A three-model majority-vote ensemble (LLaMA3, RoBERTa, SVM) classifies ADHD from post-scan narrative transcripts with F1 0.71, a modest and not statistically robust gain over single models.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Leveraging large language models and traditional machine learning ensembles for ADHD detection from narrative transcripts
A three-model majority-vote ensemble (LLaMA3, RoBERTa, SVM) classifies ADHD from post-scan narrative transcripts with F1 0.71, a modest and not statistically robust gain over single models.