sub:assertion {
<
https://doi.org/10.48550/arXiv.2502.03715>
dct:title "Boosting Knowledge Graph-based Recommendations through Confidence-Aware Augmentation with Large Language Models" ;
<
http://purl.org/spar/cito/describes> <
https://neverblink.eu/ontologies/llm-kg/methods#CKGLLMA> , <
https://neverblink.eu/ontologies/llm-kg/methods#ConfidenceAwareExplanationGeneration> , <
https://neverblink.eu/ontologies/llm-kg/methods#ConfidenceAwareMOEMessagePropagation> , <
https://neverblink.eu/ontologies/llm-kg/methods#DualViewTwoStepContrastiveLearning> , <
https://neverblink.eu/ontologies/llm-kg/methods#LLMbasedSubgraphAugmenter> ;
<
http://purl.org/spar/cito/discusses> <
https://neverblink.eu/ontologies/llm-kg/methods#CKE> , <
https://neverblink.eu/ontologies/llm-kg/methods#GreaseLM> , <
https://neverblink.eu/ontologies/llm-kg/methods#KGAT> , <
https://neverblink.eu/ontologies/llm-kg/methods#KGCL> , <
https://neverblink.eu/ontologies/llm-kg/methods#KGCN> , <
https://neverblink.eu/ontologies/llm-kg/methods#KGIN> , <
https://neverblink.eu/ontologies/llm-kg/methods#KPRN> , <
https://neverblink.eu/ontologies/llm-kg/methods#LKPNR> , <
https://neverblink.eu/ontologies/llm-kg/methods#LightGCN> , <
https://neverblink.eu/ontologies/llm-kg/methods#RenEtAl2024KnowledgeRationalization> , <
https://neverblink.eu/ontologies/llm-kg/methods#SGL> , <
https://neverblink.eu/ontologies/llm-kg/methods#SimGCL> , <
https://neverblink.eu/ontologies/llm-kg/methods#ThinkOnGraph> , <
https://neverblink.eu/ontologies/llm-kg/methods#XSimGCL> ;
a prov:Entity .
<
https://neverblink.eu/ontologies/llm-kg/methods#CKE>
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:label "CKE" .
<
https://neverblink.eu/ontologies/llm-kg/methods#CKGLLMA>
dct:subject <
https://neverblink.eu/ontologies/llm-kg/categories#SynergizedReasoning> ;
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:comment "CKG-LLMA is a novel framework that integrates LLMs and KGs bidirectionally. It uses LLMs to augment KGs and then leverages the enriched KGs to guide LLMs in generating explanations, combining multiple components for a unified reasoning process in recommendations." ;
rdfs:label "Confidence-aware KG-based Recommendation Framework with LLM Augmentation (CKG-LLMA)" ;
<
https://neverblink.eu/ontologies/llm-kg/hasTopCategory> <
https://neverblink.eu/ontologies/llm-kg/top-categories#SynergizedLLMKG> .
<
https://neverblink.eu/ontologies/llm-kg/methods#ConfidenceAwareExplanationGeneration>
dct:subject <
https://neverblink.eu/ontologies/llm-kg/categories#KGEnhancedLLMInterpretability> ;
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:comment "This method uses a two-step chain-of-thought reasoning procedure, guided by the augmented KG information and confidence scores, to instruct LLMs. It enables LLMs to generate realistic and informative natural language explanations for recommendations, thereby enhancing interpretability." ;
rdfs:label "Confidence-aware Explanation Generation" ;
<
https://neverblink.eu/ontologies/llm-kg/hasTopCategory> <
https://neverblink.eu/ontologies/llm-kg/top-categories#KGEnhancedLLM> .
<
https://neverblink.eu/ontologies/llm-kg/methods#ConfidenceAwareMOEMessagePropagation>
dct:subject <
https://neverblink.eu/ontologies/llm-kg/categories#SynergizedKnowledgeRepresentation> ;
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:comment "This mechanism introduces a learnable edge confidence for LLM-enhanced triplets, utilizing a Mixture-of-Experts layer to filter noisy information and effectively aggregate knowledge. It represents knowledge from both LLM augmentations and KG structures in a unified and robust manner." ;
rdfs:label "Confidence-aware MOE Message Propagation" ;
<
https://neverblink.eu/ontologies/llm-kg/hasTopCategory> <
https://neverblink.eu/ontologies/llm-kg/top-categories#SynergizedLLMKG> .
<
https://neverblink.eu/ontologies/llm-kg/methods#DualViewTwoStepContrastiveLearning>
dct:subject <
https://neverblink.eu/ontologies/llm-kg/categories#SynergizedKnowledgeRepresentation> ;
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:comment "This method constructs a dual-view contrastive learning framework, combining differentiable KG augmentation and interaction graph enhancement. Its aim is to learn robust user and item representations by integrating knowledge from both original KGs and LLM-augmented data through self-supervised signals." ;
rdfs:label "Dual-view Two-step Contrastive Learning" ;
<
https://neverblink.eu/ontologies/llm-kg/hasTopCategory> <
https://neverblink.eu/ontologies/llm-kg/top-categories#SynergizedLLMKG> .
<
https://neverblink.eu/ontologies/llm-kg/methods#GreaseLM>
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:label "GreaseLM" .
<
https://neverblink.eu/ontologies/llm-kg/methods#KGAT>
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:label "KGAT" .
<
https://neverblink.eu/ontologies/llm-kg/methods#KGCL>
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:label "KGCL" .
<
https://neverblink.eu/ontologies/llm-kg/methods#KGCN>
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:label "KGCN" .
<
https://neverblink.eu/ontologies/llm-kg/methods#KGIN>
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:label "KGIN" .
<
https://neverblink.eu/ontologies/llm-kg/methods#KPRN>
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:label "KPRN" .
<
https://neverblink.eu/ontologies/llm-kg/methods#LKPNR>
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:label "LKPNR" .
<
https://neverblink.eu/ontologies/llm-kg/methods#LLMbasedSubgraphAugmenter>
dct:subject <
https://neverblink.eu/ontologies/llm-kg/categories#LLMAugmentedKGConstruction> ;
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:comment "This method uses LLMs with specific multi-view prompts (User-view and Item-view) to refine and augment extracted knowledge subgraphs. Its primary goal is to enrich KGs by adding or deleting triplets, directly contributing to KG construction and quality improvement." ;
rdfs:label "LLM-based Subgraph Augmenter" ;
<
https://neverblink.eu/ontologies/llm-kg/hasTopCategory> <
https://neverblink.eu/ontologies/llm-kg/top-categories#LLMAugmentedKG> .
<
https://neverblink.eu/ontologies/llm-kg/methods#LightGCN>
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:label "LightGCN" .
<
https://neverblink.eu/ontologies/llm-kg/methods#RenEtAl2024KnowledgeRationalization>
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:label "RenEtAl2024KnowledgeRationalization" .
<
https://neverblink.eu/ontologies/llm-kg/methods#SGL>
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:label "SGL" .
<
https://neverblink.eu/ontologies/llm-kg/methods#SimGCL>
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:label "SimGCL" .
<
https://neverblink.eu/ontologies/llm-kg/methods#ThinkOnGraph>
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:label "Think-on-graph" .
<
https://neverblink.eu/ontologies/llm-kg/methods#XSimGCL>
a <
http://purl.org/spar/fabio/Workflow> ;
rdfs:label "XSimGCL" .
}