Improve Language Model and Brain Alignment via Associative Memory

Abstract: 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 LLMs and human brain while processing speech information by integrating associative memory. After verifying the alignment between LLM and brain by mapping LLM activations to brain activity, the original text stimuli expanded with simulated associative memory are regarded as input to computational LLMs. We find the alignment between LLM and brain is improved in brain regions closely related to associative memory processing. We also demonstrate LLMs 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.