Brain Score remains similar when language models are trained on diverse natural languages or on structured non-language data like DNA and code, indicating the metric tracks shared structural extraction but is not diagnostic of human-like language processing.
Gershman, Nancy Kanwisher, Matthew Botvinick, and Evelina Fedorenko
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.CL 4representative 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.
BERT activations show strongest correlation with MEG data for simple sentences; DNN representations generate synthetic brain data that improves stimuli decoding accuracy.
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 Score Tracks Shared Properties of Languages: Evidence from Many Natural Languages and Structured Sequences
Brain Score remains similar when language models are trained on diverse natural languages or on structured non-language data like DNA and code, indicating the metric tracks shared structural extraction but is not diagnostic of human-like language processing.
-
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.
-
Relating Simple Sentence Representations in Deep Neural Networks and the Brain
BERT activations show strongest correlation with MEG data for simple sentences; DNN representations generate synthetic brain data that improves stimuli decoding accuracy.
-
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.