@inproceedings{lin-etal-2025-self-supervised,
title = "Self-supervised Quantized Representation for Seamlessly Integrating Knowledge Graphs with Large Language Models",
author = "Lin, Qika and
Zhao, Tianzhe and
He, Kai and
Peng, Zhen and
Xu, Fangzhi and
Huang, Ling and
Ma, Jingying and
Feng, Mengling",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.667/",
doi = "10.18653/v1/2025.acl-long.667",
pages = "13587--13602",
ISBN = "979-8-89176-251-0",
abstract = "Due to the presence of the natural gap between Knowledge Graph (KG) structures and the natural language, the effective integration of holistic structural information of KGs with Large Language Models (LLMs) has emerged as a significant question. To this end, we propose a two-stage framework to learn and apply quantized codes for each entity, aiming for the seamless integration of KGs with LLMs. Firstly, a self-supervised quantized representation (SSQR) method is proposed to compress both KG structural and semantic knowledge into discrete codes (i.e., tokens) that align the format of language sentences. We further design KG instruction-following data by viewing these learned codes as features to directly input to LLMs, thereby achieving seamless integration. The experiment results demonstrate that SSQR outperforms existing unsupervised quantized methods, producing more distinguishable codes. Moreover, the fine-tuned LLaMA2 and LLaMA3.1 also have superior performance on KG link prediction and triple classification tasks, utilizing only 16 tokens per entity instead of thousands in conventional prompting methods."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2025-self-supervised">
<titleInfo>
<title>Self-supervised Quantized Representation for Seamlessly Integrating Knowledge Graphs with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qika</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianzhe</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fangzhi</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ling</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingying</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengling</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Due to the presence of the natural gap between Knowledge Graph (KG) structures and the natural language, the effective integration of holistic structural information of KGs with Large Language Models (LLMs) has emerged as a significant question. To this end, we propose a two-stage framework to learn and apply quantized codes for each entity, aiming for the seamless integration of KGs with LLMs. Firstly, a self-supervised quantized representation (SSQR) method is proposed to compress both KG structural and semantic knowledge into discrete codes (i.e., tokens) that align the format of language sentences. We further design KG instruction-following data by viewing these learned codes as features to directly input to LLMs, thereby achieving seamless integration. The experiment results demonstrate that SSQR outperforms existing unsupervised quantized methods, producing more distinguishable codes. Moreover, the fine-tuned LLaMA2 and LLaMA3.1 also have superior performance on KG link prediction and triple classification tasks, utilizing only 16 tokens per entity instead of thousands in conventional prompting methods.</abstract>
<identifier type="citekey">lin-etal-2025-self-supervised</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.667</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.667/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>13587</start>
<end>13602</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Self-supervised Quantized Representation for Seamlessly Integrating Knowledge Graphs with Large Language Models
%A Lin, Qika
%A Zhao, Tianzhe
%A He, Kai
%A Peng, Zhen
%A Xu, Fangzhi
%A Huang, Ling
%A Ma, Jingying
%A Feng, Mengling
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F lin-etal-2025-self-supervised
%X Due to the presence of the natural gap between Knowledge Graph (KG) structures and the natural language, the effective integration of holistic structural information of KGs with Large Language Models (LLMs) has emerged as a significant question. To this end, we propose a two-stage framework to learn and apply quantized codes for each entity, aiming for the seamless integration of KGs with LLMs. Firstly, a self-supervised quantized representation (SSQR) method is proposed to compress both KG structural and semantic knowledge into discrete codes (i.e., tokens) that align the format of language sentences. We further design KG instruction-following data by viewing these learned codes as features to directly input to LLMs, thereby achieving seamless integration. The experiment results demonstrate that SSQR outperforms existing unsupervised quantized methods, producing more distinguishable codes. Moreover, the fine-tuned LLaMA2 and LLaMA3.1 also have superior performance on KG link prediction and triple classification tasks, utilizing only 16 tokens per entity instead of thousands in conventional prompting methods.
%R 10.18653/v1/2025.acl-long.667
%U https://aclanthology.org/2025.acl-long.667/
%U https://doi.org/10.18653/v1/2025.acl-long.667
%P 13587-13602
Markdown (Informal)
[Self-supervised Quantized Representation for Seamlessly Integrating Knowledge Graphs with Large Language Models](https://aclanthology.org/2025.acl-long.667/) (Lin et al., ACL 2025)
ACL
- Qika Lin, Tianzhe Zhao, Kai He, Zhen Peng, Fangzhi Xu, Ling Huang, Jingying Ma, and Mengling Feng. 2025. Self-supervised Quantized Representation for Seamlessly Integrating Knowledge Graphs with Large Language Models. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13587–13602, Vienna, Austria. Association for Computational Linguistics.