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

Abstract

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 dissociable, an open question is whether LLMs align with neural signals from reasoning-related regions and whether such signals can improve them. Here, focusing on deductive reasoning, we show that LLM internal representations are not only partially aligned with task-based functional magnetic resonance imaging activity but can also be directly enhanced by these signals. Using a neural predictivity metric, we find that LLMs explain a substantial fraction of the explainable variance in reasoning-related regions at the aggregate level, whereas predictivity within specific reasoning types is lower, indicating both alignment and divergence. Building on this, we propose a brain-guided framework: we steer model representations along directions induced by the joint structure of model and brain representations, applying intervention at inference and fine tuning during training. We demonstrate that task-evoked brain signals can directly enhance LLM reasoning, yielding gains orthogonal to language-only supervision across ten LLMs (1.5B–72B parameters), with transfer across reasoning types and up to 13% absolute accuracy gain. Our results advance LLM–brain correspondences from correlation to guidance, establishing a brain-signal-driven pathway towards more robust and cognitively aligned artificial intelligence. Xiao et al. show that large language models partially align with human brain activity during deductive reasoning. They further show that brain signals can directly guide and improve model performance, with transfer across reasoning types.