神经侵蚀：在AI系统中模拟受控神经退行与衰老
Neural Erosion: Emulating Controlled Neurodegeneration and Aging in AI Systems
AI总结：
本文提出“神经侵蚀”方法，通过消融神经元或添加噪声模拟LLM（如LLaMA 2）的神经退行，发现其能力按抽象思维、数学、语言的顺序衰退，与人类认知衰退研究相符。
摘要：
在人工智能（AI）中创建受控方法来模拟神经退行，对于模拟大脑功能衰退和认知障碍的应用至关重要。我们利用大型语言模型（LLMs）执行的IQ测试，特别是LLaMA 2，引入了“神经侵蚀”的概念。这种刻意的侵蚀涉及在训练期间或之后消融突触或神经元，或添加高斯噪声，导致LLMs性能出现受控的渐进性下降。我们能够描述IQ测试中的神经退行过程，并表明LLM首先丧失数学能力，然后丧失语言能力，进而进一步丧失理解问题的能力。据我们所知，这是首个使用文本数据建模神经退行的工作，而其他工作则主要在计算机视觉领域进行。最后，我们将我们的研究与涉及受试者的认知衰退临床研究进行了类比。我们发现，随着神经退行性方法的应用，LLMs会先丧失抽象思维能力，随后出现数学能力退化，最终丧失语言能力，对提示作出不连贯的回应。这些发现与人类研究结果一致。
英文摘要：
Creating controlled methods to simulate neurodegeneration in artificial intelligence (AI) is crucial for applications that emulate brain function decline and cognitive disorders. We use IQ tests performed by Large Language Models (LLMs) and, more specifically, the LLaMA 2 to introduce the concept of ``neural erosion." This deliberate erosion involves ablating synapses or neurons, or adding Gaussian noise during or after training, resulting in a controlled progressive decline in the LLMs' performance. We are able to describe the neurodegeneration in the IQ tests and show that the LLM first loses its mathematical abilities and then its linguistic abilities, while further losing its ability to understand the questions. To the best of our knowledge, this is the first work that models neurodegeneration with text data, compared to other works that operate in the computer vision domain. Finally, we draw similarities between our study and cognitive decline clinical studies involving test subjects. We find that with the application of neurodegenerative methods, LLMs lose abstract thinking abilities, followed by mathematical degradation, and ultimately, a loss in linguistic ability, responding to prompts incoherently. These findings are in accordance with human studies.
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。
