@inproceedings{yun-etal-2025-lilac,
title = "{LIL}a{C}: Late Interacting in Layered Component Graph for Open-domain Multimodal Multihop Retrieval",
author = "Yun, Joohyung and
Lee, Doyup and
Han, Wook-Shin",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1037/",
pages = "20551--20570",
ISBN = "979-8-89176-332-6",
abstract = "Multimodal document retrieval aims to retrieve query-relevant components from documents composed of textual, tabular, and visual elements. An effective multimodal retriever needs to handle two main challenges: (1) mitigate the effect of irrelevant contents caused by fixed, single-granular retrieval units, and (2) support multihop reasoning by effectively capturing semantic relationships among components within and across documents. To address these challenges, we propose LILaC, a multimodal retrieval framework featuring two core innovations. First, we introduce a layered component graph, explicitly representing multimodal information at two layers{---}each representing coarse and fine granularity{---}facilitating efficient yet precise reasoning. Second, we develop a late-interaction-based subgraph retrieval method, an edge-based approach that initially identifies coarse-grained nodes for efficient candidate generation, then performs fine-grained reasoning via late interaction. Extensive experiments demonstrate that LILaC achieves state-of-the-art retrieval performance on all five benchmarks, notably without additional fine-tuning. We make the artifacts publicly available at github.com/joohyung00/lilac."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yun-etal-2025-lilac">
<titleInfo>
<title>LILaC: Late Interacting in Layered Component Graph for Open-domain Multimodal Multihop Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joohyung</namePart>
<namePart type="family">Yun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Doyup</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wook-Shin</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Multimodal document retrieval aims to retrieve query-relevant components from documents composed of textual, tabular, and visual elements. An effective multimodal retriever needs to handle two main challenges: (1) mitigate the effect of irrelevant contents caused by fixed, single-granular retrieval units, and (2) support multihop reasoning by effectively capturing semantic relationships among components within and across documents. To address these challenges, we propose LILaC, a multimodal retrieval framework featuring two core innovations. First, we introduce a layered component graph, explicitly representing multimodal information at two layers—each representing coarse and fine granularity—facilitating efficient yet precise reasoning. Second, we develop a late-interaction-based subgraph retrieval method, an edge-based approach that initially identifies coarse-grained nodes for efficient candidate generation, then performs fine-grained reasoning via late interaction. Extensive experiments demonstrate that LILaC achieves state-of-the-art retrieval performance on all five benchmarks, notably without additional fine-tuning. We make the artifacts publicly available at github.com/joohyung00/lilac.</abstract>
<identifier type="citekey">yun-etal-2025-lilac</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.1037/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>20551</start>
<end>20570</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LILaC: Late Interacting in Layered Component Graph for Open-domain Multimodal Multihop Retrieval
%A Yun, Joohyung
%A Lee, Doyup
%A Han, Wook-Shin
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F yun-etal-2025-lilac
%X Multimodal document retrieval aims to retrieve query-relevant components from documents composed of textual, tabular, and visual elements. An effective multimodal retriever needs to handle two main challenges: (1) mitigate the effect of irrelevant contents caused by fixed, single-granular retrieval units, and (2) support multihop reasoning by effectively capturing semantic relationships among components within and across documents. To address these challenges, we propose LILaC, a multimodal retrieval framework featuring two core innovations. First, we introduce a layered component graph, explicitly representing multimodal information at two layers—each representing coarse and fine granularity—facilitating efficient yet precise reasoning. Second, we develop a late-interaction-based subgraph retrieval method, an edge-based approach that initially identifies coarse-grained nodes for efficient candidate generation, then performs fine-grained reasoning via late interaction. Extensive experiments demonstrate that LILaC achieves state-of-the-art retrieval performance on all five benchmarks, notably without additional fine-tuning. We make the artifacts publicly available at github.com/joohyung00/lilac.
%U https://aclanthology.org/2025.emnlp-main.1037/
%P 20551-20570
Markdown (Informal)
[LILaC: Late Interacting in Layered Component Graph for Open-domain Multimodal Multihop Retrieval](https://aclanthology.org/2025.emnlp-main.1037/) (Yun et al., EMNLP 2025)
ACL