate in a similar way. Utilizing Llama 3, we identify the most important neurons associated with the prediction of words belonging to different part-of-speech tags. Using the achieved knowledge, we train a classifier on a dataset, which shows that the activation patterns of these key neurons can reliably predict part-of-speech tags on fresh data. The results suggest the presence of a subspace in LLMs focused on capturing part-of-speech tag concepts, resembling patterns observed in lesion studies of the brain in neuroscience.
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。