@inproceedings{han-etal-2025-leveraging,
title = "Leveraging {LLM}-Generated Schema Descriptions for Unanswerable Question Detection in Clinical Data",
author = "Han, Donghee and
Lim, Seungjae and
Roh, Daeyoung and
Kim, Sangryul and
Kim, Sehyun and
Yi, Mun Yong",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.706/",
pages = "10594--10601",
abstract = "Recent advancements in large language models (LLMs) have boosted research on generating SQL queries from domain-specific questions, particularly in the medical domain. A key challenge is detecting and filtering unanswerable questions. Existing methods often relying on model uncertainty, but these require extra resources and lack interpretability. We propose a lightweight model that predicts relevant database schemas to detect unanswerable questions, enhancing interpretability and addressing the data imbalance in binary classification tasks. Furthermore, we found that LLM-generated schema descriptions can significantly enhance the prediction accuracy. Our method provides a resource-efficient solution for unanswerable question detection in domain-specific question answering systems."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="han-etal-2025-leveraging">
<titleInfo>
<title>Leveraging LLM-Generated Schema Descriptions for Unanswerable Question Detection in Clinical Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donghee</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seungjae</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daeyoung</namePart>
<namePart type="family">Roh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sangryul</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sehyun</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mun</namePart>
<namePart type="given">Yong</namePart>
<namePart type="family">Yi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advancements in large language models (LLMs) have boosted research on generating SQL queries from domain-specific questions, particularly in the medical domain. A key challenge is detecting and filtering unanswerable questions. Existing methods often relying on model uncertainty, but these require extra resources and lack interpretability. We propose a lightweight model that predicts relevant database schemas to detect unanswerable questions, enhancing interpretability and addressing the data imbalance in binary classification tasks. Furthermore, we found that LLM-generated schema descriptions can significantly enhance the prediction accuracy. Our method provides a resource-efficient solution for unanswerable question detection in domain-specific question answering systems.</abstract>
<identifier type="citekey">han-etal-2025-leveraging</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.706/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>10594</start>
<end>10601</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging LLM-Generated Schema Descriptions for Unanswerable Question Detection in Clinical Data
%A Han, Donghee
%A Lim, Seungjae
%A Roh, Daeyoung
%A Kim, Sangryul
%A Kim, Sehyun
%A Yi, Mun Yong
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F han-etal-2025-leveraging
%X Recent advancements in large language models (LLMs) have boosted research on generating SQL queries from domain-specific questions, particularly in the medical domain. A key challenge is detecting and filtering unanswerable questions. Existing methods often relying on model uncertainty, but these require extra resources and lack interpretability. We propose a lightweight model that predicts relevant database schemas to detect unanswerable questions, enhancing interpretability and addressing the data imbalance in binary classification tasks. Furthermore, we found that LLM-generated schema descriptions can significantly enhance the prediction accuracy. Our method provides a resource-efficient solution for unanswerable question detection in domain-specific question answering systems.
%U https://aclanthology.org/2025.coling-main.706/
%P 10594-10601
Markdown (Informal)
[Leveraging LLM-Generated Schema Descriptions for Unanswerable Question Detection in Clinical Data](https://aclanthology.org/2025.coling-main.706/) (Han et al., COLING 2025)
ACL