PubMedQA

Overview edit

Variants: PubMedQA

Associated Benchmarks

This dataset is used in 3 benchmarks:

• Few-Shot Learning - Metrics: Accuracy
• Question Answering - Metrics: Accuracy
• Retrieval - Metrics: Accuracy (Top-1)

Recent Benchmark Submissions

Research Papers

Recent papers with results on this dataset:

• MetaGen Blended RAG: Higher Accuracy for Domain-Specific Q&A Without Fine-Tuning (2025) -
• RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs (2024) -
• MediSwift: Efficient Sparse Pre-trained Biomedical Language Models (2024) -
• MEDITRON-70B: Scaling Medical Pretraining for Large Language Models (2023) -
• BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine (2023) -
• The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning (2023) -
• Towards Expert-Level Medical Question Answering with Large Language Models (2023) -
• Large Language Models Encode Clinical Knowledge (2022) -
• Galactica: A Large Language Model for Science (2022) -
• BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining (2022) -
• Can large language models reason about medical questions? (2022) -
• LinkBERT: Pretraining Language Models with Document Links (2022) -
• Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing (2020) -
• PubMedQA: A Dataset for Biomedical Research Question Answering (2019) -