@inproceedings{urooj-etal-2026-candice,
title = "{CANDICE}: Agentic Causal Disentanglement with Class Conditional Knowledge Integration for Long Tailed Domain Generalization",
author = "Urooj, Midhat and
Banerjee, Ayan and
Gupta, Sandeep",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.2018/",
doi = "10.18653/v1/2026.findings-acl.2018",
pages = "40596--40624",
ISBN = "979-8-89176-395-1",
abstract = "Deep learning models deployed in clinical settings face two major challenges: \textit{domain generalization} (DG) and \textit{long-tailed} (LT) recognition. DG requires learning domain-invariant features to ensure robustness across heterogeneous acquisition protocols and patient populations. However, we identify a fundamental trade-off: objectives that enforce domain invariance often suppress class-discriminative signals essential for long-tailed recognition.To address this, we propose the \textit{Agentic Causal Disentanglement (CANDICE) Framework}, a modular architecture that integrates explicit clinical expertise from sonographers, radiologists, and specialists as a form of causal intervention. The framework combines clinical reasoning, causal representation learning, and automated pipeline construction to disentangle domain-invariant and class-discriminative features. By incorporating domain-specific causal knowledge, it effectively decouples the objectives of DG and LT learning. We evaluate CANDICE on 10 diverse medical imaging datasets spanning four modalities. The framework achieves an average performance improvement of 10.3{\%} across both multi-domain and in-domain long-tailed tasks, demonstrating its effectiveness in handling distribution shifts while preserving minority class performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="urooj-etal-2026-candice">
<titleInfo>
<title>CANDICE: Agentic Causal Disentanglement with Class Conditional Knowledge Integration for Long Tailed Domain Generalization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Midhat</namePart>
<namePart type="family">Urooj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayan</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandeep</namePart>
<namePart type="family">Gupta</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>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</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, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Deep learning models deployed in clinical settings face two major challenges: domain generalization (DG) and long-tailed (LT) recognition. DG requires learning domain-invariant features to ensure robustness across heterogeneous acquisition protocols and patient populations. However, we identify a fundamental trade-off: objectives that enforce domain invariance often suppress class-discriminative signals essential for long-tailed recognition.To address this, we propose the Agentic Causal Disentanglement (CANDICE) Framework, a modular architecture that integrates explicit clinical expertise from sonographers, radiologists, and specialists as a form of causal intervention. The framework combines clinical reasoning, causal representation learning, and automated pipeline construction to disentangle domain-invariant and class-discriminative features. By incorporating domain-specific causal knowledge, it effectively decouples the objectives of DG and LT learning. We evaluate CANDICE on 10 diverse medical imaging datasets spanning four modalities. The framework achieves an average performance improvement of 10.3% across both multi-domain and in-domain long-tailed tasks, demonstrating its effectiveness in handling distribution shifts while preserving minority class performance.</abstract>
<identifier type="citekey">urooj-etal-2026-candice</identifier>
<identifier type="doi">10.18653/v1/2026.findings-acl.2018</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.2018/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>40596</start>
<end>40624</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CANDICE: Agentic Causal Disentanglement with Class Conditional Knowledge Integration for Long Tailed Domain Generalization
%A Urooj, Midhat
%A Banerjee, Ayan
%A Gupta, Sandeep
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F urooj-etal-2026-candice
%X Deep learning models deployed in clinical settings face two major challenges: domain generalization (DG) and long-tailed (LT) recognition. DG requires learning domain-invariant features to ensure robustness across heterogeneous acquisition protocols and patient populations. However, we identify a fundamental trade-off: objectives that enforce domain invariance often suppress class-discriminative signals essential for long-tailed recognition.To address this, we propose the Agentic Causal Disentanglement (CANDICE) Framework, a modular architecture that integrates explicit clinical expertise from sonographers, radiologists, and specialists as a form of causal intervention. The framework combines clinical reasoning, causal representation learning, and automated pipeline construction to disentangle domain-invariant and class-discriminative features. By incorporating domain-specific causal knowledge, it effectively decouples the objectives of DG and LT learning. We evaluate CANDICE on 10 diverse medical imaging datasets spanning four modalities. The framework achieves an average performance improvement of 10.3% across both multi-domain and in-domain long-tailed tasks, demonstrating its effectiveness in handling distribution shifts while preserving minority class performance.
%R 10.18653/v1/2026.findings-acl.2018
%U https://aclanthology.org/2026.findings-acl.2018/
%U https://doi.org/10.18653/v1/2026.findings-acl.2018
%P 40596-40624
Markdown (Informal)
[CANDICE: Agentic Causal Disentanglement with Class Conditional Knowledge Integration for Long Tailed Domain Generalization](https://aclanthology.org/2026.findings-acl.2018/) (Urooj et al., Findings 2026)
ACL