@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://aclanthology.org/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 {`}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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="valiev-tutubalina-2024-hse">
<titleInfo>
<title>HSE NLP Team at MEDIQA-CORR 2024 Task: In-Prompt Ensemble with Entities and Knowledge Graph for Medical Error Correction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Airat</namePart>
<namePart type="family">Valiev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Tutubalina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Clinical Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Naumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asma</namePart>
<namePart type="family">Ben Abacha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danielle</namePart>
<namePart type="family">Bitterman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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 ‘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.</abstract>
<identifier type="citekey">valiev-tutubalina-2024-hse</identifier>
<identifier type="doi">10.18653/v1/2024.clinicalnlp-1.47</identifier>
<location>
<url>https://aclanthology.org/2024.clinicalnlp-1.47</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>470</start>
<end>482</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HSE NLP Team at MEDIQA-CORR 2024 Task: In-Prompt Ensemble with Entities and Knowledge Graph for Medical Error Correction
%A Valiev, Airat
%A Tutubalina, Elena
%Y Naumann, Tristan
%Y Ben Abacha, Asma
%Y Bethard, Steven
%Y Roberts, Kirk
%Y Bitterman, Danielle
%S Proceedings of the 6th Clinical Natural Language Processing Workshop
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F valiev-tutubalina-2024-hse
%X 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 ‘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.
%R 10.18653/v1/2024.clinicalnlp-1.47
%U https://aclanthology.org/2024.clinicalnlp-1.47
%U https://doi.org/10.18653/v1/2024.clinicalnlp-1.47
%P 470-482
Markdown (Informal)
[HSE NLP Team at MEDIQA-CORR 2024 Task: In-Prompt Ensemble with Entities and Knowledge Graph for Medical Error Correction](https://aclanthology.org/2024.clinicalnlp-1.47) (Valiev & Tutubalina, ClinicalNLP-WS 2024)
ACL