基于大脑活动的阅读与操控LLM状态的轴
Brain-Grounded Axes for Reading and Steering LLM States
AI总结：
本文提出利用人类大脑活动作为坐标系，通过ICA提取潜在轴，操控LLM状态，实现可解释和可控的LLM行为。
摘要：
针对大型语言模型（LLM）的可解释性方法通常从文本监督中推导方向，这可能导致缺乏外部参照。我们提出利用人类大脑活动不作为训练信号，而是作为读取和操控LLM状态的坐标系。使用SMN4Lang MEG数据集，我们构建了一个词级大脑图谱，记录相锁值（PLV）模式，并通过ICA提取潜在轴。我们通过独立词典和基于命名实体识别（NER）的标签（词性/词频用于验证）验证轴，然后训练轻量级适配器，将LLM隐藏状态映射到这些大脑轴而不微调LLM。沿着由此产生的大脑衍生方向操控，得到一个在中等TinyLlama层中稳定的词频关联轴，在词频匹配控制下保持稳定，并且在大脑与文本探测比较中，大脑轴相对于文本探测显示出更大的词频变化（相对词频变化）且词频更低。功能/内容轴（轴13）在TinyLlama、Qwen2-0.5B和GPT-2中表现出一致的操控效果，词频匹配文本层面的验证也得到支持。TinyLlama的第4层效应较大但不一致，因此我们将其视为次要（附录）。当图谱重建时不使用GPT嵌入变化特征或使用word2vec嵌入时，轴结构保持稳定（匹配轴上的相关系数为0.64-0.95），从而减少循环性担忧。探索性fMRI锚定表明，嵌入变化和词频的对齐潜力，但效果对血流动力学建模假设敏感，仅作为群体层面的证据。这些结果支持一种新接口：神经生理学基础的轴提供了可解释和可控的LLM行为操控手段。
英文摘要：
Interpretability methods for large language models (LLMs) typically derive directions from textual supervision, which can lack external grounding. We propose using human brain activity not as a training signal but as a coordinate system for reading and steering LLM states. Using the SMN4Lang MEG dataset, we construct a word-level brain atlas of phase-locking value (PLV) patterns and extract latent axes via ICA. We validate axes with independent lexica and NER-based labels (POS/log-frequency used as sanity checks), then train lightweight adapters that map LLM hidden states to these brain axes without fine-tuning the LLM. Steering along the resulting brain-derived directions yields a robust lexical (frequency-linked) axis in a mid TinyLlama layer, surviving perplexity-matched controls, and a brain-vs-text probe comparison shows larger log-frequency shifts (relative to the text probe) with lower perplexity for the brain axis. A function/content axis (axis 13) shows consistent steering in TinyLlama, Qwen2-0.5B, and GPT-2, with PPL-matched text-level corroboration. Layer-4 effects in TinyLlama are large but inconsistent, so we treat them as secondary (Appendix). Axis structure is stable when the atlas is rebuilt without GPT embedding-change features or with word2vec embeddings (|r|=0.64-0.95 across matched axes), reducing circularity concerns. Exploratory fMRI anchoring suggests potential alignment for embedding change and log frequency, but effects are sensitive to hemodynamic modeling assumptions and are treated as population-level evidence only. These results support a new interface: neurophysiology-grounded axes provide interpretable and controllable handles for LLM behavior.
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。
