@inproceedings{xu-etal-2026-hemp,
title = "{HEMP}: Hierarchical Entity-aligned Memory Prompting for {CT} Report Generation",
author = "Xu, Tong and
Qian, Yiming and
Shan, Zhe and
Xie, Xia",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1545/",
pages = "35250--35260",
ISBN = "979-8-89176-459-0",
abstract = "Automated CT report generation remains challenging because it requires both fine-grained grounding of pathological entities in multi-view volumetric evidence and clinically coherent language that reflects diagnostic priors from historical cases. Existing methods often rely on noisy cross-modal alignment or underutilize retrieved report knowledge during decoding. We propose HEMP, which is a Hierarchical Entity-aligned Memory Prompting framework for LLM-based CT report generation. HEMP first performs two-stage entity-visual alignment where graph-constrained entity-conditioned attention retrieves initial evidence and an optimal transport refinement enforces principled coupling between entity nodes and visual tokens under marginal constraints. To inject case-conditioned linguistic priors, we design a Conditional Dual-Hopfield Memory module that retrieves case-conditioned report priors and integrates them through both implicit feature-level fusion into entity representations and explicit memory tokens appended to the prompt. Finally, we enforce clinical consistency via hierarchical severity supervision at the entity, region, and sign-group levels. Comprehensive Experiments demonstrate that our method outperforms previous methods and achieves SoTA performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2026-hemp">
<titleInfo>
<title>HEMP: Hierarchical Entity-aligned Memory Prompting for CT Report Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiming</namePart>
<namePart type="family">Qian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhe</namePart>
<namePart type="family">Shan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xia</namePart>
<namePart type="family">Xie</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</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Automated CT report generation remains challenging because it requires both fine-grained grounding of pathological entities in multi-view volumetric evidence and clinically coherent language that reflects diagnostic priors from historical cases. Existing methods often rely on noisy cross-modal alignment or underutilize retrieved report knowledge during decoding. We propose HEMP, which is a Hierarchical Entity-aligned Memory Prompting framework for LLM-based CT report generation. HEMP first performs two-stage entity-visual alignment where graph-constrained entity-conditioned attention retrieves initial evidence and an optimal transport refinement enforces principled coupling between entity nodes and visual tokens under marginal constraints. To inject case-conditioned linguistic priors, we design a Conditional Dual-Hopfield Memory module that retrieves case-conditioned report priors and integrates them through both implicit feature-level fusion into entity representations and explicit memory tokens appended to the prompt. Finally, we enforce clinical consistency via hierarchical severity supervision at the entity, region, and sign-group levels. Comprehensive Experiments demonstrate that our method outperforms previous methods and achieves SoTA performance.</abstract>
<identifier type="citekey">xu-etal-2026-hemp</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1545/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>35250</start>
<end>35260</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HEMP: Hierarchical Entity-aligned Memory Prompting for CT Report Generation
%A Xu, Tong
%A Qian, Yiming
%A Shan, Zhe
%A Xie, Xia
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F xu-etal-2026-hemp
%X Automated CT report generation remains challenging because it requires both fine-grained grounding of pathological entities in multi-view volumetric evidence and clinically coherent language that reflects diagnostic priors from historical cases. Existing methods often rely on noisy cross-modal alignment or underutilize retrieved report knowledge during decoding. We propose HEMP, which is a Hierarchical Entity-aligned Memory Prompting framework for LLM-based CT report generation. HEMP first performs two-stage entity-visual alignment where graph-constrained entity-conditioned attention retrieves initial evidence and an optimal transport refinement enforces principled coupling between entity nodes and visual tokens under marginal constraints. To inject case-conditioned linguistic priors, we design a Conditional Dual-Hopfield Memory module that retrieves case-conditioned report priors and integrates them through both implicit feature-level fusion into entity representations and explicit memory tokens appended to the prompt. Finally, we enforce clinical consistency via hierarchical severity supervision at the entity, region, and sign-group levels. Comprehensive Experiments demonstrate that our method outperforms previous methods and achieves SoTA performance.
%U https://aclanthology.org/2026.emnlp-main.1545/
%P 35250-35260
Markdown (Informal)
[HEMP: Hierarchical Entity-aligned Memory Prompting for CT Report Generation](https://aclanthology.org/2026.emnlp-main.1545/) (Xu et al., EMNLP 2026)
ACL