@inproceedings{gundabathula-kolar-2024-promptmind,
title = "{P}rompt{M}ind Team at {EHRSQL}-2024: Improving Reliability of {SQL} Generation using Ensemble {LLM}s",
author = "Gundabathula, Satya and
Kolar, Sriram",
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-1.34/",
doi = "10.18653/v1/2024.clinicalnlp-1.34",
pages = "360--366",
abstract = "This paper presents our approach to the EHRSQL-2024 shared task, which aims to develop a reliable Text-to-SQL system for electronic health records. We propose two approaches that leverage large language models (LLMs) for prompting and fine-tuning to generate EHRSQL queries. In both techniques, we concentrate on bridging the gap between the real-world knowledge on which LLMs are trained and the domain-specific knowledge required for the task. The paper provides the results of each approach individually, demonstrating that they achieve high execution accuracy. Additionally, we show that an ensemble approach further enhances generation reliability by reducing errors. This approach secured us 2nd place in the shared task competition. The methodologies outlined in this paper are designed to be transferable to domain-specific Text-to-SQL problems that emphasize both accuracy and reliability."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gundabathula-kolar-2024-promptmind">
<titleInfo>
<title>PromptMind Team at EHRSQL-2024: Improving Reliability of SQL Generation using Ensemble LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Satya</namePart>
<namePart type="family">Gundabathula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sriram</namePart>
<namePart type="family">Kolar</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 approach to the EHRSQL-2024 shared task, which aims to develop a reliable Text-to-SQL system for electronic health records. We propose two approaches that leverage large language models (LLMs) for prompting and fine-tuning to generate EHRSQL queries. In both techniques, we concentrate on bridging the gap between the real-world knowledge on which LLMs are trained and the domain-specific knowledge required for the task. The paper provides the results of each approach individually, demonstrating that they achieve high execution accuracy. Additionally, we show that an ensemble approach further enhances generation reliability by reducing errors. This approach secured us 2nd place in the shared task competition. The methodologies outlined in this paper are designed to be transferable to domain-specific Text-to-SQL problems that emphasize both accuracy and reliability.</abstract>
<identifier type="citekey">gundabathula-kolar-2024-promptmind</identifier>
<identifier type="doi">10.18653/v1/2024.clinicalnlp-1.34</identifier>
<location>
<url>https://aclanthology.org/2024.clinicalnlp-1.34/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>360</start>
<end>366</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PromptMind Team at EHRSQL-2024: Improving Reliability of SQL Generation using Ensemble LLMs
%A Gundabathula, Satya
%A Kolar, Sriram
%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 gundabathula-kolar-2024-promptmind
%X This paper presents our approach to the EHRSQL-2024 shared task, which aims to develop a reliable Text-to-SQL system for electronic health records. We propose two approaches that leverage large language models (LLMs) for prompting and fine-tuning to generate EHRSQL queries. In both techniques, we concentrate on bridging the gap between the real-world knowledge on which LLMs are trained and the domain-specific knowledge required for the task. The paper provides the results of each approach individually, demonstrating that they achieve high execution accuracy. Additionally, we show that an ensemble approach further enhances generation reliability by reducing errors. This approach secured us 2nd place in the shared task competition. The methodologies outlined in this paper are designed to be transferable to domain-specific Text-to-SQL problems that emphasize both accuracy and reliability.
%R 10.18653/v1/2024.clinicalnlp-1.34
%U https://aclanthology.org/2024.clinicalnlp-1.34/
%U https://doi.org/10.18653/v1/2024.clinicalnlp-1.34
%P 360-366
Markdown (Informal)
[PromptMind Team at EHRSQL-2024: Improving Reliability of SQL Generation using Ensemble LLMs](https://aclanthology.org/2024.clinicalnlp-1.34/) (Gundabathula & Kolar, ClinicalNLP 2024)
ACL