@inproceedings{burgin-etal-2025-quark,
title = "{Q}u{ARK}: {LLM}-Based Domain-Specific Question Answering Using Retrieval Augmented Generation and Knowledge Graphs",
author = "Burgin, Edward and
Dutta, Sourav and
Wang, Mingxue",
editor = "Angelova, Galia and
Kunilovskaya, Maria and
Escribe, Marie and
Mitkov, Ruslan",
booktitle = "Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.ranlp-1.25/",
pages = "210--217",
abstract = "Retrieval Augmented Generation (RAG) has been pivotal in the utilization of Large Language Models (LLM) to improve the factuality of long-form question answering systems in industrial settings. Knowledge graphs (KG) represent a linking of disparate information sources that potentially yield useful information for mitigating the issues of insufficient knowledge and hallucination within the LLM-RAG pipeline. However, the creation of domain-specific KG is costly and usually requires a domain expert. To alleviate the above challenges, this work proposes QuARK, a novel domain-specific question answering framework to enhance the knowledge capabilities of LLM by integrating structured KG, thereby significantly reducing the reliance on the ``generic'' latent knowledge of LLMs. Here, we showcase how LLMs can be deployed to not only act in dynamic information retrieval and in answer generating frameworks, but also as flexible agents to automatically extract relevant entities and relations for the automated construction of domain-specific KGs. Crucially we propose how the pairing of question decomposition and semantic triplet retrieval within RAG can enable optimal subgraph retrieval. Experimental evaluations of our framework on financial domain public dataset, demonstrate that it enables a robust pipeline incorporating schema-free KG within a RAG framework to improve the overall accuracy by nearly 13{\%}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="burgin-etal-2025-quark">
<titleInfo>
<title>QuARK: LLM-Based Domain-Specific Question Answering Using Retrieval Augmented Generation and Knowledge Graphs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Edward</namePart>
<namePart type="family">Burgin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sourav</namePart>
<namePart type="family">Dutta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingxue</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
</titleInfo>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Kunilovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Escribe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Retrieval Augmented Generation (RAG) has been pivotal in the utilization of Large Language Models (LLM) to improve the factuality of long-form question answering systems in industrial settings. Knowledge graphs (KG) represent a linking of disparate information sources that potentially yield useful information for mitigating the issues of insufficient knowledge and hallucination within the LLM-RAG pipeline. However, the creation of domain-specific KG is costly and usually requires a domain expert. To alleviate the above challenges, this work proposes QuARK, a novel domain-specific question answering framework to enhance the knowledge capabilities of LLM by integrating structured KG, thereby significantly reducing the reliance on the “generic” latent knowledge of LLMs. Here, we showcase how LLMs can be deployed to not only act in dynamic information retrieval and in answer generating frameworks, but also as flexible agents to automatically extract relevant entities and relations for the automated construction of domain-specific KGs. Crucially we propose how the pairing of question decomposition and semantic triplet retrieval within RAG can enable optimal subgraph retrieval. Experimental evaluations of our framework on financial domain public dataset, demonstrate that it enables a robust pipeline incorporating schema-free KG within a RAG framework to improve the overall accuracy by nearly 13%.</abstract>
<identifier type="citekey">burgin-etal-2025-quark</identifier>
<location>
<url>https://aclanthology.org/2025.ranlp-1.25/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>210</start>
<end>217</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T QuARK: LLM-Based Domain-Specific Question Answering Using Retrieval Augmented Generation and Knowledge Graphs
%A Burgin, Edward
%A Dutta, Sourav
%A Wang, Mingxue
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F burgin-etal-2025-quark
%X Retrieval Augmented Generation (RAG) has been pivotal in the utilization of Large Language Models (LLM) to improve the factuality of long-form question answering systems in industrial settings. Knowledge graphs (KG) represent a linking of disparate information sources that potentially yield useful information for mitigating the issues of insufficient knowledge and hallucination within the LLM-RAG pipeline. However, the creation of domain-specific KG is costly and usually requires a domain expert. To alleviate the above challenges, this work proposes QuARK, a novel domain-specific question answering framework to enhance the knowledge capabilities of LLM by integrating structured KG, thereby significantly reducing the reliance on the “generic” latent knowledge of LLMs. Here, we showcase how LLMs can be deployed to not only act in dynamic information retrieval and in answer generating frameworks, but also as flexible agents to automatically extract relevant entities and relations for the automated construction of domain-specific KGs. Crucially we propose how the pairing of question decomposition and semantic triplet retrieval within RAG can enable optimal subgraph retrieval. Experimental evaluations of our framework on financial domain public dataset, demonstrate that it enables a robust pipeline incorporating schema-free KG within a RAG framework to improve the overall accuracy by nearly 13%.
%U https://aclanthology.org/2025.ranlp-1.25/
%P 210-217
Markdown (Informal)
[QuARK: LLM-Based Domain-Specific Question Answering Using Retrieval Augmented Generation and Knowledge Graphs](https://aclanthology.org/2025.ranlp-1.25/) (Burgin et al., RANLP 2025)
ACL