@inproceedings{sheu-etal-2026-evidag,
title = "{E}vi{DAG}: Auditable Causal {DAG} Authoring with Biomedical Literature",
author = "Sheu, Yi-han and
Steigman, Michael R. and
Zhou, Yu and
Wang, Bo and
Yen, Fan-Yu and
Smoller, Jordan W.",
editor = "Agrawal, Sweta and
Abad, Alberto",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-demos.49/",
pages = "506--515",
ISBN = "979-8-89176-461-3",
abstract = "Constructing causal directed acyclic graphs (DAGs) is a core step in biomedical causal analysis, yet it remains a largely manual process. Analysts must connect study variables to prior literature, evaluate uncertain causal claims, and preserve sufficient provenance for expert review. We present EviDAG, a browser-based system for authoring causal DAGs as auditable, evidence-linked artifacts from biomedical literature. Given free-text descriptions of study concepts, EviDAG creates a reproducible literature snapshot, uses an LLM-based reasoning module to generate structured pairwise causal judgments, links literature-supported judgments to verbatim evidence excerpts, and assembles the judgments into a constraint-checked graph. Each proposed edge includes confidence estimates, provenance, and a reviewable rationale. The interface supports study specification, progress monitoring, evidence review, graph comparison, adjustment-set computation, and export. In evaluations against both compact benchmark DAGs and reference DAGs derived from published literature, EviDAG achieves high edge recall on the literature-based cohort while retaining verifiable evidence trails absent from LLM-only baselines. EviDAG thus offloads the mechanical burden of causal DAG curation while making the resulting assumptions auditable, supporting the design, analysis, and interpretation of biomedical studies."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sheu-etal-2026-evidag">
<titleInfo>
<title>EviDAG: Auditable Causal DAG Authoring with Biomedical Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yi-han</namePart>
<namePart type="family">Sheu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Steigman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fan-Yu</namePart>
<namePart type="family">Yen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="given">W</namePart>
<namePart type="family">Smoller</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: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sweta</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Abad</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">979-8-89176-461-3</identifier>
</relatedItem>
<abstract>Constructing causal directed acyclic graphs (DAGs) is a core step in biomedical causal analysis, yet it remains a largely manual process. Analysts must connect study variables to prior literature, evaluate uncertain causal claims, and preserve sufficient provenance for expert review. We present EviDAG, a browser-based system for authoring causal DAGs as auditable, evidence-linked artifacts from biomedical literature. Given free-text descriptions of study concepts, EviDAG creates a reproducible literature snapshot, uses an LLM-based reasoning module to generate structured pairwise causal judgments, links literature-supported judgments to verbatim evidence excerpts, and assembles the judgments into a constraint-checked graph. Each proposed edge includes confidence estimates, provenance, and a reviewable rationale. The interface supports study specification, progress monitoring, evidence review, graph comparison, adjustment-set computation, and export. In evaluations against both compact benchmark DAGs and reference DAGs derived from published literature, EviDAG achieves high edge recall on the literature-based cohort while retaining verifiable evidence trails absent from LLM-only baselines. EviDAG thus offloads the mechanical burden of causal DAG curation while making the resulting assumptions auditable, supporting the design, analysis, and interpretation of biomedical studies.</abstract>
<identifier type="citekey">sheu-etal-2026-evidag</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-demos.49/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>506</start>
<end>515</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EviDAG: Auditable Causal DAG Authoring with Biomedical Literature
%A Sheu, Yi-han
%A Steigman, Michael R.
%A Zhou, Yu
%A Wang, Bo
%A Yen, Fan-Yu
%A Smoller, Jordan W.
%Y Agrawal, Sweta
%Y Abad, Alberto
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-461-3
%F sheu-etal-2026-evidag
%X Constructing causal directed acyclic graphs (DAGs) is a core step in biomedical causal analysis, yet it remains a largely manual process. Analysts must connect study variables to prior literature, evaluate uncertain causal claims, and preserve sufficient provenance for expert review. We present EviDAG, a browser-based system for authoring causal DAGs as auditable, evidence-linked artifacts from biomedical literature. Given free-text descriptions of study concepts, EviDAG creates a reproducible literature snapshot, uses an LLM-based reasoning module to generate structured pairwise causal judgments, links literature-supported judgments to verbatim evidence excerpts, and assembles the judgments into a constraint-checked graph. Each proposed edge includes confidence estimates, provenance, and a reviewable rationale. The interface supports study specification, progress monitoring, evidence review, graph comparison, adjustment-set computation, and export. In evaluations against both compact benchmark DAGs and reference DAGs derived from published literature, EviDAG achieves high edge recall on the literature-based cohort while retaining verifiable evidence trails absent from LLM-only baselines. EviDAG thus offloads the mechanical burden of causal DAG curation while making the resulting assumptions auditable, supporting the design, analysis, and interpretation of biomedical studies.
%U https://aclanthology.org/2026.emnlp-demos.49/
%P 506-515
Markdown (Informal)
[EviDAG: Auditable Causal DAG Authoring with Biomedical Literature](https://aclanthology.org/2026.emnlp-demos.49/) (Sheu et al., EMNLP 2026)
ACL
- Yi-han Sheu, Michael R. Steigman, Yu Zhou, Bo Wang, Fan-Yu Yen, and Jordan W. Smoller. 2026. EviDAG: Auditable Causal DAG Authoring with Biomedical Literature. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 506–515, Budapest, Hungary. Association for Computational Linguistics.