Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 37 min ago
PreprintCC BY-NC-NDbioRxiv

AI-like parallelogram geometry of word relations in the human neocortex

  • R. Wang
  • Y. Tian
  • K. Ohmae1
  • S. Ohmae1
  1. 1Chinese Institute for Brain Research, Beijing, China
Read full textPDFDOICite

Abstract

The same semantic relation (e.g., queen-king and woman-man) is encoded as a shared vector direction in language AI, forming parallelogram geometry, whereas its presence in the human brain remains unknown. Our fMRI analysis revealed similar geometry in the neocortex, particularly in higher-order language regions. Our findings link the brain and AI through a common geometry, advancing understanding of how abstract relational knowledge is organized and used in human language processing.

Related

  1. Cortical isolation separates rhythmic synchrony from network integration in the human neocortex.
    R. Bod, K. Toth, O. Farkas +11
    bioRxivPreprintCC BY-NDFull textNeurosciencebioRxiv
  2. Human-specific morphoregulatory signatures in basal radial glia characterise neocortex evolution
    Theresa M. Schütze, Annika Kolodziejczyk, Nora Ditzer +20
    Nature CommunicationsPeer-reviewedCC BY 4.0Full textNeuroscienceCrossref
  3. Precise Development of Functional and Anatomical Columns in the Neocortex
    Ingrid Bureau, Gordon M.G Shepherd, Karel Svoboda
    NeuronPeer-reviewedLicence not statedFull text149 citedNeuroscienceHAL
  4. Rapid spatial cognition in mice, with and without neocortex and hippocampus
    J. Zheng, R. Guimaraes, Z. Turan +5
    bioRxivPreprintCC BYFull text1 citedNeurosciencebioRxiv
  5. The Spectrum of Asynchronous Dynamics in Spiking Networks as a Model for the Diversity of Non-rhythmic Waking States in the Neocortex
    Yann Zerlaut, Stefano Zucca, Stefano Panzeri +1
    Cell ReportsPeer-reviewedCC BY 4.0Full text23 citedNeuroscienceHAL

Cite

BibTeXRIS
BibTeX
@misc{wang2026ailike,
  title = {{AI-like parallelogram geometry of word relations in the human neocortex}},
  author = {R. Wang and Y. Tian and K. Ohmae and S. Ohmae},
  howpublished = {bioRxiv},
  year = {2026},
  month = sep,
  doi = {10.64898/2026.09.07.749996},
  url = {https://www.biorxiv.org/content/10.64898/2026.09.07.749996v1},
  note = {CC BY-NC-ND},
}
RIS
TY  - UNPB
TI  - AI-like parallelogram geometry of word relations in the human neocortex
AU  - R. Wang
AU  - Y. Tian
AU  - K. Ohmae
AU  - S. Ohmae
PY  - 2026
DA  - 2026/09/07
PB  - bioRxiv
DO  - 10.64898/2026.09.07.749996
UR  - https://www.biorxiv.org/content/10.64898/2026.09.07.749996v1
AB  - The same semantic relation (e.g., queen-king and woman-man) is encoded as a shared vector direction in language AI, forming parallelogram geometry, whereas its presence in the human brain remains unknown. Our fMRI analysis revealed similar geometry in the neocortex, particularly in higher-order language regions. Our findings link the brain and AI through a common geometry, advancing understanding of how abstract relational knowledge is organized and used in human language processing.
ER  -