Tag
This ERP study examines recursive locative processing in Mandarin-speaking children with autism, finding reduced early predictive engagement and increased semantic integration demands in the ASD group.
This paper uses sparse autoencoders to decompose LLMs into interpretable features and shows that semantic features explain brain alignment with cortical semantic topography, generalizing across English, Chinese, and French.
This paper investigates whether Brain Score, a metric comparing language model representations to human fMRI activations during reading, is truly capturing human-like language processing or merely structural similarity. The researchers train language models on diverse natural languages and non-linguistic structured data (genome, Python, nested parentheses), finding that models trained on different languages and even non-linguistic sequences achieve similar Brain Score performance, suggesting the metric may not be sensitive enough to distinguish human-specific processing.