From the 1 of 6 linked papers with an AI index.
6 papers
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…
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…
Model Selection with Regression and Representational Similarity Analysis for Linear and Nonlinear Data
Chuanji Gao, Gang Chen, Svetlana V. Shinkareva +1
In cognitive psychology and neuroscience, adjudicating between competing theoretical models is a common methodological challenge. Researchers often rely on either first-order direc…
Topological inference on brain networks with application to lesion symptom mapping
Yuan Wang, Jian Yin, Nicholas Riccardi +3
Persistent homology (PH) characterizes the shape of brain networks through persistence features. Group comparison of persistence features from brain networks can be challenging as…
Stroke Lesions as a Rosetta Stone for Language Model Interpretability
Julius Fridriksson, Roger D. Newman-Norlund, Saeed Ahmadi +10
Large language models (LLMs) have achieved remarkable capabilities, yet methods to verify which model components are truly necessary for language function remain limited. Current i…
Multifaceted neural representation of words in naturalistic language
Xuan Yang, Chuanji Gao, Cheng Xiao +2
Understanding how the brain represents the multifaceted properties of words in context is essential for explaining the neural architecture of human language. Here, we combine large…