REVIEW 5 cited by
Benchmarking Retrieval-Augmented Generation for Medicine
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
While large language models (LLMs) have achieved state-of-the-art performance on a wide range of medical question answering (QA) tasks, they still face challenges with hallucinations and outdated knowledge. Retrieval-augmented generation (RAG) is a promising solution and has been widely adopted. However, a RAG system can involve multiple flexible components, and there is a lack of best practices regarding the optimal RAG setting for various medical purposes. To systematically evaluate such systems, we propose the Medical Information Retrieval-Augmented Generation Evaluation (MIRAGE), a first-of-its-kind benchmark including 7,663 questions from five medical QA datasets. Using MIRAGE, we conducted large-scale experiments with over 1.8 trillion prompt tokens on 41 combinations of different corpora, retrievers, and backbone LLMs through the MedRAG toolkit introduced in this work. Overall, MedRAG improves the accuracy of six different LLMs by up to 18% over chain-of-thought prompting, elevating the performance of GPT-3.5 and Mixtral to GPT-4-level. Our results show that the combination of various medical corpora and retrievers achieves the best performance. In addition, we discovered a log-linear scaling property and the "lost-in-the-middle" effects in medical RAG. We believe our comprehensive evaluations can serve as practical guidelines for implementing RAG systems for medicine.
Forward citations
Cited by 5 Pith papers
-
Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generation
Clinical RAG can attribute real evidence about drug Y to queried drug X at high rates under adversarial retrieval, a failure invisible to faithfulness and citation metrics but detectable by entity-attribution verification.
-
HealthBranches: Synthesizing Clinically-Grounded Question Answering Datasets via Decision Pathways
A semi-automated pipeline turns clinical decision trees into 4,063 medical Q&A pairs with explicit reasoning paths, and early LLM benchmarks show models improve when given those paths.
-
Retrieval augmented generation based dynamic prompting for few-shot biomedical named entity recognition using large language models
Retrieval-based selection of in-context examples improves few-shot biomedical named entity recognition F1 over random selection, with TF-IDF and SBERT outperforming ColBERT and DPR.
-
Architecting Clinical Collaboration: Multi-Agent Reasoning Systems for Multimodal Medical VQA
A systematic study on dermatology VQA finds that multi-agent reasoning and retrieval architectures outperform fine-tuned open-source vision-language models, maintaining 70% accuracy under distribution shift.
-
A Comprehensive Graph Framework for Question Answering with Mode-Seeking Preference Alignment
GraphMPA combines an embedding-similarity hierarchical graph with mode-seeking preference optimization to improve RAG question answering on six datasets.
Discussion (0). Sign in to comment.