@inproceedings{shah-etal-2026-vaidya,
title = "{VAIDYA}: Validated Agents for Intelligent Diagnosis and Yielded Analysis",
author = "Shah, Kalash and
Bhutani, Gautam and
Sarbhangia, Rohitaswa and
Snehan, J",
editor = "Mille, Simon and
Gehrmann, Sebastian and
Schmidtov{\'a}, Patr{\'i}cia and
Du{\v{s}}ek, Ond{\v{r}}ej and
Fadaee, Marzieh and
Lo, Kyle and
Santus, Enrico and
Stanovsky, Gabriel",
booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.gem-main.3/",
pages = "11--33",
ISBN = "979-8-89176-423-1",
abstract = "Recent advances in large language models (LLMs) have demonstrated impressive medical reasoning capabilities. However, current evaluation methods are mostly limited to static case vignettes and multiple-choice questions which fail to reflect the complexity, uncertainty, and iterative nature of real-world clinical decision-making. To bridge this gap, we propose **DiagBench**, a novel benchmark where models interact dynamically with a LLM based Patient Simulator, querying relevant clinical details to formulate accurate diagnoses. To complement this, we introduce **MedConvBench**, a diagnostic conversation benchmark designed to assess the relevance and quality of model-generated clinical reasoning. To further address the interpretability and alignment challenges of AI-assisted diagnosis, we develop a modular and medically grounded framework called **VAIDYA** that mirrors a physician{'}s stepwise diagnostic reasoning. This structured approach improves transparency and yields substantial performance gains over base LLMs. Our work takes a critical step toward aligning AI systems with real-world clinical practices by combining dynamic interaction, interpretability, and clinical validation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shah-etal-2026-vaidya">
<titleInfo>
<title>VAIDYA: Validated Agents for Intelligent Diagnosis and Yielded Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kalash</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gautam</namePart>
<namePart type="family">Bhutani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rohitaswa</namePart>
<namePart type="family">Sarbhangia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">J</namePart>
<namePart type="family">Snehan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics (GEM)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Mille</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrícia</namePart>
<namePart type="family">Schmidtová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Dušek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marzieh</namePart>
<namePart type="family">Fadaee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyle</namePart>
<namePart type="family">Lo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Stanovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-423-1</identifier>
</relatedItem>
<abstract>Recent advances in large language models (LLMs) have demonstrated impressive medical reasoning capabilities. However, current evaluation methods are mostly limited to static case vignettes and multiple-choice questions which fail to reflect the complexity, uncertainty, and iterative nature of real-world clinical decision-making. To bridge this gap, we propose **DiagBench**, a novel benchmark where models interact dynamically with a LLM based Patient Simulator, querying relevant clinical details to formulate accurate diagnoses. To complement this, we introduce **MedConvBench**, a diagnostic conversation benchmark designed to assess the relevance and quality of model-generated clinical reasoning. To further address the interpretability and alignment challenges of AI-assisted diagnosis, we develop a modular and medically grounded framework called **VAIDYA** that mirrors a physician’s stepwise diagnostic reasoning. This structured approach improves transparency and yields substantial performance gains over base LLMs. Our work takes a critical step toward aligning AI systems with real-world clinical practices by combining dynamic interaction, interpretability, and clinical validation.</abstract>
<identifier type="citekey">shah-etal-2026-vaidya</identifier>
<location>
<url>https://aclanthology.org/2026.gem-main.3/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>11</start>
<end>33</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VAIDYA: Validated Agents for Intelligent Diagnosis and Yielded Analysis
%A Shah, Kalash
%A Bhutani, Gautam
%A Sarbhangia, Rohitaswa
%A Snehan, J.
%Y Mille, Simon
%Y Gehrmann, Sebastian
%Y Schmidtová, Patrícia
%Y Dušek, Ondřej
%Y Fadaee, Marzieh
%Y Lo, Kyle
%Y Santus, Enrico
%Y Stanovsky, Gabriel
%S Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics (GEM)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-423-1
%F shah-etal-2026-vaidya
%X Recent advances in large language models (LLMs) have demonstrated impressive medical reasoning capabilities. However, current evaluation methods are mostly limited to static case vignettes and multiple-choice questions which fail to reflect the complexity, uncertainty, and iterative nature of real-world clinical decision-making. To bridge this gap, we propose **DiagBench**, a novel benchmark where models interact dynamically with a LLM based Patient Simulator, querying relevant clinical details to formulate accurate diagnoses. To complement this, we introduce **MedConvBench**, a diagnostic conversation benchmark designed to assess the relevance and quality of model-generated clinical reasoning. To further address the interpretability and alignment challenges of AI-assisted diagnosis, we develop a modular and medically grounded framework called **VAIDYA** that mirrors a physician’s stepwise diagnostic reasoning. This structured approach improves transparency and yields substantial performance gains over base LLMs. Our work takes a critical step toward aligning AI systems with real-world clinical practices by combining dynamic interaction, interpretability, and clinical validation.
%U https://aclanthology.org/2026.gem-main.3/
%P 11-33
Markdown (Informal)
[VAIDYA: Validated Agents for Intelligent Diagnosis and Yielded Analysis](https://aclanthology.org/2026.gem-main.3/) (Shah et al., GEM 2026)
ACL