A compact 15-feature set using LLM-generated content coverage and TF-IDF class similarities reaches 85.4% accuracy for Alzheimer's detection on ADReSS, beating 40 traditional linguistic features.
We introduced the concept of leveraging TF-IDF alongside ad- vanced LLMs’ viusal processing ability to generate useful fea- tures
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Devising a Set of Compact and Explainable Spoken Language Feature for Screening Alzheimer's Disease
A compact 15-feature set using LLM-generated content coverage and TF-IDF class similarities reaches 85.4% accuracy for Alzheimer's detection on ADReSS, beating 40 traditional linguistic features.