激活引导的神经元干预以在大型语言模型中诱导阿尔茨海默病相关的计算语言表型
Activation-Guided Neuron Intervention to Induce Alzheimer's-Related Computational Language Phenotypes in a Large Language Model
浏览论文内容
中文总结 AI 辅助
本研究基于Qwen3-8B构建激活引导干预框架，通过缩放权重调节AD相关神经元，发现放大该神经元会导致多认知域功能损伤，减弱则多保留性能，为AD计算表型提供了概念验证。
中文摘要 AI 辅助
自发性言语的变化是阿尔茨海默病（AD）认知功能障碍的早期信号，大型语言模型（LLMs）可对其进行检测。但仅检测无法确定潜在的模型表征是否在功能上与行为相关。我们引入了一种基于激活引导的干预框架，使用Qwen3-8B模型。该框架识别出对AD转录本的激活率高于对照转录本的前馈神经元，并在生成过程中通过缩放对应的下投影权重来调节这些神经元的输出贡献。这产生了9种编辑变体，其干预方向、幅度和范围各不相同。原始模型与编辑模型完成了相同的12轮神经心理学测试，通过盲法人工评分和计算语言学指标进行评估。放大AD相关神经元会导致故事回忆、言语流畅性、工作记忆、程序性话语、场景构建和共指消解出现分级损伤；减弱则在很大程度上保留了性能，并选择性地改善了若干结果。放大还降低了词汇惊喜度、思想密度、句法复杂性和话语数量，与人类AD言语中报告的变化广泛平行。这些发现表明，仅从临床语言差异中识别出的神经元可影响多个认知领域的行为，为AD相关计算表型提供了概念验证，并为实验性研究语言与更广泛认知功能障碍之间的联系提供了可控框架。
英文摘要
Changes in spontaneous speech provide an early signal of cognitive dysfunction in Alzheimer's disease (AD) that large language models (LLMs) can detect. However, detection alone cannot establish whether the underlying model representations contribute functionally to behavior. We introduce an activation-guided intervention framework using Qwen3-8B. The framework identifies feed-forward neurons with higher activation rates for AD than control transcripts and modulates their output contributions during generation by scaling the corresponding down-projection weights. This yielded nine edited variants differing in intervention direction, magnitude, and scope. The original and edited models completed the same 12-turn neuropsychological battery, assessed through blinded human ratings and computational linguistic measures. Amplifying AD-associated neurons produced graded impairments in story recall, verbal fluency, working memory, procedural discourse, scene construction, and coreference resolution. Attenuation largely preserved performance and selectively improved several outcomes. Amplification also reduced lexical surprisal, idea density, syntactic complexity, and discourse quantity, broadly paralleling changes reported in human AD speech. These findings show that neurons identified solely from clinical language differences can influence behavior across multiple cognitive domains, providing proof of concept for an AD-related computational phenotype and a controlled framework for experimentally examining links between language and broader cognitive dysfunction.
