@inproceedings{parovic-etal-2025-generating,
title = "Generating Domain-Specific Knowledge Graphs from Large Language Models",
author = "Parovi{\'c}, Marinela and
Li, Ze and
Du, Jinhua",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.602/",
doi = "10.18653/v1/2025.findings-acl.602",
pages = "11558--11574",
ISBN = "979-8-89176-256-5",
abstract = "Knowledge graphs (KGs) have been a cornerstone of search and recommendation due to their ability to store factual knowledge about any domain in a structured form enabling easy search and retrieval. Large language models (LLMs) have shown impressive world knowledge across different benchmarks and domains but their knowledge is inconveniently scattered across their billions of parameters. In this paper, we propose a prompt-based method to construct domain-specific KGs by extracting knowledge solely from LLMs' parameters. First, we use an LLM to create a schema for a specific domain, which contains a set of domain-representative entities and relations. After that, we use the schema to guide the LLM through an iterative data generation process equipped with Chain-of-Verification (CoVe) for increased data quality. Using this method, we construct KGs for two domains: books and landmarks, which we then evaluate against Wikidata, an open-source human-created KG. Our results show that LLMs can generate large domain-specific KGs containing tens of thousands of entities and relations. However, due to the increased hallucination rates as the procedure evolves, the utility of large-scale LLM-generated KGs in practical applications could remain limited."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="parovic-etal-2025-generating">
<titleInfo>
<title>Generating Domain-Specific Knowledge Graphs from Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marinela</namePart>
<namePart type="family">Parović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ze</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinhua</namePart>
<namePart type="family">Du</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>Findings of the Association for Computational Linguistics: ACL 2025</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">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Knowledge graphs (KGs) have been a cornerstone of search and recommendation due to their ability to store factual knowledge about any domain in a structured form enabling easy search and retrieval. Large language models (LLMs) have shown impressive world knowledge across different benchmarks and domains but their knowledge is inconveniently scattered across their billions of parameters. In this paper, we propose a prompt-based method to construct domain-specific KGs by extracting knowledge solely from LLMs’ parameters. First, we use an LLM to create a schema for a specific domain, which contains a set of domain-representative entities and relations. After that, we use the schema to guide the LLM through an iterative data generation process equipped with Chain-of-Verification (CoVe) for increased data quality. Using this method, we construct KGs for two domains: books and landmarks, which we then evaluate against Wikidata, an open-source human-created KG. Our results show that LLMs can generate large domain-specific KGs containing tens of thousands of entities and relations. However, due to the increased hallucination rates as the procedure evolves, the utility of large-scale LLM-generated KGs in practical applications could remain limited.</abstract>
<identifier type="citekey">parovic-etal-2025-generating</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.602</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.602/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>11558</start>
<end>11574</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating Domain-Specific Knowledge Graphs from Large Language Models
%A Parović, Marinela
%A Li, Ze
%A Du, Jinhua
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F parovic-etal-2025-generating
%X Knowledge graphs (KGs) have been a cornerstone of search and recommendation due to their ability to store factual knowledge about any domain in a structured form enabling easy search and retrieval. Large language models (LLMs) have shown impressive world knowledge across different benchmarks and domains but their knowledge is inconveniently scattered across their billions of parameters. In this paper, we propose a prompt-based method to construct domain-specific KGs by extracting knowledge solely from LLMs’ parameters. First, we use an LLM to create a schema for a specific domain, which contains a set of domain-representative entities and relations. After that, we use the schema to guide the LLM through an iterative data generation process equipped with Chain-of-Verification (CoVe) for increased data quality. Using this method, we construct KGs for two domains: books and landmarks, which we then evaluate against Wikidata, an open-source human-created KG. Our results show that LLMs can generate large domain-specific KGs containing tens of thousands of entities and relations. However, due to the increased hallucination rates as the procedure evolves, the utility of large-scale LLM-generated KGs in practical applications could remain limited.
%R 10.18653/v1/2025.findings-acl.602
%U https://aclanthology.org/2025.findings-acl.602/
%U https://doi.org/10.18653/v1/2025.findings-acl.602
%P 11558-11574
Markdown (Informal)
[Generating Domain-Specific Knowledge Graphs from Large Language Models](https://aclanthology.org/2025.findings-acl.602/) (Parović et al., Findings 2025)
ACL