paper-with-me

Papers

Large Language Models Align with the Human Brain during Creative Thinking

2026-04-03 · Mete Ismayilzada, Simone A. Luchini, Abdulkadir Gokce, Badr AlKhamissi, Antoine Bosselut, Antonio Laverghetta, Lonneke van der Plas, Roger E. Beaty arxiv

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.

📄 PDF Abstract BibTeX arXiv:2604.03480

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

From Language to Cognition: How LLMs Outgrow the Human Language Network

2025-03-03 · Badr AlKhamissi, Greta Tuckute, Yingtian Tang, Taha Binhuraib 외

Large language models (LLMs) exhibit remarkable similarity to neural activity in the human language network. However, the key properties of language shaping brain-like representations, and their evolution during training…

World Knowledge

Triple Phase Transitions: Understanding the Learning Dynamics of Large Language Models from a Neuroscience Perspective

2025-02-28 · Yuko Nakagi, Keigo Tada, Sota Yoshino, Shinji Nishimoto 외

Large language models (LLMs) often exhibit abrupt emergent behavior, whereby new abilities arise at certain points during their training. This phenomenon, commonly referred to as a ''phase transition'', remains poorly un…

Instruction Following

Linguistic properties and model scale in brain encoding: from small to compressed language models

2026-02-07 · Subba Reddy Oota, Vijay Rowtula, Satya Sai Srinath Namburi, Khushbu Pahwa 외 arxiv

Recent work has shown that scaling large language models (LLMs) improves their alignment with human brain activity, yet it remains unclear what drives these gains and which representational properties are responsible. Al…

Do Large Language Models Think Like the Brain? Sentence-Level Evidence from fMRI and Hierarchical Embeddings

2025-05-28 · Yu Lei, Xingyang Ge, Yi Zhang, Yiming Yang 외

Understanding whether large language models (LLMs) and the human brain converge on similar computational principles remains a fundamental and important question in cognitive neuroscience and AI. Do the brain-like pattern…

Sentence

Beyond representational alignment with brain-guided language models for robust reasoning

2026-06-10 · Mingqing Xiao, Kai Du, Zhouchen Lin arxiv

The correspondence between large language models (LLMs) and the neural mechanisms underlying human higher-order cognition remains insufficiently characterized. Given that language and reasoning in the human brain appear …