LLM与大脑的表征对齐不等于机制相同，不能直接推导出语言处理的生物神经原理。
No country for old linguists: LLM-brain alignment underdetermines neural computation
- 表征对齐仅约束可能的机制，无法确定具体计算过程。
- 模型与大脑在统计学习上相似，但未必共享相同算法或架构。
- 适合关注神经科学与AI交叉研究的学者阅读，尤其警惕过度解读对齐意义。
Nastase 等人（2026）认为大语言模型（LLMs）可能揭示语言处理机制，因二者均依赖分布式、上下文敏感的表征，并由统计学习塑造。他们反对简单的皮层“盒子结构”观点，有力论证了 LLM-大脑对齐研究的价值。关键问题是：这种对齐能支持何种推断？本文主张：表征对齐在原则上可限制机制假设，但本身不足以识别具体机制。尽管作者承认编码模型可捕捉神经活动中的特征，却未必共享架构或算法，但他们有时仍从对齐推导出“共同计算原则”，甚至认为 LLM 可作为语言的“完全机制模型”。这与其方法论警告——对齐不意味着共享架构或算法——存在逻辑冲突。本文讨论了该主张在逻辑、因果和计算层面的不确定性问题。
原文摘要 · Abstract (English)
Nastase et al. (2026) argue that large language models (LLMs) may illuminate language processing because both rely on distributed, context-sensitive representations shaped by statistical learning. Their rejection of simple cortical "boxology" is persuasive, and they articulate a strong case for the value of LLM-brain alignment research. The key question is what kind of inference LLM-brain alignment licenses. My claim here will be narrow: representational alignment can in principle constrain mechanistic hypotheses, but it does not by itself identify a mechanism. Nastase et al. acknowledge that an encoding model can capture features represented in neural activity without establishing a shared architecture or algorithm. Yet the authors sometime move from alignment to "shared computational principles" and ultimately to LLMs as mechanistic models of natural language. Indeed, their methodological caveat that alignment does not establish a shared architecture or algorithm sits uneasily with their conclusion that LLMs might instantiate the same computational principles as biological brains and provide a "fully mechanistic model" of language. I discuss what I consider to be problems of logical, causal, and computational underdetermination in Nastase et al.'s (2026) proposal.
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。