Mapping Brains with Language Models: A Survey
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Mapping Brains with Language Models : A Survey. / Karamolegkou, Antonia; Abdou, Mostafa; Søgaard, Anders.
Findings of the Association for Computational Linguistics: ACL 2023. Association for Computational Linguistics (ACL), 2023. p. 9748-9762.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Mapping Brains with Language Models
T2 - Findings of the Association for Computational Linguistics: ACL 2023
AU - Karamolegkou, Antonia
AU - Abdou, Mostafa
AU - Søgaard, Anders
PY - 2023
Y1 - 2023
N2 - Over the years, many researchers have seemingly made the same observation: Brain and language model activations exhibit some structural similarities, enabling linear partial mappings between features extracted from neural recordings and computational language models. In an attempt to evaluate how much evidence has been accumulated for this observation, we survey over 30 studies spanning 10 datasets and 8 metrics. How much evidence has been accumulated, and what, if anything, is missing before we can draw conclusions? Our analysis of the evaluation methods used in the literature reveals that some of the metrics are less conservative. We also find that the accumulated evidence, for now, remains ambiguous, but correlations with model size and quality provide grounds for cautious optimism.
AB - Over the years, many researchers have seemingly made the same observation: Brain and language model activations exhibit some structural similarities, enabling linear partial mappings between features extracted from neural recordings and computational language models. In an attempt to evaluate how much evidence has been accumulated for this observation, we survey over 30 studies spanning 10 datasets and 8 metrics. How much evidence has been accumulated, and what, if anything, is missing before we can draw conclusions? Our analysis of the evaluation methods used in the literature reveals that some of the metrics are less conservative. We also find that the accumulated evidence, for now, remains ambiguous, but correlations with model size and quality provide grounds for cautious optimism.
U2 - 10.18653/v1/2023.findings-acl.618
DO - 10.18653/v1/2023.findings-acl.618
M3 - Article in proceedings
SP - 9748
EP - 9762
BT - Findings of the Association for Computational Linguistics: ACL 2023
PB - Association for Computational Linguistics (ACL)
Y2 - 1 July 2023 through 1 July 2023
ER -
ID: 381566615