sub:assertion {
<
https://doi.org/10.48550/arXiv.2404.19744>
dct:title "PrivComp-KG: Leveraging Knowledge Graph and Large Language Models for Privacy Policy Compliance Verification" ;
<
http://purl.org/spar/cito/describes> <
https://neverblink.eu/ontologies/llm-kg/methods#PrivCompKG> , <
https://neverblink.eu/ontologies/llm-kg/methods#RAGLLMComplianceFactExtraction> ;
<
http://purl.org/spar/cito/discusses> <
https://neverblink.eu/ontologies/llm-kg/methods#BERTAbstractiveSummarizer> , <
https://neverblink.eu/ontologies/llm-kg/methods#ChromaDB> , <
https://neverblink.eu/ontologies/llm-kg/methods#Llama7B> , <
https://neverblink.eu/ontologies/llm-kg/methods#ProtegeSoftware> , <
https://neverblink.eu/ontologies/llm-kg/methods#RAGAS> , <
https://neverblink.eu/ontologies/llm-kg/methods#ResourceDescriptionFramework> , <
https://neverblink.eu/ontologies/llm-kg/methods#RetrievalAugmentedGeneration> , <
https://neverblink.eu/ontologies/llm-kg/methods#SemanticWebRuleLanguage> , <
https://neverblink.eu/ontologies/llm-kg/methods#WebOntologyLanguage> ;
a prov:Entity .
<
https://neverblink.eu/ontologies/llm-kg/methods#BERTAbstractiveSummarizer>
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:label "BERT abstractive summarizer" .
<
https://neverblink.eu/ontologies/llm-kg/methods#ChromaDB>
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:label "ChromaDB" .
<
https://neverblink.eu/ontologies/llm-kg/methods#Llama7B>
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:label "Llama-7B" .
<
https://neverblink.eu/ontologies/llm-kg/methods#PrivCompKG>
dct:subject <
https://neverblink.eu/ontologies/llm-kg/categories#SynergizedKnowledgeRepresentation> ;
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:comment "PrivComp-KG is a novel, unified framework that combines LLM-extracted knowledge with a structured knowledge graph and its reasoning capabilities to verify privacy policy compliance. The LLM populates the KG with extracted relations between privacy policies and regulatory articles, enabling the KG to effectively represent the complex compliance landscape for subsequent inference via SWRL rules." ;
rdfs:label "PrivComp-KG" ;
<
https://neverblink.eu/ontologies/llm-kg/hasTopCategory> <
https://neverblink.eu/ontologies/llm-kg/top-categories#SynergizedLLMKG> .
<
https://neverblink.eu/ontologies/llm-kg/methods#ProtegeSoftware>
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:label "Protege software" .
<
https://neverblink.eu/ontologies/llm-kg/methods#RAGAS>
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:label "RAGAS" .
<
https://neverblink.eu/ontologies/llm-kg/methods#RAGLLMComplianceFactExtraction>
dct:subject <
https://neverblink.eu/ontologies/llm-kg/categories#LLMAugmentedKGConstruction> ;
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:comment "This method proposes a specific pipeline using a RAG-enabled LLM (Llama-7B with ChromaDB and a vector store of GDPR article chunks) and a tailored prompting strategy to identify relevant GDPR articles and segments aligning with privacy policy sections. This extracted information directly contributes to populating the PrivComp-KG, thus augmenting KG construction by providing extracted compliance facts." ;
rdfs:label "RAG-LLM Compliance Fact Extraction" ;
<
https://neverblink.eu/ontologies/llm-kg/hasTopCategory> <
https://neverblink.eu/ontologies/llm-kg/top-categories#LLMAugmentedKG> .
<
https://neverblink.eu/ontologies/llm-kg/methods#ResourceDescriptionFramework>
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:label "Resource Description Framework" .
<
https://neverblink.eu/ontologies/llm-kg/methods#RetrievalAugmentedGeneration>
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:label "Retrieval Augmented Generation" .
<
https://neverblink.eu/ontologies/llm-kg/methods#SemanticWebRuleLanguage>
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:label "Semantic Web Rule Language" .
<
https://neverblink.eu/ontologies/llm-kg/methods#WebOntologyLanguage>
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:label "Web Ontology Language" .
}