Salvato in:
Dettagli Bibliografici
Autori principali: Antonello, Richard, Singh, Chandan, Jain, Shailee, Hsu, Aliyah, Guo, Sihang, Gao, Jianfeng, Yu, Bin, Huth, Alexander
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2410.00812
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915178001465344
author Antonello, Richard
Singh, Chandan
Jain, Shailee
Hsu, Aliyah
Guo, Sihang
Gao, Jianfeng
Yu, Bin
Huth, Alexander
author_facet Antonello, Richard
Singh, Chandan
Jain, Shailee
Hsu, Aliyah
Guo, Sihang
Gao, Jianfeng
Yu, Bin
Huth, Alexander
contents Representations from large language models are highly effective at predicting BOLD fMRI responses to language stimuli. However, these representations are largely opaque: it is unclear what features of the language stimulus drive the response in each brain area. We present generative causal testing (GCT), a framework for generating concise explanations of language selectivity in the brain from predictive models and then testing those explanations in follow-up experiments using LLM-generated stimuli.This approach is successful at explaining selectivity both in individual voxels and cortical regions of interest (ROIs), including newly identified microROIs in prefrontal cortex. We show that explanatory accuracy is closely related to the predictive power and stability of the underlying predictive models. Finally, we show that GCT can dissect fine-grained differences between brain areas with similar functional selectivity. These results demonstrate that LLMs can be used to bridge the widening gap between data-driven models and formal scientific theories.
format Preprint
id arxiv_https___arxiv_org_abs_2410_00812
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generative causal testing to bridge data-driven models and scientific theories in language neuroscience
Antonello, Richard
Singh, Chandan
Jain, Shailee
Hsu, Aliyah
Guo, Sihang
Gao, Jianfeng
Yu, Bin
Huth, Alexander
Computation and Language
Neurons and Cognition
Representations from large language models are highly effective at predicting BOLD fMRI responses to language stimuli. However, these representations are largely opaque: it is unclear what features of the language stimulus drive the response in each brain area. We present generative causal testing (GCT), a framework for generating concise explanations of language selectivity in the brain from predictive models and then testing those explanations in follow-up experiments using LLM-generated stimuli.This approach is successful at explaining selectivity both in individual voxels and cortical regions of interest (ROIs), including newly identified microROIs in prefrontal cortex. We show that explanatory accuracy is closely related to the predictive power and stability of the underlying predictive models. Finally, we show that GCT can dissect fine-grained differences between brain areas with similar functional selectivity. These results demonstrate that LLMs can be used to bridge the widening gap between data-driven models and formal scientific theories.
title Generative causal testing to bridge data-driven models and scientific theories in language neuroscience
topic Computation and Language
Neurons and Cognition
url https://arxiv.org/abs/2410.00812