Simulated associative memory, added as augmented text or taught through instruction tuning, appears to improve how well language model activations predict fMRI brain responses in story listening.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improve Language Model and Brain Alignment via Associative Memory
Simulated associative memory, added as augmented text or taught through instruction tuning, appears to improve how well language model activations predict fMRI brain responses in story listening.