@inproceedings{lovon-melgarejo-etal-2026-greyc,
title = "{GREYC} at {CRF} Filling 2026: Rewrite Before You Extract - Rewriting Clinical Notes for Automated {CRF}",
author = {Lovon-Melgarejo, Jesus and
Pantin, J{\'e}r{\'e}mie and
Dias, Ga{\"e}l},
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-1.34/",
doi = "10.63317/323qntyvhp3m",
pages = "384--389",
abstract = "This paper describes the system we submitted to the CRF:filling 2026 shared task. We propose a modular, LLM-based framework including an LLM as rewriter, which enhances the original clinical note from the perspective of each target CRF item; an LLM extractor, which retrieves the relevant value using a k-shot prompting strategy; and an LLM as a judge, which determines whether the clinical note contains evidence to support a given answer, defaulting to `unknown' otherwise. We evaluated our system on the English portion of the dataset; our complete framework achieves a macro-F1 of 0.64 on the development set. Our analysis reveals that while the rewriting step effectively generates correct factual information, it also increases false positives. The judge component mitigates this by adopting a conservative prediction strategy that substantially reduces false positives at the cost of a moderate reduction in true positives, yielding higher precision and better alignment with the shared task metric. On the test set, a light version of our system ranked 21 out of 32 public submissions, achieving a macro-F1 of 0.45."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lovon-melgarejo-etal-2026-greyc">
<titleInfo>
<title>GREYC at CRF Filling 2026: Rewrite Before You Extract - Rewriting Clinical Notes for Automated CRF</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jesus</namePart>
<namePart type="family">Lovon-Melgarejo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jérémie</namePart>
<namePart type="family">Pantin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaël</namePart>
<namePart type="family">Dias</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>This paper describes the system we submitted to the CRF:filling 2026 shared task. We propose a modular, LLM-based framework including an LLM as rewriter, which enhances the original clinical note from the perspective of each target CRF item; an LLM extractor, which retrieves the relevant value using a k-shot prompting strategy; and an LLM as a judge, which determines whether the clinical note contains evidence to support a given answer, defaulting to ‘unknown’ otherwise. We evaluated our system on the English portion of the dataset; our complete framework achieves a macro-F1 of 0.64 on the development set. Our analysis reveals that while the rewriting step effectively generates correct factual information, it also increases false positives. The judge component mitigates this by adopting a conservative prediction strategy that substantially reduces false positives at the cost of a moderate reduction in true positives, yielding higher precision and better alignment with the shared task metric. On the test set, a light version of our system ranked 21 out of 32 public submissions, achieving a macro-F1 of 0.45.</abstract>
<identifier type="citekey">lovon-melgarejo-etal-2026-greyc</identifier>
<identifier type="doi">10.63317/323qntyvhp3m</identifier>
<location>
<url>https://aclanthology.org/2026.cl4health-1.34/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>384</start>
<end>389</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GREYC at CRF Filling 2026: Rewrite Before You Extract - Rewriting Clinical Notes for Automated CRF
%A Lovon-Melgarejo, Jesus
%A Pantin, Jérémie
%A Dias, Gaël
%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 lovon-melgarejo-etal-2026-greyc
%X This paper describes the system we submitted to the CRF:filling 2026 shared task. We propose a modular, LLM-based framework including an LLM as rewriter, which enhances the original clinical note from the perspective of each target CRF item; an LLM extractor, which retrieves the relevant value using a k-shot prompting strategy; and an LLM as a judge, which determines whether the clinical note contains evidence to support a given answer, defaulting to ‘unknown’ otherwise. We evaluated our system on the English portion of the dataset; our complete framework achieves a macro-F1 of 0.64 on the development set. Our analysis reveals that while the rewriting step effectively generates correct factual information, it also increases false positives. The judge component mitigates this by adopting a conservative prediction strategy that substantially reduces false positives at the cost of a moderate reduction in true positives, yielding higher precision and better alignment with the shared task metric. On the test set, a light version of our system ranked 21 out of 32 public submissions, achieving a macro-F1 of 0.45.
%R 10.63317/323qntyvhp3m
%U https://aclanthology.org/2026.cl4health-1.34/
%U https://doi.org/10.63317/323qntyvhp3m
%P 384-389
Markdown (Informal)
[GREYC at CRF Filling 2026: Rewrite Before You Extract - Rewriting Clinical Notes for Automated CRF](https://aclanthology.org/2026.cl4health-1.34/) (Lovon-Melgarejo et al., CL4Health 2026)
ACL