Avi-ad Avraam Buskila
2 papers · Latest:
Natural Language Processing
Domain Fine-Tuning vs. Retrieval-Augmented Generation for Medical Multiple-Choice Question Answering: A Controlled Comparison at the 4B-Parameter Scale
This paper compares domain fine-tuning and retrieval-augmented generation for medical question answering with 4B LLMs, finding fine-tuning superior.
2604.23801
Information RetrievalEvaluating Small Open LLMs for Medical Question Answering: A Practical Framework
This paper introduces an open-source framework to evaluate small open LLMs for medical QA, highlighting low reproducibility as a critical safety concern.
2604.10535
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.