@inproceedings{ghizzota-etal-2026-integrating,
title = "Integrating Knowledge Graph and Large Language Models for Defining Business Strategies",
author = "Ghizzota, Eleonora and
Jordan, Alex and
Petruzzelli, Alessandro and
Siciliani, Lucia and
Spillo, Giuseppe and
Basile, Pierpaolo and
Sola, Davide and
Scarso Borioli, Giovanni and
Semeraro, Giovanni",
editor = "S{\'e}rasset, Gilles and
Gkirtzou, Katerina and
Cochez, Michael and
Kalo, Jan-Christoph",
booktitle = "Proceedings of the Knowledge Graphs and Large Language Models Workshop ({KG}-{LLM}) @ {LREC}26",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.kallm-1.6/",
doi = "10.63317/4e642nbxhuqr",
pages = "53--62",
abstract = "Effective business strategy formulation requires synthesising diverse, often conflicting information sources into coherent action plans. While Large Language Models (LLMs) show potential for processing textual information at scale, their application is limited by hallucinations and a lack of grounding in proprietary data. This paper proposes a methodology that integrates a domain-specific Knowledge Graph (KG) with a GraphRAG pipeline to generate strategic briefing documents, or Primers, which provide a structured overview of a company{'}s competitive environment. Our approach utilizes an ontology-first framework and Cypher-based graph traversal to capture the relational nature of strategic knowledge beyond simple vector retrieval. Experimental results on a Q{\&}A dataset demonstrate that the Vector + Cypher retrieval strategy significantly improves grounding over LLM-only baselines and outperforms naive vector retrieval in terms of completeness and usefulness. These findings suggest that the synergy of LLMs and structured KGs provides a robust foundation for automated strategic analysis in real-world business scenarios."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ghizzota-etal-2026-integrating">
<titleInfo>
<title>Integrating Knowledge Graph and Large Language Models for Defining Business Strategies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eleonora</namePart>
<namePart type="family">Ghizzota</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Jordan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Petruzzelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Siciliani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Spillo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierpaolo</namePart>
<namePart type="family">Basile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davide</namePart>
<namePart type="family">Sola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Scarso Borioli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Semeraro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gilles</namePart>
<namePart type="family">Sérasset</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katerina</namePart>
<namePart type="family">Gkirtzou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Cochez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan-Christoph</namePart>
<namePart type="family">Kalo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Effective business strategy formulation requires synthesising diverse, often conflicting information sources into coherent action plans. While Large Language Models (LLMs) show potential for processing textual information at scale, their application is limited by hallucinations and a lack of grounding in proprietary data. This paper proposes a methodology that integrates a domain-specific Knowledge Graph (KG) with a GraphRAG pipeline to generate strategic briefing documents, or Primers, which provide a structured overview of a company’s competitive environment. Our approach utilizes an ontology-first framework and Cypher-based graph traversal to capture the relational nature of strategic knowledge beyond simple vector retrieval. Experimental results on a Q&A dataset demonstrate that the Vector + Cypher retrieval strategy significantly improves grounding over LLM-only baselines and outperforms naive vector retrieval in terms of completeness and usefulness. These findings suggest that the synergy of LLMs and structured KGs provides a robust foundation for automated strategic analysis in real-world business scenarios.</abstract>
<identifier type="citekey">ghizzota-etal-2026-integrating</identifier>
<identifier type="doi">10.63317/4e642nbxhuqr</identifier>
<location>
<url>https://aclanthology.org/2026.kallm-1.6/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>53</start>
<end>62</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Integrating Knowledge Graph and Large Language Models for Defining Business Strategies
%A Ghizzota, Eleonora
%A Jordan, Alex
%A Petruzzelli, Alessandro
%A Siciliani, Lucia
%A Spillo, Giuseppe
%A Basile, Pierpaolo
%A Sola, Davide
%A Scarso Borioli, Giovanni
%A Semeraro, Giovanni
%Y Sérasset, Gilles
%Y Gkirtzou, Katerina
%Y Cochez, Michael
%Y Kalo, Jan-Christoph
%S Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F ghizzota-etal-2026-integrating
%X Effective business strategy formulation requires synthesising diverse, often conflicting information sources into coherent action plans. While Large Language Models (LLMs) show potential for processing textual information at scale, their application is limited by hallucinations and a lack of grounding in proprietary data. This paper proposes a methodology that integrates a domain-specific Knowledge Graph (KG) with a GraphRAG pipeline to generate strategic briefing documents, or Primers, which provide a structured overview of a company’s competitive environment. Our approach utilizes an ontology-first framework and Cypher-based graph traversal to capture the relational nature of strategic knowledge beyond simple vector retrieval. Experimental results on a Q&A dataset demonstrate that the Vector + Cypher retrieval strategy significantly improves grounding over LLM-only baselines and outperforms naive vector retrieval in terms of completeness and usefulness. These findings suggest that the synergy of LLMs and structured KGs provides a robust foundation for automated strategic analysis in real-world business scenarios.
%R 10.63317/4e642nbxhuqr
%U https://aclanthology.org/2026.kallm-1.6/
%U https://doi.org/10.63317/4e642nbxhuqr
%P 53-62
Markdown (Informal)
[Integrating Knowledge Graph and Large Language Models for Defining Business Strategies](https://aclanthology.org/2026.kallm-1.6/) (Ghizzota et al., KaLLM 2026)
ACL
- Eleonora Ghizzota, Alex Jordan, Alessandro Petruzzelli, Lucia Siciliani, Giuseppe Spillo, Pierpaolo Basile, Davide Sola, Giovanni Scarso Borioli, and Giovanni Semeraro. 2026. Integrating Knowledge Graph and Large Language Models for Defining Business Strategies. In Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26, pages 53–62, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).