Training-language dominance, not English inherent properties, determines brain-LLM alignment across English, Chinese, and French, with additional independent effects from typological distance concentrated in syntactic brain regions.
Huth and Wendy A
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
Sparse autoencoders applied to GPT-2 and Llama models recover semantic features accounting for 94% of peak brain encoding performance and map onto distinct cortical semantic regions across three languages.
Language coherence arises from slow contextual integration in default-mode cortex and rapid event-driven reconfiguration in auditory and language areas, captured by LLM-derived signals in single-subject fMRI.
A retroactive interference model using multi-dimensional memory valences and one free integer parameter reproduces the power-law form of forgetting observed in experiments.
LITcoder introduces a modular open-source library for constructing, benchmarking, and comparing neural encoding models that map continuous stimuli such as stories to fMRI brain data.
citing papers explorer
-
Brain-LLM Alignment Tracks Training Data, Not Typology
Training-language dominance, not English inherent properties, determines brain-LLM alignment across English, Chinese, and French, with additional independent effects from typological distance concentrated in syntactic brain regions.
-
Sparse Autoencoders Map Brain-LLM Alignment onto Cortical Semantic Topography
Sparse autoencoders applied to GPT-2 and Llama models recover semantic features accounting for 94% of peak brain encoding performance and map onto distinct cortical semantic regions across three languages.
-
Coherence in the brain unfolds across separable temporal regimes
Language coherence arises from slow contextual integration in default-mode cortex and rapid event-driven reconfiguration in auditory and language areas, captured by LLM-derived signals in single-subject fMRI.
-
Retroactive Interference Model of Power-Law Forgetting
A retroactive interference model using multi-dimensional memory valences and one free integer parameter reproduces the power-law form of forgetting observed in experiments.
-
LITcoder: A General-Purpose Library for Building and Comparing Encoding Models
LITcoder introduces a modular open-source library for constructing, benchmarking, and comparing neural encoding models that map continuous stimuli such as stories to fMRI brain data.