Large Language Models Align with the Human Brain during Creative Thinking

• URL: http://arxiv.org/abs/2604.03480v1
• Date: Fri, 03 Apr 2026 22:02:15 GMT
• Title: Large Language Models Align with the Human Brain during Creative Thinking
• Abstract summary: We study brain alignment during creative thinking using fMRI data from 170 participants performing the Alternate Uses Task (AUT)<n>We find that brain-LLM alignment scales with model size (default mode network only) and idea originality (both networks)<n>We further show that post-training objectives shape alignment in functionally selective ways.
• Score: 19.08997828415446
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 scales with model size (default mode network only) and idea originality (both networks), with effects strongest early in the creative process. We further show that post-training objectives shape alignment in functionally selective ways: a creativity-optimized \texttt{Llama-3.1-8B-Instruct} preserves alignment with high-creativity neural responses while reducing alignment with low-creativity ones; a human behavior fine-tuned model elevates alignment with both; and a reasoning-trained variant shows the opposite pattern, suggesting chain-of-thought training steers representations away from creative neural geometry toward analytical processing. These results demonstrate that post-training objectives selectively reshape LLM representations relative to the neural geometry of human creative thought.

Related papers

• CreativityNeuro: Steering Language Model Weights to Improve Divergent Thinking and Reduce Mode Collapse [16.388226447545566]
  We introduce CreativityNeuro, a data-free method for enhancing divergent thinking in large language models (LLMs)<n>On the Divergent Association Task ( DAT), CreativityNeuro improves performance by up to 14 human percentile points.<n>In a large-scale human evaluation (N=720), CreativityNeuro achieves significant improvements in originality, surprise, and creativity, transferring to longer-form and more open-ended tasks.
  arXiv  Detail & Related papers  (2026-07-01T19:54:39Z)
• Brain alignment of reasoning and action representations from vision-language and action models during naturalistic gameplay [40.44107959566121]
  We study brain alignment of representative models from two foundation-model families using fMRI recordings.<n>We find that both vision-language models (VLMs) and large-action models (LAMs) exhibit significantly exhibit voxel-wise encoding performance.
  arXiv  Detail & Related papers  (2026-05-19T04:40:14Z)
• Mind-Brush: Integrating Agentic Cognitive Search and Reasoning into Image Generation [47.97278965762397]
  We introduce Mind-Brush, a unified agentic framework that transforms generation into a dynamic, knowledge-driven workflow.<n>Simulating a human-like 'think-research-create' paradigm, Mind-Brush actively retrieves multimodal evidence to ground out-of-distribution concepts.<n>Extensive experiments demonstrate that Mind-Brush significantly enhances the capabilities of unified models.
  arXiv  Detail & Related papers  (2026-02-02T07:42:13Z)
• Training Emergent Joint Associations: A Reinforcement Learning Approach to Creative Thinking in Language Models [9.943285575387849]
  Associative thinking is a foundational element of human creativity and problem-solving.<n>This paper explores whether reinforcement learning guided by associative thinking principles can enhance a model's performance across diverse generative tasks.
  arXiv  Detail & Related papers  (2025-11-22T02:10:27Z)
• Concept-Guided Interpretability via Neural Chunking [64.6429903327095]
  We show that neural networks exhibit patterns in their raw population activity that mirror regularities in the training data.<n>We propose three methods to extract recurring chunks on a neural population level.<n>Our work points to a new direction for interpretability, one that harnesses both cognitive principles and the structure of naturalistic data.
  arXiv  Detail & Related papers  (2025-05-16T13:49:43Z)
• Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning [58.86928947970342]
  Embodied-R is a framework combining large-scale Vision-Language Models for perception and small-scale Language Models for reasoning.<n>After training on only 5k embodied video samples, Embodied-R with a 3B LM matches state-of-the-art multimodal reasoning models.<n>Embodied-R also exhibits emergent thinking patterns such as systematic analysis and contextual integration.
  arXiv  Detail & Related papers  (2025-04-17T06:16:11Z)
• Talking to the brain: Using Large Language Models as Proxies to Model Brain Semantic Representation [6.870138108382051]
  We introduce a novel paradigm leveraging multimodal large language models (LLMs) as proxies to extract semantic information from naturalistic images.<n>LLMs-derived representations successfully predict established neural activity patterns measured by fMRI.<n>A brain semantic network constructed from LLM-derived representations identifies meaningful clusters reflecting functional and contextual associations.
  arXiv  Detail & Related papers  (2025-02-26T00:40:28Z)
• Humanlike Cognitive Patterns as Emergent Phenomena in Large Language Models [2.9312156642007294]
  We systematically review Large Language Models' capabilities across three important cognitive domains: decision-making biases, reasoning, and creativity.<n>On decision-making, our synthesis reveals that while LLMs demonstrate several human-like biases, some biases observed in humans are absent.<n>On reasoning, advanced LLMs like GPT-4 exhibit deliberative reasoning akin to human System-2 thinking, while smaller models fall short of human-level performance.<n>A distinct dichotomy emerges in creativity: while LLMs excel in language-based creative tasks, such as storytelling, they struggle with divergent thinking tasks that require real-world context.
  arXiv  Detail & Related papers  (2024-12-20T02:26:56Z)
• Brain-like Functional Organization within Large Language Models [58.93629121400745]
  The human brain has long inspired the pursuit of artificial intelligence (AI) Recent neuroimaging studies provide compelling evidence of alignment between the computational representation of artificial neural networks (ANNs) and the neural responses of the human brain to stimuli. In this study, we bridge this gap by directly coupling sub-groups of artificial neurons with functional brain networks (FBNs) This framework links the AN sub-groups to FBNs, enabling the delineation of brain-like functional organization within large language models (LLMs)
  arXiv  Detail & Related papers  (2024-10-25T13:15:17Z)
• MindBridge: A Cross-Subject Brain Decoding Framework [60.58552697067837]
  Brain decoding aims to reconstruct stimuli from acquired brain signals. Currently, brain decoding is confined to a per-subject-per-model paradigm. We present MindBridge, that achieves cross-subject brain decoding by employing only one model.
  arXiv  Detail & Related papers  (2024-04-11T15:46:42Z)
• What if...?: Thinking Counterfactual Keywords Helps to Mitigate Hallucination in Large Multi-modal Models [50.97705264224828]
  We propose Counterfactual Inception, a novel method that implants counterfactual thinking into Large Multi-modal Models. We aim for the models to engage with and generate responses that span a wider contextual scene understanding. Comprehensive analyses across various LMMs, including both open-source and proprietary models, corroborate that counterfactual thinking significantly reduces hallucination.
  arXiv  Detail & Related papers  (2024-03-20T11:27:20Z)
• Backprop-Free Reinforcement Learning with Active Neural Generative Coding [84.11376568625353]
  We propose a computational framework for learning action-driven generative models without backpropagation of errors (backprop) in dynamic environments. We develop an intelligent agent that operates even with sparse rewards, drawing inspiration from the cognitive theory of planning as inference. The robust performance of our agent offers promising evidence that a backprop-free approach for neural inference and learning can drive goal-directed behavior.
  arXiv  Detail & Related papers  (2021-07-10T19:02:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.