{
  "abstract": "Alzheimer's Disease (AD) detection from spoken language has advanced considerably with the rise of large pre-trained speech and language models, including wav2vec 2.0, BERT, generative LLMs, and emerging audio-LLMs. These models often report higher performance on shared AD detection benchmarks than handcrafted-feature pipelines, while reducing the need for manual feature design. Yet their advantages remain difficult to interpret: pre-trained representations are largely a black box, benchmark gains are not always statistically robust, and performance can vary substantially across languages, elicitation protocols, and clinical task definitions.\n\nThis survey proposes a taxonomy of how large pre-trained speech and language models have been used for AD detection and progression-related tasks. We define Large Pre-trained Models (LPMs) as Transformer-based models trained with self-supervised or weakly supervised objectives, distinguishing them from earlier non-Transformer pre-trained representations. We then organize the literature into six usage strategies: direct application, fine-tuning, transfer learning, multitask learning, multilingual modeling, and generative-LLM-based assessment. Across these categories, we synthesize evidence from shared benchmarks and recent studies to answer four questions: 1) what taxonomy captures how LPMs are used for AD detection; 2) what progress and advantages do LPMs offer for AD detection; 3) what challenges and limitations do LPMs exhibit; and 4) what future opportunities and open tasks they present.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 10,
  "authors": [
    {
      "name": "Yuan-Chao Li"
    },
    {
      "name": "Yilin Pan"
    },
    {
      "name": "Yin-Long Liu"
    },
    {
      "name": "Liu He"
    },
    {
      "name": "Qi Sun"
    },
    {
      "name": "Siyu Zhang"
    },
    {
      "name": "Wei-Qiang Zhang"
    },
    {
      "name": "Saturnino Luz"
    },
    {
      "name": "Zhenhua Ling"
    },
    {
      "name": "Jiahong Yuan"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/ewdkjeffntazd.bib",
  "cited_by": 0,
  "doi": "10.31234/osf.io/s57tz_v2",
  "fulltext_url": null,
  "id": "ewdkjeffntazd",
  "issns": [],
  "landing_url": "https://osf.io/preprints/psyarxiv/s57tz_v2/",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "bepress",
      "Clinical Psychology"
    ],
    [
      "bepress",
      "Neurocognitive Disorders"
    ],
    [
      "bepress",
      "Neurodevelopmental Disorders"
    ],
    [
      "bepress",
      "Social and Behavioral Sciences"
    ],
    [
      "openalex",
      "2738|Dementia and Cognitive Impairment Research"
    ]
  ],
  "openalex": "W7207799528",
  "pdf_url": "https://osf.io/s57tz/download",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-03",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/ewdkjeffntazd.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:26:06Z",
      "native_id": "s57tz",
      "source": "osf",
      "url": "https://osf.io/preprints/psyarxiv/s57tz_v2/"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "bepress:Clinical Psychology",
      "subfield": "psychiatry"
    }
  ],
  "title": "Alzheimer's Disease Detection via Large Pre-Trained Speech and Language Models: Taxonomy, Progress, and Open Challenges",
  "title_text": "Alzheimer's Disease Detection via Large Pre-Trained Speech and Language Models: Taxonomy, Progress, and Open Challenges",
  "type": "preprint",
  "updated_at": "2026-10-30T12:26:06Z",
  "url": "https://research.draconitic.com/paper/ewdkjeffntazd",
  "venue": "PsyArXiv",
  "versions": []
}