# Efficient Medical Question Answering with Knowledge-Augmented Question Generation

arXiv: https://arxiv.org/abs/2405.14654 · HTML: https://mlsanity.com/paper/2405.14654/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 10 references that are in the map.
- First posted on arXiv 23 May 2024.

## Builds on (most cited first, 7 of 7)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [Capabilities of GPT-4 on Medical Challenge Problems](https://mlsanity.com/paper/2303.13375/) (2023)
- [Orca: Progressive Learning from Complex Explanation Traces of GPT-4](https://mlsanity.com/paper/2306.02707/) (2023)
- [PMC-LLaMA: Towards Building Open-source Language Models for Medicine](https://mlsanity.com/paper/2304.14454/) (2023)

## Built on by (most cited first, 2 of 2)

- [Continually Self-Improving Language Models for Bariatric Surgery Question--Answering](https://mlsanity.com/paper/2505.16102/) (2025)
- [Severity-Aware Curriculum Learning with Multi-Model Response Selection for Medical Text Generation](https://mlsanity.com/paper/2606.05510/) (2026)

## Abstract (arXiv)

In the expanding field of language model applications, medical knowledge representation remains a significant challenge due to the specialized nature of the domain. Large language models, such as GPT-4, obtain reasonable scores on medical question answering tasks, but smaller models are far behind. In this work, we introduce a method to improve the proficiency of a small language model in the medical domain by employing a two-fold approach. We first fine-tune the model on a corpus of medical textbooks. Then, we use GPT-4 to generate questions similar to the downstream task, prompted with textbook knowledge, and use them to fine-tune the model. Additionally, we introduce ECN-QA, a novel medical question answering dataset containing ``progressive questions'' composed of related sequential questions. We show the benefits of our training strategy on this dataset. The study's findings highlight the potential of small language models in the medical domain when appropriately fine-tuned. The code and weights are available at https://github.com/raidium-med/MQG.