@inproceedings{jalan-etal-2026-ontodiagnose,
title = "{O}nto{D}iagnose: Ontology-Grounded Reasoning for Medical Question Answering with Language Models",
author = "Jalan, Pratik and
Joshi, Mukul and
Jadhav, Kshitij Sharad",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1768/",
doi = "10.18653/2026.findings-emnlp.1768",
pages = "37819--37843",
ISBN = "979-8-89176-462-0",
abstract = "Language models achieve strong performance in medical question answering, yet hallucinations persist even in domain-specialized models, particularly on complex clinical vignettes involving rare presentations, multi-hop reasoning, and ambiguous evidence requiring explicit relational grounding. We introduce OntoDiagnose, a training-free, ontology-grounded, clinician-inspired reasoning pipeline that augments parametric knowledge with structured evidence from SNOMED CT. Given a clinical question, OntoDiagnose extracts salient medical entities, grounds them in the ontology, explores a bounded subgraph, and compresses relevant relations into compact, interpretable evidence chains that guide reasoning. We evaluate OntoDiagnose across USMLE-style and biomedical QA benchmarks using MedGemma, BioMistral, MedPhi, and OpenBioLLM under zero-shot, few-shot, and chain-of-thought settings. OntoDiagnose consistently improves over prompt-only baselines, with an average gain of 9.6 accuracy points on MedQA and the largest relative gains for the lowest-scoring models. These results show the benefit of incorporating ontology-grounded evidence into medical question answering without modifying model parameters."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jalan-etal-2026-ontodiagnose">
<titleInfo>
<title>OntoDiagnose: Ontology-Grounded Reasoning for Medical Question Answering with Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pratik</namePart>
<namePart type="family">Jalan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mukul</namePart>
<namePart type="family">Joshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kshitij</namePart>
<namePart type="given">Sharad</namePart>
<namePart type="family">Jadhav</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Language models achieve strong performance in medical question answering, yet hallucinations persist even in domain-specialized models, particularly on complex clinical vignettes involving rare presentations, multi-hop reasoning, and ambiguous evidence requiring explicit relational grounding. We introduce OntoDiagnose, a training-free, ontology-grounded, clinician-inspired reasoning pipeline that augments parametric knowledge with structured evidence from SNOMED CT. Given a clinical question, OntoDiagnose extracts salient medical entities, grounds them in the ontology, explores a bounded subgraph, and compresses relevant relations into compact, interpretable evidence chains that guide reasoning. We evaluate OntoDiagnose across USMLE-style and biomedical QA benchmarks using MedGemma, BioMistral, MedPhi, and OpenBioLLM under zero-shot, few-shot, and chain-of-thought settings. OntoDiagnose consistently improves over prompt-only baselines, with an average gain of 9.6 accuracy points on MedQA and the largest relative gains for the lowest-scoring models. These results show the benefit of incorporating ontology-grounded evidence into medical question answering without modifying model parameters.</abstract>
<identifier type="citekey">jalan-etal-2026-ontodiagnose</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.1768</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1768/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>37819</start>
<end>37843</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OntoDiagnose: Ontology-Grounded Reasoning for Medical Question Answering with Language Models
%A Jalan, Pratik
%A Joshi, Mukul
%A Jadhav, Kshitij Sharad
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F jalan-etal-2026-ontodiagnose
%X Language models achieve strong performance in medical question answering, yet hallucinations persist even in domain-specialized models, particularly on complex clinical vignettes involving rare presentations, multi-hop reasoning, and ambiguous evidence requiring explicit relational grounding. We introduce OntoDiagnose, a training-free, ontology-grounded, clinician-inspired reasoning pipeline that augments parametric knowledge with structured evidence from SNOMED CT. Given a clinical question, OntoDiagnose extracts salient medical entities, grounds them in the ontology, explores a bounded subgraph, and compresses relevant relations into compact, interpretable evidence chains that guide reasoning. We evaluate OntoDiagnose across USMLE-style and biomedical QA benchmarks using MedGemma, BioMistral, MedPhi, and OpenBioLLM under zero-shot, few-shot, and chain-of-thought settings. OntoDiagnose consistently improves over prompt-only baselines, with an average gain of 9.6 accuracy points on MedQA and the largest relative gains for the lowest-scoring models. These results show the benefit of incorporating ontology-grounded evidence into medical question answering without modifying model parameters.
%R 10.18653/2026.findings-emnlp.1768
%U https://aclanthology.org/2026.findings-emnlp.1768/
%U https://doi.org/10.18653/2026.findings-emnlp.1768
%P 37819-37843
Markdown (Informal)
[OntoDiagnose: Ontology-Grounded Reasoning for Medical Question Answering with Language Models](https://aclanthology.org/2026.findings-emnlp.1768/) (Jalan et al., Findings 2026)
ACL