用联想记忆提升语言模型与人脑的匹配度。
Improve Language Model and Brain Alignment via Associative Memory
- 在输入中加入模拟联想记忆信息，增强模型与人脑的对齐。
- 改进后模型在关联记忆相关脑区的响应更贴近人脑活动。
- 特定微调使大模型更符合人类认知，适合脑科学与AI融合研究。
联想记忆在人类认知系统中负责整合相关信息以实现理解。本文通过引入联想记忆机制，提升语言模型与人脑在处理语音信息时的对齐程度。通过将语言模型激活映射到脑活动，验证了模型与人脑的对齐关系。随后，将原始文本刺激扩展为包含模拟联想记忆的信息，并作为计算语言模型的输入。结果显示，模型在与联想记忆处理密切相关的脑区中，与人脑的对齐程度显著提升。此外，通过构建包含1000个故事的「Association」数据集，并设计鼓励联想记忆输入、输出关联内容的指令，经特定监督微调的大语言模型表现出更强的人脑响应一致性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。