@inproceedings{kumar-2026-thesis,
title = "Thesis Proposal: Stability-Aware, Evidence-Grounded Knowledge Graph for Substance Use Disorders and Social Determinants of Health",
author = "Kumar, Gautham Vijay",
editor = "Baez Santamaria, Selene and
Somayajula, Sai Ashish and
Yamaguchi, Atsuki",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 4: Student Research Workshop)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-srw.58/",
pages = "787--796",
ISBN = "979-8-89176-383-8",
abstract = "Clinical Natural Language Processing (NLP) integrates large language models (LLMs) to extract biomedical insights from unstructured clinical text. Most named entity recognition (NER) and relation extraction (RE) datasets rely on manual annotation, which is costly and difficult to scale. Many biomedical knowledge graphs (KG) suffer from underspecified relations, conflate causal and correlational claims, and edges lack evidence for reasoning. This dissertation presents a semantic stability framework for constructing explainable KGs, highlighting stable extraction as fundamental for scalable NER and RE, and essential for graph structure. We applied this to Substance Use Disorders (SUD) and Social Determinants of Health (SDOH) from PubMed corpus and NER and RE annotation guide. Multiple LLMs perform extraction under shared semantic constraints, with disagreements resolved through Human-in-the-Loop (HITL) validation. We define semantic stability through NER and RE metrics, using stabilized gold data for model training and evaluation. We then develop a claim-centered KG, where edges represent evidence, provenance, relation type, directionality, polarity, and stability indicators. This benchmark and pipeline supports multi-hop reasoning, triadic SUD{--}SDOH{--}SUD mediation patterns, and feedback loop analysis. This will advance etiological inquiries and data-driven health policy analysis."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kumar-2026-thesis">
<titleInfo>
<title>Thesis Proposal: Stability-Aware, Evidence-Grounded Knowledge Graph for Substance Use Disorders and Social Determinants of Health</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gautham</namePart>
<namePart type="given">Vijay</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Selene</namePart>
<namePart type="family">Baez Santamaria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="given">Ashish</namePart>
<namePart type="family">Somayajula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atsuki</namePart>
<namePart type="family">Yamaguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-383-8</identifier>
</relatedItem>
<abstract>Clinical Natural Language Processing (NLP) integrates large language models (LLMs) to extract biomedical insights from unstructured clinical text. Most named entity recognition (NER) and relation extraction (RE) datasets rely on manual annotation, which is costly and difficult to scale. Many biomedical knowledge graphs (KG) suffer from underspecified relations, conflate causal and correlational claims, and edges lack evidence for reasoning. This dissertation presents a semantic stability framework for constructing explainable KGs, highlighting stable extraction as fundamental for scalable NER and RE, and essential for graph structure. We applied this to Substance Use Disorders (SUD) and Social Determinants of Health (SDOH) from PubMed corpus and NER and RE annotation guide. Multiple LLMs perform extraction under shared semantic constraints, with disagreements resolved through Human-in-the-Loop (HITL) validation. We define semantic stability through NER and RE metrics, using stabilized gold data for model training and evaluation. We then develop a claim-centered KG, where edges represent evidence, provenance, relation type, directionality, polarity, and stability indicators. This benchmark and pipeline supports multi-hop reasoning, triadic SUD–SDOH–SUD mediation patterns, and feedback loop analysis. This will advance etiological inquiries and data-driven health policy analysis.</abstract>
<identifier type="citekey">kumar-2026-thesis</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-srw.58/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>787</start>
<end>796</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Thesis Proposal: Stability-Aware, Evidence-Grounded Knowledge Graph for Substance Use Disorders and Social Determinants of Health
%A Kumar, Gautham Vijay
%Y Baez Santamaria, Selene
%Y Somayajula, Sai Ashish
%Y Yamaguchi, Atsuki
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-383-8
%F kumar-2026-thesis
%X Clinical Natural Language Processing (NLP) integrates large language models (LLMs) to extract biomedical insights from unstructured clinical text. Most named entity recognition (NER) and relation extraction (RE) datasets rely on manual annotation, which is costly and difficult to scale. Many biomedical knowledge graphs (KG) suffer from underspecified relations, conflate causal and correlational claims, and edges lack evidence for reasoning. This dissertation presents a semantic stability framework for constructing explainable KGs, highlighting stable extraction as fundamental for scalable NER and RE, and essential for graph structure. We applied this to Substance Use Disorders (SUD) and Social Determinants of Health (SDOH) from PubMed corpus and NER and RE annotation guide. Multiple LLMs perform extraction under shared semantic constraints, with disagreements resolved through Human-in-the-Loop (HITL) validation. We define semantic stability through NER and RE metrics, using stabilized gold data for model training and evaluation. We then develop a claim-centered KG, where edges represent evidence, provenance, relation type, directionality, polarity, and stability indicators. This benchmark and pipeline supports multi-hop reasoning, triadic SUD–SDOH–SUD mediation patterns, and feedback loop analysis. This will advance etiological inquiries and data-driven health policy analysis.
%U https://aclanthology.org/2026.eacl-srw.58/
%P 787-796
Markdown (Informal)
[Thesis Proposal: Stability-Aware, Evidence-Grounded Knowledge Graph for Substance Use Disorders and Social Determinants of Health](https://aclanthology.org/2026.eacl-srw.58/) (Kumar, EACL 2026)
ACL