Saved in:
Bibliographic Details
Main Authors: Taherinezhad, Fatemeh, Nezhad, Mohamad Javad Momeni, Karimi, Sepehr, Rashidi, Sina, Zolnour, Ali, Dadkhah, Maryam, Haghbin, Yasaman, AzadMaleki, Hossein, Zolnoori, Maryam
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.03525
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918468617502720
author Taherinezhad, Fatemeh
Nezhad, Mohamad Javad Momeni
Karimi, Sepehr
Rashidi, Sina
Zolnour, Ali
Dadkhah, Maryam
Haghbin, Yasaman
AzadMaleki, Hossein
Zolnoori, Maryam
author_facet Taherinezhad, Fatemeh
Nezhad, Mohamad Javad Momeni
Karimi, Sepehr
Rashidi, Sina
Zolnour, Ali
Dadkhah, Maryam
Haghbin, Yasaman
AzadMaleki, Hossein
Zolnoori, Maryam
contents Over half of US adults with Alzheimer disease and related dementias remain undiagnosed, and speech-based screening offers a scalable detection approach. We compared large language model adaptation strategies for dementia detection using the DementiaBank speech corpus, evaluating nine text-only models and three multimodal audio-text models on recordings from DementiaBank speech corpus. Adaptations included in-context learning with different demonstration selection policies, reasoning-augmented prompting, parameter-efficient fine-tuning, and multimodal integration. Results showed that class-centroid demonstrations achieved the highest in-context learning performance, reasoning improved smaller models, and token-level fine-tuning generally produced the best scores. Adding a classification head substantially improved underperforming models. Among multimodal models, fine-tuned audio-text systems performed well but did not surpass the top text-only models. These findings highlight that model adaptation strategies, including demonstration selection, reasoning design, and tuning method, critically influence speech-based dementia detection, and that properly adapted open-weight models can match or exceed commercial systems.
format Preprint
id arxiv_https___arxiv_org_abs_2509_03525
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Speech-Based Cognitive Screening: A Systematic Evaluation of LLM Adaptation Strategies
Taherinezhad, Fatemeh
Nezhad, Mohamad Javad Momeni
Karimi, Sepehr
Rashidi, Sina
Zolnour, Ali
Dadkhah, Maryam
Haghbin, Yasaman
AzadMaleki, Hossein
Zolnoori, Maryam
Computation and Language
Artificial Intelligence
Audio and Speech Processing
Over half of US adults with Alzheimer disease and related dementias remain undiagnosed, and speech-based screening offers a scalable detection approach. We compared large language model adaptation strategies for dementia detection using the DementiaBank speech corpus, evaluating nine text-only models and three multimodal audio-text models on recordings from DementiaBank speech corpus. Adaptations included in-context learning with different demonstration selection policies, reasoning-augmented prompting, parameter-efficient fine-tuning, and multimodal integration. Results showed that class-centroid demonstrations achieved the highest in-context learning performance, reasoning improved smaller models, and token-level fine-tuning generally produced the best scores. Adding a classification head substantially improved underperforming models. Among multimodal models, fine-tuned audio-text systems performed well but did not surpass the top text-only models. These findings highlight that model adaptation strategies, including demonstration selection, reasoning design, and tuning method, critically influence speech-based dementia detection, and that properly adapted open-weight models can match or exceed commercial systems.
title Speech-Based Cognitive Screening: A Systematic Evaluation of LLM Adaptation Strategies
topic Computation and Language
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2509.03525