大型语言模型在创造性思维过程中与人类大脑对齐
Large Language Models Align with the Human Brain during Creative Thinking
AI总结：
研究探讨了在创造性思维过程中，fMRI数据揭示了大脑与不同规模LLM之间的对齐关系，发现模型大小和想法原创性影响对齐程度，且训练目标影响表示与人类创造力神经几何的匹配程度。
摘要：
创造性思维是人类认知的核心方面，发散性思维被认为是其核心生成引擎。大型语言模型（LLMs）最近在发散性思维测试中表现出色，已有研究表明任务表现越高的模型越接近人类大脑活动。然而，现有大脑-LLM对齐研究集中在被动而非创造性的任务上。本文利用170名参与者的fMRI数据，研究了在执行替代用途任务（AUT）期间的大脑对齐情况。从不同规模（270M-72B）的LLM中提取表示，并通过表征相似性分析（RSA）测量与大脑响应的对齐程度，目标是创造力相关的默认模式网络和前额叶网络。研究发现，大脑-LLM对齐程度与模型大小（仅默认模式网络）和想法原创性（两个网络）成正比，效果在创造性过程早期最强。进一步研究显示，训练目标以功能选择性方式影响对齐：一个优化创造力的Llama-3.1-8B-Instruct模型保持高创造力神经响应的对齐，同时降低低创造力响应的对齐；一个经过人类行为微调的模型提升两者对齐；而一个经过推理训练的变体则呈现相反模式，表明链式思维训练使表示远离创造性神经几何，转向分析性处理。这些结果表明，训练目标有选择地重塑LLM表示，使其相对于人类创造性思维的神经几何。
英文摘要：
Creative thinking is a fundamental aspect of human cognition, and divergent thinking-the capacity to generate novel and varied ideas-is widely regarded as its core generative engine. Large language models (LLMs) have recently demonstrated impressive performance on divergent thinking tests and prior work has shown that models with higher task performance tend to be more aligned to human brain activity. However, existing brain-LLM alignment studies have focused on passive, non-creative tasks. Here, we explore brain alignment during creative thinking using fMRI data from 170 participants performing the Alternate Uses Task (AUT). We extract representations from LLMs varying in size (270M-72B) and measure alignment to brain responses via Representational Similarity Analysis (RSA), targeting the creativity-related default mode and frontoparietal networks. We find that brain-LLM alignment is positively associated with model size (default mode network only) and with idea originality (both networks), with these relationships clearest early in the creative process. We further find that post-training objectives are associated with functionally selective differences in alignment: a creativity-optimized Llama-3.1-8B-Instruct retains alignment with high-creativity neural responses while lacking the positive low-creativity alignment present in other variants, but a reasoning-trained variant shows the opposite asymmetry, with negative alignment to high-creativity responses. Together, these results suggest that brain alignment offers an informative lens on how post-training relates to the neural geometry of human creative thought.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
