@inproceedings{guo-etal-2026-seekg,
title = "{S}ee{KG}: Multi-modal {LLM}s Understand Knowledge Graphs as Images",
author = "Guo, Lingbing and
Zhang, Yichi and
Liu, Yang and
Chen, Zhuo and
Sun, Zequn",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.93/",
pages = "1916--1932",
ISBN = "979-8-89176-462-0",
abstract = "The representation learning of knowledge graphs (KGs) is a longstanding research problem. While graph neural networks (GNNs) have driven recent progress, they still struggle with encoding textual features and subtle relationships of KGs, particularly in conveying key information to large language models (LLMs). The emergence of multi-modal LLMs (MLLMs), which combine linguistic and visual understanding, presents an intriguing opportunity: Could their vision capabilities inspire mental visualization, facilitating conceptual thinking and semantic reasoning akin to human cognition? To investigate this premise, we propose SeeKG, an innovative framework that transforms KGs into visually rendered representations as image inputs for MLLMs. We evaluate SeeKG under both training-free and supervised fine-tuning settings, where the experimental results show that SeeKG excels in understanding KG sub-graphs and achieves competitive performance even without training or demonstrations. Further fine-tuning on small-batch data reveals that it outperforms state-of-the-art LLM-based methods by substantial margins across multiple KG completion datasets."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2026-seekg">
<titleInfo>
<title>SeeKG: Multi-modal LLMs Understand Knowledge Graphs as Images</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lingbing</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuo</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zequn</namePart>
<namePart type="family">Sun</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>The representation learning of knowledge graphs (KGs) is a longstanding research problem. While graph neural networks (GNNs) have driven recent progress, they still struggle with encoding textual features and subtle relationships of KGs, particularly in conveying key information to large language models (LLMs). The emergence of multi-modal LLMs (MLLMs), which combine linguistic and visual understanding, presents an intriguing opportunity: Could their vision capabilities inspire mental visualization, facilitating conceptual thinking and semantic reasoning akin to human cognition? To investigate this premise, we propose SeeKG, an innovative framework that transforms KGs into visually rendered representations as image inputs for MLLMs. We evaluate SeeKG under both training-free and supervised fine-tuning settings, where the experimental results show that SeeKG excels in understanding KG sub-graphs and achieves competitive performance even without training or demonstrations. Further fine-tuning on small-batch data reveals that it outperforms state-of-the-art LLM-based methods by substantial margins across multiple KG completion datasets.</abstract>
<identifier type="citekey">guo-etal-2026-seekg</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.93/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1916</start>
<end>1932</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SeeKG: Multi-modal LLMs Understand Knowledge Graphs as Images
%A Guo, Lingbing
%A Zhang, Yichi
%A Liu, Yang
%A Chen, Zhuo
%A Sun, Zequn
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F guo-etal-2026-seekg
%X The representation learning of knowledge graphs (KGs) is a longstanding research problem. While graph neural networks (GNNs) have driven recent progress, they still struggle with encoding textual features and subtle relationships of KGs, particularly in conveying key information to large language models (LLMs). The emergence of multi-modal LLMs (MLLMs), which combine linguistic and visual understanding, presents an intriguing opportunity: Could their vision capabilities inspire mental visualization, facilitating conceptual thinking and semantic reasoning akin to human cognition? To investigate this premise, we propose SeeKG, an innovative framework that transforms KGs into visually rendered representations as image inputs for MLLMs. We evaluate SeeKG under both training-free and supervised fine-tuning settings, where the experimental results show that SeeKG excels in understanding KG sub-graphs and achieves competitive performance even without training or demonstrations. Further fine-tuning on small-batch data reveals that it outperforms state-of-the-art LLM-based methods by substantial margins across multiple KG completion datasets.
%U https://aclanthology.org/2026.findings-emnlp.93/
%P 1916-1932
Markdown (Informal)
[SeeKG: Multi-modal LLMs Understand Knowledge Graphs as Images](https://aclanthology.org/2026.findings-emnlp.93/) (Guo et al., Findings 2026)
ACL