Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Large Language Models Align with the Human Brain during Creative Thinking

Mete Ismayilzada, Simone A. Luchini, Abdulkadir Gokce, Badr AlKhamissi, Antoine Bosselut, Antonio Laverghetta, Lonneke van der Plas, Roger E. Beaty

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.

Large Language Models Align with the Human Brain during Creative Thinking

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.

Paper Structure

This paper contains 18 sections, 10 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. Brain-LLM Alignment
  4. LLMs and Creative Thinking
  5. Methodology
  6. Brain Data
  7. Model Data
  8. Brain Alignment
  9. Alignment with High vs. Low Creativity Responses
  10. Experimental Setup
  11. Models
  12. Alignment Factors
  13. Model Representations
  14. Results
  15. LLMs Align with the Human Brain During Creative Thinking
  16. ...and 3 more sections

Figures (10)

  • Figure 1: Our high-level brain alignment methodology.
  • Figure 2: Default Mode Network (DMN) AUT brain alignment results by model size and task performance using model activations on stimuli (prompt) only.$r$ and $p$ correspond to the Pearson correlation coefficient and p-value.
  • Figure 3: Left: The distribution of the best model layer (measured as relative depth) for alignment. Right: Default Mode Network (DMN) brain alignment results by best layer relative depth using model activations on stimuli (prompt) only.
  • Figure 4: Default Mode Network (DMN) AUT brain alignment results for high and low creativity response populations. The left red and right green bars indicate positive alignment with high and low creativity responses, respectively. Flipped bars indicate negative alignment.
  • Figure 5: Default Mode Network (DMN) AUT brain alignment results by model size and task performance using model activations on stimuli (prompt) and model response.$r$ and $p$ correspond to the Pearson correlation coefficient and p-value.
  • ...and 5 more figures