From the 1 of 2 linked papers with an AI index.
2 papers
cs.CL2026
Recovering Lesion Parameters from Aphasic Picture Naming Error Profiles in Large Language Models
Yong Yang, Roger Newman-Norlund, Xiang Guan +10
Interpretability methods for large language models (LLMs) describe internal state but do not directly test whether that state is causally sufficient to produce the observed behavio…
cs.AI2026
Lesioned Multimodal Language Models Reproduce Aphasic Picture-Naming Patterns
Yong Yang, Xiang Guan, Sophie Arheix-Parras +7
The study shows that applying targeted lesions or noise to a multimodal language model (LLaVA 1.6) can replicate the picture‑naming error patterns observed in individuals with post…