4 papers
Perturbation-based Regional Interpretability through Subtraction Mapping (PRISM): naming-error dissociations in language models and post-stroke aphasia
Xiang Guan, Roger D. Newman-Norlund, Yong Yang +8
Mechanistic interpretability of large language models lacks spatially resolved, falsifiable tools for testing whether internal components are specialized for distinct cognitive ope…
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…
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…
Exploring Fusion Strategies for Multimodal Vision-Language Systems
Regan Willis, Jason Bakos
Modern machine learning models often combine multiple input streams of data to more accurately capture the information that informs their decisions. In multimodal machine learning,…