A QLoRA-fine-tuned Llama 3.2-3B-Instruct with RAG shows mixed benchmark results (MedMCQA 56.4% vs 50.9% base), but the hospital-data RAG component is not evaluated.
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
-
Lightweight Clinical Decision Support System using QLoRA-Fine-Tuned LLMs and Retrieval-Augmented Generation
A QLoRA-fine-tuned Llama 3.2-3B-Instruct with RAG shows mixed benchmark results (MedMCQA 56.4% vs 50.9% base), but the hospital-data RAG component is not evaluated.