A LoRA-tuned LLM integrates four complementary speech views to detect dementia, reaching 90.14% F1 on ADReSSo with ablation support for each view's contribution.
LoRA-Tuned Large Language Models for Dementia Detection via Multi-View Speech-Derived Features
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Early detection of dementia enables timely intervention, and reflecting cognitive impairment, spontaneous speech offers a non-invasive screening modality. Conventional approaches often focus on a single representational dimension -- such as acoustic descriptors, pause modeling, automatic speech recognition (ASR) transcripts, or multimodal fusion -- limiting integrative reasoning across heterogeneous cognitive symptoms. We propose a low-rank adaptation (LoRA)-tuned large language model (LLM) that performs structured multi-view reasoning over four complementary speech-derived signals: ASR transcripts with pause markers, discourse-level topic cues, temporal fluency statistics, and phonological sequences. These cues are encoded within a unified prompt, enabling a single LLM to learn a coherent decision function without modality-specific encoders or late-stage fusion. On ADReSSo, our best model achieves an F1-score of 90.14%, and ablation confirms the complementary contribution of each view.
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LoRA-Tuned Large Language Models for Dementia Detection via Multi-View Speech-Derived Features
A LoRA-tuned LLM integrates four complementary speech views to detect dementia, reaching 90.14% F1 on ADReSSo with ablation support for each view's contribution.