分析大型语言模型（LLMs）中的叙事处理：使用GPT4测试BERT
Analyzing Narrative Processing in Large Language Models (LLMs): Using GPT4 to test BERT
AI总结：
本研究利用ChatGPT生成叙事风格变体并输入BERT，通过分析隐藏单元激活模式发现BERT浅层先编码风格、深层再编码内容，从而为理解LLMs内部机制及人脑语言处理提供新模型。
摘要：
通过语言传递和接收复杂信息的能力是人类独有的，也是传统、文化和多样化社会互动的基础。随着基于Transformer的大型语言模型（LLMs）的颠覆性引入，人类不再是唯一能够“理解”和生成语言的实体。在本研究中，我们迈出了将LLMs作为模型来理解神经网络中语言处理基本机制的第一步，以便对人类大脑如何进行语言处理做出预测并生成假设。为此，我们使用ChatGPT为十篇不同叙事（伊索寓言）生成了七种不同的风格变体。我们将这些故事作为开源LLM BERT的输入，并使用多维尺度分析和聚类分析对BERT隐藏单元的激活模式进行了分析。我们发现，隐藏单元的激活向量在BERT的较浅层（第1层）先根据风格变体聚类，之后（第4-5层）才根据叙事内容聚类。尽管BERT由12个相同且堆叠并在大型文本语料库上训练的构建模块组成，但不同层执行不同的任务。这是人脑的一个非常有用的模型，其中自相似结构，即大脑皮层的不同区域，可以具有不同的功能，因此非常适合以非常高效的方式处理语言。所提出的方法一方面有潜力打开LLMs的黑箱，另一方面可能是进一步揭示人类语言处理和一般认知背后神经过程的一步。
英文摘要：
The ability to transmit and receive complex information via language is unique to humans and is the basis of traditions, culture and versatile social interactions. Through the disruptive introduction of transformer based large language models (LLMs) humans are not the only entity to "understand" and produce language any more. In the present study, we have performed the first steps to use LLMs as a model to understand fundamental mechanisms of language processing in neural networks, in order to make predictions and generate hypotheses on how the human brain does language processing. Thus, we have used ChatGPT to generate seven different stylistic variations of ten different narratives (Aesop's fables). We used these stories as input for the open source LLM BERT and have analyzed the activation patterns of the hidden units of BERT using multi-dimensional scaling and cluster analysis. We found that the activation vectors of the hidden units cluster according to stylistic variations in earlier layers of BERT (1) than narrative content (4-5). Despite the fact that BERT consists of 12 identical building blocks that are stacked and trained on large text corpora, the different layers perform different tasks. This is a very useful model of the human brain, where self-similar structures, i.e. different areas of the cerebral cortex, can have different functions and are therefore well suited to processing language in a very efficient way. The proposed approach has the potential to open the black box of LLMs on the one hand, and might be a further step to unravel the neural processes underlying human language processing and cognition in general.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
