Improve Language Model and Brain Alignment via Associative Memory

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yin, Congchi, Zhang, Yongpeng, Wen, Xuyun, Li, Piji
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909617005527040
author Yin, Congchi
Zhang, Yongpeng
Wen, Xuyun
Li, Piji
author_facet Yin, Congchi
Zhang, Yongpeng
Wen, Xuyun
Li, Piji
contents Associative memory engages in the integration of relevant information for comprehension in the human cognition system. In this work, we seek to improve alignment between language models and human brain while processing speech information by integrating associative memory. After verifying the alignment between language model and brain by mapping language model activations to brain activity, the original text stimuli expanded with simulated associative memory are regarded as input to computational language models. We find the alignment between language model and brain is improved in brain regions closely related to associative memory processing. We also demonstrate large language models after specific supervised fine-tuning better align with brain response, by building the \textit{Association} dataset containing 1000 samples of stories, with instructions encouraging associative memory as input and associated content as output.
format Preprint
id arxiv_https___arxiv_org_abs_2505_13844
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improve Language Model and Brain Alignment via Associative Memory
Yin, Congchi
Zhang, Yongpeng
Wen, Xuyun
Li, Piji
Computation and Language
Associative memory engages in the integration of relevant information for comprehension in the human cognition system. In this work, we seek to improve alignment between language models and human brain while processing speech information by integrating associative memory. After verifying the alignment between language model and brain by mapping language model activations to brain activity, the original text stimuli expanded with simulated associative memory are regarded as input to computational language models. We find the alignment between language model and brain is improved in brain regions closely related to associative memory processing. We also demonstrate large language models after specific supervised fine-tuning better align with brain response, by building the \textit{Association} dataset containing 1000 samples of stories, with instructions encouraging associative memory as input and associated content as output.
title Improve Language Model and Brain Alignment via Associative Memory
topic Computation and Language
url https://arxiv.org/abs/2505.13844