@inproceedings{yang-etal-2026-datasets,
title = "Datasets for a Chatbot for Clinical Trial Search",
author = "Yang, Yumeng and
Ludmir, Ethan and
Roberts, Kirk",
editor = "Gupta, Deepak and
Thompson, Paul and
Ananiadou, Sophia and
Demner-Fushman, Dina",
booktitle = "Proceedings of the Third Workshop on Patient-Oriented Language Processing ({CL}4{H}ealth) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.cl4health-1.13/",
doi = "10.63317/3pk9cracmxy7",
pages = "139--148",
abstract = "Matching patients to clinical trials is a critical bottleneck hindered by complex eligibility criteria. While conversational AI offers a promising solution, its safe deployment depends on high-quality, domain specific data. This paper introduces three benchmark datasets designed to support the development and evaluation of conversational agents for clinical trial pre-screening. First, a manually-annotated paired-criterion dataset provides a gold standard for structuring raw criteria, which we used to objectively group 12,596 criteria. Second, we curated a human-authored question benchmark to validate the clinical fidelity and patient-centric clarity of questions generated by a medical LLM, ensuring the AI{'}s dialogue is accurate and understandable. Third, we constructed a human-validated assessment corpus of criterion-question-answer tuples with human-labeled outcomes to evaluate criterion classification based on a patient{'}s answer to a generated question. The primary contribution of this work is a foundational set of benchmark datasets, designed to support and evaluate key components for a chatbot for clinical trial search."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2026-datasets">
<titleInfo>
<title>Datasets for a Chatbot for Clinical Trial Search</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yumeng</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ethan</namePart>
<namePart type="family">Ludmir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Deepak</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Thompson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Matching patients to clinical trials is a critical bottleneck hindered by complex eligibility criteria. While conversational AI offers a promising solution, its safe deployment depends on high-quality, domain specific data. This paper introduces three benchmark datasets designed to support the development and evaluation of conversational agents for clinical trial pre-screening. First, a manually-annotated paired-criterion dataset provides a gold standard for structuring raw criteria, which we used to objectively group 12,596 criteria. Second, we curated a human-authored question benchmark to validate the clinical fidelity and patient-centric clarity of questions generated by a medical LLM, ensuring the AI’s dialogue is accurate and understandable. Third, we constructed a human-validated assessment corpus of criterion-question-answer tuples with human-labeled outcomes to evaluate criterion classification based on a patient’s answer to a generated question. The primary contribution of this work is a foundational set of benchmark datasets, designed to support and evaluate key components for a chatbot for clinical trial search.</abstract>
<identifier type="citekey">yang-etal-2026-datasets</identifier>
<identifier type="doi">10.63317/3pk9cracmxy7</identifier>
<location>
<url>https://aclanthology.org/2026.cl4health-1.13/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>139</start>
<end>148</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Datasets for a Chatbot for Clinical Trial Search
%A Yang, Yumeng
%A Ludmir, Ethan
%A Roberts, Kirk
%Y Gupta, Deepak
%Y Thompson, Paul
%Y Ananiadou, Sophia
%Y Demner-Fushman, Dina
%S Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F yang-etal-2026-datasets
%X Matching patients to clinical trials is a critical bottleneck hindered by complex eligibility criteria. While conversational AI offers a promising solution, its safe deployment depends on high-quality, domain specific data. This paper introduces three benchmark datasets designed to support the development and evaluation of conversational agents for clinical trial pre-screening. First, a manually-annotated paired-criterion dataset provides a gold standard for structuring raw criteria, which we used to objectively group 12,596 criteria. Second, we curated a human-authored question benchmark to validate the clinical fidelity and patient-centric clarity of questions generated by a medical LLM, ensuring the AI’s dialogue is accurate and understandable. Third, we constructed a human-validated assessment corpus of criterion-question-answer tuples with human-labeled outcomes to evaluate criterion classification based on a patient’s answer to a generated question. The primary contribution of this work is a foundational set of benchmark datasets, designed to support and evaluate key components for a chatbot for clinical trial search.
%R 10.63317/3pk9cracmxy7
%U https://aclanthology.org/2026.cl4health-1.13/
%U https://doi.org/10.63317/3pk9cracmxy7
%P 139-148
Markdown (Informal)
[Datasets for a Chatbot for Clinical Trial Search](https://aclanthology.org/2026.cl4health-1.13/) (Yang et al., CL4Health 2026)
ACL
- Yumeng Yang, Ethan Ludmir, and Kirk Roberts. 2026. Datasets for a Chatbot for Clinical Trial Search. In Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026, pages 139–148, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).