@inproceedings{lekuthai-etal-2025-ec,
title = "{EC}-{RAFT}: Automated Generation of Clinical Trial Eligibility Criteria through Retrieval-Augmented Fine-Tuning",
author = "Lekuthai, Nopporn and
Pewngam, Nattawit and
Sokrai, Supitcha and
Achakulvisut, Titipat",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.491/",
doi = "10.18653/v1/2025.findings-acl.491",
pages = "9432--9444",
ISBN = "979-8-89176-256-5",
abstract = "Eligibility criteria (EC) are critical components of clinical trial design, defining the parameters for participant inclusion and exclusion. However, designing EC remains a complex, expertise-intensive process. Traditional approaches to EC generation may fail to produce comprehensive, contextually appropriate criteria. To address these challenges, we introduce EC-RAFT, a method that utilizes Retrieval-Augmented Fine-Tuning (RAFT) to generate structured and cohesive EC directly from clinical trial titles and descriptions. EC-RAFT integrates contextual retrieval, synthesized intermediate reasoning, and fine-tuned language models to produce comprehensive EC sets. To enhance clinical alignment evaluation with referenced criteria, we also propose an LLM-guided evaluation pipeline. Our results demonstrate that our solution, which uses Llama-3.1-8B-Instruct as a base model, achieves a BERTScore of 86.23 and an EC-matched LLM-as-a-Judge score of 1.66 out of 3, outperforming zero-shot Llama-3.1 and Gemini-1.5 by 0.41 and 0.11 points, respectively. On top of that, EC-RAFT also outperforms other fine-tuned versions of Llama-3.1. EC-RAFT was trained in a low-cost setup and, therefore, can be used as a practical solution for EC generation while ensuring quality and relevance in clinical trial design. We release our code on GitHub at https://github.com/biodatlab/ec-raft/"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lekuthai-etal-2025-ec">
<titleInfo>
<title>EC-RAFT: Automated Generation of Clinical Trial Eligibility Criteria through Retrieval-Augmented Fine-Tuning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nopporn</namePart>
<namePart type="family">Lekuthai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nattawit</namePart>
<namePart type="family">Pewngam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Supitcha</namePart>
<namePart type="family">Sokrai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Titipat</namePart>
<namePart type="family">Achakulvisut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Eligibility criteria (EC) are critical components of clinical trial design, defining the parameters for participant inclusion and exclusion. However, designing EC remains a complex, expertise-intensive process. Traditional approaches to EC generation may fail to produce comprehensive, contextually appropriate criteria. To address these challenges, we introduce EC-RAFT, a method that utilizes Retrieval-Augmented Fine-Tuning (RAFT) to generate structured and cohesive EC directly from clinical trial titles and descriptions. EC-RAFT integrates contextual retrieval, synthesized intermediate reasoning, and fine-tuned language models to produce comprehensive EC sets. To enhance clinical alignment evaluation with referenced criteria, we also propose an LLM-guided evaluation pipeline. Our results demonstrate that our solution, which uses Llama-3.1-8B-Instruct as a base model, achieves a BERTScore of 86.23 and an EC-matched LLM-as-a-Judge score of 1.66 out of 3, outperforming zero-shot Llama-3.1 and Gemini-1.5 by 0.41 and 0.11 points, respectively. On top of that, EC-RAFT also outperforms other fine-tuned versions of Llama-3.1. EC-RAFT was trained in a low-cost setup and, therefore, can be used as a practical solution for EC generation while ensuring quality and relevance in clinical trial design. We release our code on GitHub at https://github.com/biodatlab/ec-raft/</abstract>
<identifier type="citekey">lekuthai-etal-2025-ec</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.491</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.491/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>9432</start>
<end>9444</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EC-RAFT: Automated Generation of Clinical Trial Eligibility Criteria through Retrieval-Augmented Fine-Tuning
%A Lekuthai, Nopporn
%A Pewngam, Nattawit
%A Sokrai, Supitcha
%A Achakulvisut, Titipat
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F lekuthai-etal-2025-ec
%X Eligibility criteria (EC) are critical components of clinical trial design, defining the parameters for participant inclusion and exclusion. However, designing EC remains a complex, expertise-intensive process. Traditional approaches to EC generation may fail to produce comprehensive, contextually appropriate criteria. To address these challenges, we introduce EC-RAFT, a method that utilizes Retrieval-Augmented Fine-Tuning (RAFT) to generate structured and cohesive EC directly from clinical trial titles and descriptions. EC-RAFT integrates contextual retrieval, synthesized intermediate reasoning, and fine-tuned language models to produce comprehensive EC sets. To enhance clinical alignment evaluation with referenced criteria, we also propose an LLM-guided evaluation pipeline. Our results demonstrate that our solution, which uses Llama-3.1-8B-Instruct as a base model, achieves a BERTScore of 86.23 and an EC-matched LLM-as-a-Judge score of 1.66 out of 3, outperforming zero-shot Llama-3.1 and Gemini-1.5 by 0.41 and 0.11 points, respectively. On top of that, EC-RAFT also outperforms other fine-tuned versions of Llama-3.1. EC-RAFT was trained in a low-cost setup and, therefore, can be used as a practical solution for EC generation while ensuring quality and relevance in clinical trial design. We release our code on GitHub at https://github.com/biodatlab/ec-raft/
%R 10.18653/v1/2025.findings-acl.491
%U https://aclanthology.org/2025.findings-acl.491/
%U https://doi.org/10.18653/v1/2025.findings-acl.491
%P 9432-9444
Markdown (Informal)
[EC-RAFT: Automated Generation of Clinical Trial Eligibility Criteria through Retrieval-Augmented Fine-Tuning](https://aclanthology.org/2025.findings-acl.491/) (Lekuthai et al., Findings 2025)
ACL