LLM Prompt-Tuning with LoRA for Speech-Based Alzheimer's Detection
A non-invasive Alzheimer's-disease detection method that classifies speech-derived text with a pretrained large language model (LLaMA2) adapted via a prompt fine-tuning / prompt-based learning strategy and conditional learning. To work under limited compute, it uses parameter-efficient LoRA (low-rank adaptation) instead of full fine-tuning. Under 10-fold cross-validation it attains 81.31% accuracy, a 4.46% absolute gain over a BERT baseline, and is proposed as a route to accessible at-home smartphone screening for dementia.
Alzheimer’s disease detection based on large language model prompt engineering Tian Zheng1,2
Research paper (cs.HC) proposing a non-invasive, low-cost method to detect Alzheimer's disease from speech using large-language-model prompt engineering. Motivated by aging populations and scarce, lo…