@inproceedings{khlaut-etal-2024-efficient,
    title = "Efficient Medical Question Answering with Knowledge-Augmented Question Generation",
    author = "Khlaut, Julien  and
      Dancette, Corentin  and
      Ferreres, Elodie  and
      Alaedine, Benani  and
      Herent, Herent  and
      Manceron, Pierre",
    editor = "Naumann, Tristan  and
      Ben Abacha, Asma  and
      Bethard, Steven  and
      Roberts, Kirk  and
      Bitterman, Danielle",
    booktitle = "Proceedings of the 6th Clinical Natural Language Processing Workshop",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.clinicalnlp-1.2",
    doi = "10.18653/v1/2024.clinicalnlp-1.2",
    pages = "10--20",
    abstract = "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 QA 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.",
}