@inproceedings{valiev-tutubalina-2024-hse,
    title = "{HSE} {NLP} Team at {MEDIQA}-{CORR} 2024 Task: In-Prompt Ensemble with Entities and Knowledge Graph for Medical Error Correction",
    author = "Valiev, Airat  and
      Tutubalina, Elena",
    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://preview.aclanthology.org/add-emnlp-2024-awards/2024.clinicalnlp-1.47/",
    doi = "10.18653/v1/2024.clinicalnlp-1.47",
    pages = "470--482",
    abstract = "This paper presents our LLM-based system designed for the MEDIQA-CORR @ NAACL-ClinicalNLP 2024 Shared Task 3, focusing on medical error detection and correction in medical records. Our approach consists of three key components: entity extraction, prompt engineering, and ensemble. First, we automatically extract biomedical entities such as therapies, diagnoses, and biological species. Next, we explore few-shot learning techniques and incorporate graph information from the MeSH database for the identified entities. Finally, we investigate two methods for ensembling: (i) combining the predictions of three previous LLMs using an AND strategy within a prompt and (ii) integrating the previous predictions into the prompt as separate {\textquoteleft}expert' solutions, accompanied by trust scores representing their performance. The latter system ranked second with a BERTScore score of 0.8059 and third with an aggregated score of 0.7806 out of the 15 teams' solutions in the shared task."
}