老语言学家的无立足之地：LLM-大脑对齐对神经计算的决定不足
No country for old linguists: LLM-brain alignment underdetermines neural computation
- McGovern Medical School at UTHealth Houston（德克萨斯大学休斯顿健康科学中心麦戈文医学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文针对Nastase等人（2026）的观点提出质疑，指出LLM-大脑对齐仅能约束机制假说，无法确定具体机制，该提案存在逻辑、因果及计算决定不足问题。
AI中文摘要：
Nastase等人（2026）指出，大型语言模型（LLMs）或能为语言处理研究提供启示，因为两者都依赖由统计学习塑造的分布式、上下文敏感的表征，他们对简单皮层“盒状模型”的拒斥颇具说服力，并充分论证了LLM-大脑对齐研究的价值。关键问题在于，LLM-大脑对齐能支持何种推论。本文主张的观点较为狭隘：表征对齐原则上可对机制假说形成约束，但无法仅凭自身确定具体机制。Nastase等人承认，编码模型可捕捉神经活动中表征的特征，却无法确立共享架构或算法；然而作者有时会从“对齐”直接推导至“共享计算原则”，最终得出LLMs可作为自然语言机制模型的结论。事实上，他们关于“对齐无法确立共享架构或算法”的方法论警示，与“LLMs可能与生物大脑具有相同计算原则，可提供语言的‘完全机制模型’”的结论存在矛盾。本文将探讨Nastase等人（2026）的提案中存在的逻辑、因果及计算决定不足问题。
英文摘要：
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.
