cs.LGNov 18, 2026

Transferring an analysis of human brain organization to language models

Authors: Donghyeok Lee, Sangwon Yu, Sangkwon Park, Hye Youn Park, Munyoung Chang, Sungroh Yoon

Organizations: Interdisciplinary Program in Artificial Intelligence, Seoul National University, Seoul, 08826, Republic of Korea. · Upstage AI, Seoul, 06130, Republic of Korea. · Department of Electrical and Computer Engineering, Seoul National University, Seoul, 08826, Republic of Korea. · Department of Psychiatry, Seoul National University Bundang Hospital, Seongnam, Republic of Korea. · 

Abstract

During human cortical development, functional systems become increasingly differentiated. We asked whether improved reasoning in language models involves a comparable regional reorganization. Applying diffusion-map embedding, used to characterize cortical organization, to matched base and reasoning-trained models from three families, we found broadly preserved gradient profiles with localized changes within a contiguous layer span. Grafting weights from these spans into instruction-tuned hosts improved mathematical reasoning on average, with gains rising with region overlap, while retaining more previously solved problems than grafts elsewhere. Across training, the span formed gradually during the early rise in performance, and grafts from intermediate stages helped. Grafts shifted most hosts partly towards their donors' behaviour and sometimes improved on problems the donors failed; the same analysis located a transferable span in a medical model. Together, these findings identify a reasoning-related region whose weights improve reasoning with low interference in the host's existing mathematical competence.

Figures & tables

Explore similar work

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

    Jun 10, 2026Mingqing Xiao, Kai Du, Zhouchen LinLogical ReasoningLanguage Modeling

  2. Cognitive Expert Language Models Better Align with the Corresponding Brain Systems

    Sep 28, 2026Zhivar Sourati, Mengxuan Helen Wu, Nona Ghazizadeh +3Cognitive Modeling

  3. Thinking in Different Spaces: Domain-Specific Latent Geometry Survives Cross-Architecture Translation

    Mar 20, 2026Marcus Armstrong, Navid Ayoobi, Arjun MukherjeeRepresentation Geometry in Language ModelsActivation Steering