评分不等于结构：脑对齐与跨语言迁移中的测量陷阱
原标题：The Score Is Not the Structure: Brain Alignment and Cross-Lingual Transfer
AI 摘要
该论文对表征相似性评分提出方法论质疑：在跨语言探针迁移和脑对齐两个场景中，评分可能反映的是测量工具失效或目标不敏感，而非真实共享结构。跨语言实验中，17 种语言里有 4 种探针准确率仅相当于随机猜测，剔除后效应量减半；脑对齐实验中，破坏对应关系的目标仍能达到接近真实目标的 CKA 分数，脑特异性增量很小。作者建议在追问对应关系是否有用之前，先检验评分中有多少可在无对应关系时依然存在。
正文节选
Linguistic Principles for Foundation Models (LP4FM) The Score Is Not the Structure: Brain Alignment and Cross-Lingual Transfer Abstract Researchers routinely claim that a model shares structure with something else, with the human brain or across languages, and support the claim with a similarity score. We ask a question that comes first: what does such a score read when the shared structure is absent, or when the tool used to measure it does not work? We run that check in two settings. In both,