Metraipolis › archive › dc_355530bb2b15

Activation-Guided Neuron Intervention to Induce Alzheimer's-Related Computational Language Phenotypes in a Large Language Model — arXiv:2608.03067

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03067
License (as archived)
CC0-1.0
Archived
2026-10-31T12:30:55.421Z
SHA-256 of the archived text
9984490088cd96483f8a0c9070565950c229560c18351febfa5307fc1851a107
Stable URL of this page
https://metraipolis.com/documento/dc_355530bb2b15

How to cite

Activation-Guided Neuron Intervention to Induce Alzheimer's-Related Computational Language Phenotypes in a Large Language Model — arXiv:2608.03067 — arXiv (en), https://arxiv.org/abs/2608.03067 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_355530bb2b15 (Metraipolis archive dc_355530bb2b15, sha256 9984490088cd96483f8a0c9070565950c229560c18351febfa5307fc1851a107)
BibTeX
@misc{dc355530bb2b15,
  title = {Activation-Guided Neuron Intervention to Induce Alzheimer's-Related Computational Language Phenotypes in a Large Language Model — arXiv:2608.03067},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03067},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_355530bb2b15; sha256 9984490088cd96483f8a0c9070565950c229560c18351febfa5307fc1851a107},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03067. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Changes in spontaneous speech provide an early signal of cognitive dysfunction in Alzheimer's disease (AD) that large language models (LLMs) can detect. However, detection alone cannot establish whether the underlying model representations contribute functionally to behavior. We introduce an activation-guided intervention framework using Qwen3-8B. The framework identifies feed-forward neurons with higher activation rates for AD than control transcripts and modulates their output contributions during generation by scaling the corresponding down-projection weights. This yielded nine edited variants differing in intervention direction, magnitude, and scope. The original and edited models completed the same 12-turn neuropsychological battery, assessed through blinded human ratings and computational linguistic measures. Amplifying AD-associated neurons produced graded impairments in story recall, verbal fluency, working memory, procedural discourse, scene construction, and coreference resolution. Attenuation largely preserved performance and selectively improved several outcomes. Amplification also reduced lexical surprisal, idea density, syntactic complexity, and discourse quantity, broadly paralleling changes reported in human AD speech. These findings show that neurons identified solely from clinical language differences can influence behavior across multiple cognitive domains, providing proof of concept for an AD-related computational phenotype and a controlled framework for experimentally examining links between language and broader cognitive dysfunction.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.03067 — 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 2026-10-31T12:17:37.736Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).