@inproceedings{shi-etal-2026-sarl,
title = "{SARL}-{ICD}: Structure-aware Contrastive Representation Learning with {LLM}-augmented Label Descriptions for Automatic {ICD} Coding",
author = "Shi, Jincheng and
Huang, Tianyang and
Zhu, Shanfeng",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1178/",
pages = "26993--27009",
ISBN = "979-8-89176-459-0",
abstract = "Automatic ICD coding is an extreme multi-label classification task that requires assigning standardized diagnostic codes to clinical notes. Recent pretrained language model (PLM) based methods achieve strong performance, but they often overfit to repetitive semi-structured patterns in discharge summaries rather than learning clinically meaningful semantics. Moreover, existing approaches insufficiently utilize the rich semantic information contained in ICD code descriptions. In this study, we propose SARL-ICD, a structure-aware framework for automatic ICD coding centered around two key ideas: contrastive representation learning and label-text semantic interaction. First, we introduce JMoCo, a Jaccard-guided MoCo-style pretraining strategy that constructs positive pairs using ICD-code similarity while restricting pretraining to clinically informative narrative sections. This design encourages the model to learn patient-specific clinical semantics. Second, we propose a lightweight label-text interaction module that injects semantic information from LLM-augmented ICD code descriptions into document representations. We further employ an adaptive fusion module to combine complementary strengths of different ICD coding architectures. Extensive experiments on MIMIC-III-full and MIMIC-IV demonstrate that our method achieves state-of-the-art performance across multiple evaluation metrics. Additional analyses further show that JMoCo improves representation similarity alignment and reduces structural shortcut learning in semi-structured clinical documents."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shi-etal-2026-sarl">
<titleInfo>
<title>SARL-ICD: Structure-aware Contrastive Representation Learning with LLM-augmented Label Descriptions for Automatic ICD Coding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jincheng</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyang</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shanfeng</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Automatic ICD coding is an extreme multi-label classification task that requires assigning standardized diagnostic codes to clinical notes. Recent pretrained language model (PLM) based methods achieve strong performance, but they often overfit to repetitive semi-structured patterns in discharge summaries rather than learning clinically meaningful semantics. Moreover, existing approaches insufficiently utilize the rich semantic information contained in ICD code descriptions. In this study, we propose SARL-ICD, a structure-aware framework for automatic ICD coding centered around two key ideas: contrastive representation learning and label-text semantic interaction. First, we introduce JMoCo, a Jaccard-guided MoCo-style pretraining strategy that constructs positive pairs using ICD-code similarity while restricting pretraining to clinically informative narrative sections. This design encourages the model to learn patient-specific clinical semantics. Second, we propose a lightweight label-text interaction module that injects semantic information from LLM-augmented ICD code descriptions into document representations. We further employ an adaptive fusion module to combine complementary strengths of different ICD coding architectures. Extensive experiments on MIMIC-III-full and MIMIC-IV demonstrate that our method achieves state-of-the-art performance across multiple evaluation metrics. Additional analyses further show that JMoCo improves representation similarity alignment and reduces structural shortcut learning in semi-structured clinical documents.</abstract>
<identifier type="citekey">shi-etal-2026-sarl</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1178/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>26993</start>
<end>27009</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SARL-ICD: Structure-aware Contrastive Representation Learning with LLM-augmented Label Descriptions for Automatic ICD Coding
%A Shi, Jincheng
%A Huang, Tianyang
%A Zhu, Shanfeng
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F shi-etal-2026-sarl
%X Automatic ICD coding is an extreme multi-label classification task that requires assigning standardized diagnostic codes to clinical notes. Recent pretrained language model (PLM) based methods achieve strong performance, but they often overfit to repetitive semi-structured patterns in discharge summaries rather than learning clinically meaningful semantics. Moreover, existing approaches insufficiently utilize the rich semantic information contained in ICD code descriptions. In this study, we propose SARL-ICD, a structure-aware framework for automatic ICD coding centered around two key ideas: contrastive representation learning and label-text semantic interaction. First, we introduce JMoCo, a Jaccard-guided MoCo-style pretraining strategy that constructs positive pairs using ICD-code similarity while restricting pretraining to clinically informative narrative sections. This design encourages the model to learn patient-specific clinical semantics. Second, we propose a lightweight label-text interaction module that injects semantic information from LLM-augmented ICD code descriptions into document representations. We further employ an adaptive fusion module to combine complementary strengths of different ICD coding architectures. Extensive experiments on MIMIC-III-full and MIMIC-IV demonstrate that our method achieves state-of-the-art performance across multiple evaluation metrics. Additional analyses further show that JMoCo improves representation similarity alignment and reduces structural shortcut learning in semi-structured clinical documents.
%U https://aclanthology.org/2026.emnlp-main.1178/
%P 26993-27009
Markdown (Informal)
[SARL-ICD: Structure-aware Contrastive Representation Learning with LLM-augmented Label Descriptions for Automatic ICD Coding](https://aclanthology.org/2026.emnlp-main.1178/) (Shi et al., EMNLP 2026)
ACL