Scholarlink

<p>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.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

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

  • 期刊论文

  • 发表日期：

    2026年8月3日

查看全文
  • Mingqing Xiao,
  • Kai Du,
  • Zhouchen Lin

摘要

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.