Metraipolis › archive › dc_e887ab783bef

A Low-Rank Space Captures Linear Alignment Between LLM and Human Neural Activity During Naturalistic Language Listening — arXiv:2610.40511

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40511
License (as archived)
CC0-1.0
Archived
2026-10-31T06:17:09.095Z
SHA-256 of the archived text
2d204d3927cc6e398c5da88da78c714aee241420335f8066530ae72d5b5f1533
Stable URL of this page
https://metraipolis.com/documento/dc_e887ab783bef

How to cite

A Low-Rank Space Captures Linear Alignment Between LLM and Human Neural Activity During Naturalistic Language Listening — arXiv:2610.40511 — arXiv (en), https://arxiv.org/abs/2610.40511 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e887ab783bef (Metraipolis archive dc_e887ab783bef, sha256 2d204d3927cc6e398c5da88da78c714aee241420335f8066530ae72d5b5f1533)
BibTeX
@misc{dce887ab783bef,
  title = {A Low-Rank Space Captures Linear Alignment Between LLM and Human Neural Activity During Naturalistic Language Listening — arXiv:2610.40511},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40511},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e887ab783bef; sha256 2d204d3927cc6e398c5da88da78c714aee241420335f8066530ae72d5b5f1533},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40511. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) are increasingly used as computational models of human language processing, yet it remains unclear which components of their representations drive alignment with neural activity. Here, we use ridge reduced-rank regression to identify the brain-predictive subspace of LLM representations: the representational directions that support linear prediction of neural responses. Across three naturalistic language-listening datasets spanning intracranial electrophysiology and fMRI, and six model conditions spanning autoregressive, bidirectional masked, and randomly initialized language models, we find that full linear encoding performance can be recovered using only 1-3% of the original embedding dimensionality. These low-dimensional subspaces generalize across held-out participants and, to a lesser extent, across datasets, suggesting that neural predictivity is concentrated in a compact and partially shared representational space. We next compare these brain-predictive directions with the principal axes of variation in the embeddings. Principal component analysis requires substantially more dimensions to recover neural prediction, demonstrating that the directions most useful for predicting neural activity are distinct from those capturing the most overall variance within LLM representations themselves. Finally, characterizing the learned subspaces allows us to surface interpretable features that are overrepresented in neural activity above and beyond the LLM representations. Together, these results show that LLM-brain alignment is supported by a small, structured subset of model representations and provides a framework for better understanding exactly why these representations align. Code can be found at: this https URL

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Neurons and Cognition (q-bio.NC).
Pagina del lavoro: https://arxiv.org/abs/2610.40511 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T06:07:23.376Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).