1
Perturbation-based Regional Interpretability through Subtraction Mapping (PRISM): naming-error dissociations in language models and post-stroke aphasia
用扰动映射揭示语言模型与脑损伤失语症中命名错误的共通机制，值得关注。
arXiv:2608.12717v1 Announce Type: new Abstract: Mechanistic interpretability of large language models lacks spatially resolved, falsifiable tools for …