@inproceedings{landes-etal-2026-socialstep,
title = "{S}ocial{S}tep: Fast Prediction of Social Determinants of Health",
author = "Landes, Paul and
Cross, Adam Richard and
Sun, Jimeng",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.846/",
doi = "10.63317/2t6bdjt7dvvi",
pages = "10802--10814",
abstract = "Given thousands of medical documents, how can we automatically uncover patients' social risk factors? Social Determinants of Health (SDoH) constitute a growing class of non-clinical risk factors that shape patient trajectories. While clinically significant, automatic detection of SDoH from free text remains understudied due to scarce and imbalanced training data. Current approaches often rely on monolithic large language models. We present SocialStep, a two-step hybrid pipeline that first uses a lightweight classifier to triage sentences and then applies a Large Language Model (LLM) for multilabel classification to the relevant subset. On the Medical Information Mart for Intensive Care III (MIMIC-III) dataset, SocialStep improves macro F1 by 5 points over the state-of-the-art baseline while running 12.2{\texttimes} faster. These findings demonstrate that integrating compact neural encoders with large language models provides a scalable and highly accurate framework for clinical NLP tasks, including SDoH extraction. Notably, we also observe some unexpected patterns in LLM performance. SocialStep offers a practical blueprint for hybrid model deployment that identifies critical social risk factors without prohibitive computational cost."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="landes-etal-2026-socialstep">
<titleInfo>
<title>SocialStep: Fast Prediction of Social Determinants of Health</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Landes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="given">Richard</namePart>
<namePart type="family">Cross</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jimeng</namePart>
<namePart type="family">Sun</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 Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Given thousands of medical documents, how can we automatically uncover patients’ social risk factors? Social Determinants of Health (SDoH) constitute a growing class of non-clinical risk factors that shape patient trajectories. While clinically significant, automatic detection of SDoH from free text remains understudied due to scarce and imbalanced training data. Current approaches often rely on monolithic large language models. We present SocialStep, a two-step hybrid pipeline that first uses a lightweight classifier to triage sentences and then applies a Large Language Model (LLM) for multilabel classification to the relevant subset. On the Medical Information Mart for Intensive Care III (MIMIC-III) dataset, SocialStep improves macro F1 by 5 points over the state-of-the-art baseline while running 12.2× faster. These findings demonstrate that integrating compact neural encoders with large language models provides a scalable and highly accurate framework for clinical NLP tasks, including SDoH extraction. Notably, we also observe some unexpected patterns in LLM performance. SocialStep offers a practical blueprint for hybrid model deployment that identifies critical social risk factors without prohibitive computational cost.</abstract>
<identifier type="citekey">landes-etal-2026-socialstep</identifier>
<identifier type="doi">10.63317/2t6bdjt7dvvi</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.846/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>10802</start>
<end>10814</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SocialStep: Fast Prediction of Social Determinants of Health
%A Landes, Paul
%A Cross, Adam Richard
%A Sun, Jimeng
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F landes-etal-2026-socialstep
%X Given thousands of medical documents, how can we automatically uncover patients’ social risk factors? Social Determinants of Health (SDoH) constitute a growing class of non-clinical risk factors that shape patient trajectories. While clinically significant, automatic detection of SDoH from free text remains understudied due to scarce and imbalanced training data. Current approaches often rely on monolithic large language models. We present SocialStep, a two-step hybrid pipeline that first uses a lightweight classifier to triage sentences and then applies a Large Language Model (LLM) for multilabel classification to the relevant subset. On the Medical Information Mart for Intensive Care III (MIMIC-III) dataset, SocialStep improves macro F1 by 5 points over the state-of-the-art baseline while running 12.2× faster. These findings demonstrate that integrating compact neural encoders with large language models provides a scalable and highly accurate framework for clinical NLP tasks, including SDoH extraction. Notably, we also observe some unexpected patterns in LLM performance. SocialStep offers a practical blueprint for hybrid model deployment that identifies critical social risk factors without prohibitive computational cost.
%R 10.63317/2t6bdjt7dvvi
%U https://aclanthology.org/2026.lrec-1.846/
%U https://doi.org/10.63317/2t6bdjt7dvvi
%P 10802-10814
Markdown (Informal)
[SocialStep: Fast Prediction of Social Determinants of Health](https://aclanthology.org/2026.lrec-1.846/) (Landes et al., LREC 2026)
ACL