@inproceedings{lorenzo-etal-2026-generating,
title = "Generating Linguistically Diverse and Semantically Faithful Patient Reports",
author = "Lorenzo, Alejandra and
Coulet, Adrien and
Gardent, Claire",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.2/",
pages = "24--48",
ISBN = "979-8-89176-439-2",
abstract = "To protect patient privacy, medical models are frequently trained on synthetic datasets. Focusing on 13 clinical attributes commonly found in breast cancer records, we propose a synthetic data generation framework in which each generated sample is a data{--}report pair: the structured data capture the 13 attributes of interest, while the accompanying (French) text simulates a corresponding breast cancer pathology report. Data privacy and coverage are obtained by generating the structured data using a tabular data synthesiser. In this work, we focus on enhancing the diversity and quality of the generated texts through a combination of data-driven knowledge distillation, data filtering and data combination. Our findings suggest that the quality of the training data used for the student model outweighs its quantity; that combining data from multiple teachers helps improve performance; and that a compact model (Mistral 7B) can match the zero-shot Information Extraction performance of a significantly larger model (MedGemma 27B) when fine-tuned on high-quality synthetic data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lorenzo-etal-2026-generating">
<titleInfo>
<title>Generating Linguistically Diverse and Semantically Faithful Patient Reports</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alejandra</namePart>
<namePart type="family">Lorenzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrien</namePart>
<namePart type="family">Coulet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="family">Gardent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>To protect patient privacy, medical models are frequently trained on synthetic datasets. Focusing on 13 clinical attributes commonly found in breast cancer records, we propose a synthetic data generation framework in which each generated sample is a data–report pair: the structured data capture the 13 attributes of interest, while the accompanying (French) text simulates a corresponding breast cancer pathology report. Data privacy and coverage are obtained by generating the structured data using a tabular data synthesiser. In this work, we focus on enhancing the diversity and quality of the generated texts through a combination of data-driven knowledge distillation, data filtering and data combination. Our findings suggest that the quality of the training data used for the student model outweighs its quantity; that combining data from multiple teachers helps improve performance; and that a compact model (Mistral 7B) can match the zero-shot Information Extraction performance of a significantly larger model (MedGemma 27B) when fine-tuned on high-quality synthetic data.</abstract>
<identifier type="citekey">lorenzo-etal-2026-generating</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.2/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>24</start>
<end>48</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating Linguistically Diverse and Semantically Faithful Patient Reports
%A Lorenzo, Alejandra
%A Coulet, Adrien
%A Gardent, Claire
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F lorenzo-etal-2026-generating
%X To protect patient privacy, medical models are frequently trained on synthetic datasets. Focusing on 13 clinical attributes commonly found in breast cancer records, we propose a synthetic data generation framework in which each generated sample is a data–report pair: the structured data capture the 13 attributes of interest, while the accompanying (French) text simulates a corresponding breast cancer pathology report. Data privacy and coverage are obtained by generating the structured data using a tabular data synthesiser. In this work, we focus on enhancing the diversity and quality of the generated texts through a combination of data-driven knowledge distillation, data filtering and data combination. Our findings suggest that the quality of the training data used for the student model outweighs its quantity; that combining data from multiple teachers helps improve performance; and that a compact model (Mistral 7B) can match the zero-shot Information Extraction performance of a significantly larger model (MedGemma 27B) when fine-tuned on high-quality synthetic data.
%U https://aclanthology.org/2026.aacl-long.2/
%P 24-48
Markdown (Informal)
[Generating Linguistically Diverse and Semantically Faithful Patient Reports](https://aclanthology.org/2026.aacl-long.2/) (Lorenzo et al., AACL-IJCNLP 2026)
ACL
- Alejandra Lorenzo, Adrien Coulet, and Claire Gardent. 2026. Generating Linguistically Diverse and Semantically Faithful Patient Reports. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 24–48, Hengqin, China. Association for Computational Linguistics.