https://w3id.org/np/RAS-0OM11mapYuyVaN1gXkHnZWCvmVxg4EjoeYc1gQzpo/Head https://w3id.org/np/RAS-0OM11mapYuyVaN1gXkHnZWCvmVxg4EjoeYc1gQzpo http://www.nanopub.org/nschema#hasAssertion https://w3id.org/np/RAS-0OM11mapYuyVaN1gXkHnZWCvmVxg4EjoeYc1gQzpo/assertion https://w3id.org/np/RAS-0OM11mapYuyVaN1gXkHnZWCvmVxg4EjoeYc1gQzpo http://www.nanopub.org/nschema#hasProvenance https://w3id.org/np/RAS-0OM11mapYuyVaN1gXkHnZWCvmVxg4EjoeYc1gQzpo/provenance https://w3id.org/np/RAS-0OM11mapYuyVaN1gXkHnZWCvmVxg4EjoeYc1gQzpo http://www.nanopub.org/nschema#hasPublicationInfo https://w3id.org/np/RAS-0OM11mapYuyVaN1gXkHnZWCvmVxg4EjoeYc1gQzpo/pubinfo https://w3id.org/np/RAS-0OM11mapYuyVaN1gXkHnZWCvmVxg4EjoeYc1gQzpo http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://www.nanopub.org/nschema#Nanopublication https://w3id.org/np/RAS-0OM11mapYuyVaN1gXkHnZWCvmVxg4EjoeYc1gQzpo/assertion https://doi.org/10.48550/arXiv.2405.20139 http://purl.org/dc/terms/title GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning https://doi.org/10.48550/arXiv.2405.20139 http://purl.org/spar/cito/describes https://neverblink.eu/ontologies/llm-kg/methods#GnnRag https://doi.org/10.48550/arXiv.2405.20139 http://purl.org/spar/cito/describes https://neverblink.eu/ontologies/llm-kg/methods#GnnRagRa https://doi.org/10.48550/arXiv.2405.20139 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#GRetriever https://doi.org/10.48550/arXiv.2405.20139 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#GraftNet https://doi.org/10.48550/arXiv.2405.20139 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#KbBinder https://doi.org/10.48550/arXiv.2405.20139 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#KdCoT https://doi.org/10.48550/arXiv.2405.20139 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#LmSr https://doi.org/10.48550/arXiv.2405.20139 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#Nsm https://doi.org/10.48550/arXiv.2405.20139 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#ReaRev https://doi.org/10.48550/arXiv.2405.20139 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#RoG https://doi.org/10.48550/arXiv.2405.20139 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#Sbert https://doi.org/10.48550/arXiv.2405.20139 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#ToG https://doi.org/10.48550/arXiv.2405.20139 http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://www.w3.org/ns/prov#Entity https://neverblink.eu/ontologies/llm-kg/methods#GRetriever http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#GRetriever http://www.w3.org/2000/01/rdf-schema#label G-Retriever https://neverblink.eu/ontologies/llm-kg/methods#GnnRag http://purl.org/dc/terms/subject https://neverblink.eu/ontologies/llm-kg/categories#KGEnhancedLLMInference https://neverblink.eu/ontologies/llm-kg/methods#GnnRag http://purl.org/spar/fabio/hasURL https://github.com/cmavro/ReaRev_KGQA https://neverblink.eu/ontologies/llm-kg/methods#GnnRag http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#GnnRag http://www.w3.org/2000/01/rdf-schema#comment GNN-RAG enhances LLM performance on KGQA by using a GNN to retrieve relevant multi-hop reasoning paths from a KG. These verbalized paths are then fed to the LLM as context for RAG, thereby improving the LLM's ability to answer complex questions during its inference stage and reducing hallucinations. https://neverblink.eu/ontologies/llm-kg/methods#GnnRag http://www.w3.org/2000/01/rdf-schema#label GNN-RAG https://neverblink.eu/ontologies/llm-kg/methods#GnnRag https://neverblink.eu/ontologies/llm-kg/hasTopCategory https://neverblink.eu/ontologies/llm-kg/top-categories#KGEnhancedLLM https://neverblink.eu/ontologies/llm-kg/methods#GnnRagRa http://purl.org/dc/terms/subject https://neverblink.eu/ontologies/llm-kg/categories#KGEnhancedLLMInference https://neverblink.eu/ontologies/llm-kg/methods#GnnRagRa http://purl.org/spar/fabio/hasURL https://github.com/cmavro/ReaRev_KGQA https://neverblink.eu/ontologies/llm-kg/methods#GnnRagRa http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#GnnRagRa http://www.w3.org/2000/01/rdf-schema#comment GNN-RAG+RA further boosts LLM KGQA performance by employing retrieval augmentation, combining GNN-induced reasoning paths with LLM-based retrieved paths (e.g., from RoG). This method increases the diversity and recall of retrieved KG information, which in turn enhances the LLM's reasoning and answer accuracy during inference. https://neverblink.eu/ontologies/llm-kg/methods#GnnRagRa http://www.w3.org/2000/01/rdf-schema#label GNN-RAG+RA https://neverblink.eu/ontologies/llm-kg/methods#GnnRagRa https://neverblink.eu/ontologies/llm-kg/hasTopCategory https://neverblink.eu/ontologies/llm-kg/top-categories#KGEnhancedLLM https://neverblink.eu/ontologies/llm-kg/methods#GraftNet http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#GraftNet http://www.w3.org/2000/01/rdf-schema#label GraftNet https://neverblink.eu/ontologies/llm-kg/methods#KbBinder http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#KbBinder http://www.w3.org/2000/01/rdf-schema#label KB-BINDER https://neverblink.eu/ontologies/llm-kg/methods#KdCoT http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#KdCoT http://www.w3.org/2000/01/rdf-schema#label KD-CoT https://neverblink.eu/ontologies/llm-kg/methods#LmSr http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#LmSr http://www.w3.org/2000/01/rdf-schema#label LM SR https://neverblink.eu/ontologies/llm-kg/methods#Nsm http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#Nsm http://www.w3.org/2000/01/rdf-schema#label NSM https://neverblink.eu/ontologies/llm-kg/methods#ReaRev http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#ReaRev http://www.w3.org/2000/01/rdf-schema#label ReaRev https://neverblink.eu/ontologies/llm-kg/methods#RoG http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#RoG http://www.w3.org/2000/01/rdf-schema#label RoG https://neverblink.eu/ontologies/llm-kg/methods#Sbert http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#Sbert http://www.w3.org/2000/01/rdf-schema#label SBERT https://neverblink.eu/ontologies/llm-kg/methods#ToG http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#ToG http://www.w3.org/2000/01/rdf-schema#label ToG https://w3id.org/np/RAS-0OM11mapYuyVaN1gXkHnZWCvmVxg4EjoeYc1gQzpo/provenance https://w3id.org/np/RAS-0OM11mapYuyVaN1gXkHnZWCvmVxg4EjoeYc1gQzpo/assertion http://www.w3.org/ns/prov#wasAttributedTo https://neverblink.eu/ontologies/llm-kg/agent https://w3id.org/np/RAS-0OM11mapYuyVaN1gXkHnZWCvmVxg4EjoeYc1gQzpo/assertion http://www.w3.org/ns/prov#wasDerivedFrom https://doi.org/10.48550/arXiv.2405.20139 https://w3id.org/np/RAS-0OM11mapYuyVaN1gXkHnZWCvmVxg4EjoeYc1gQzpo/pubinfo https://w3id.org/np/RAS-0OM11mapYuyVaN1gXkHnZWCvmVxg4EjoeYc1gQzpo http://purl.org/dc/terms/created 2026-02-26T16:19:24.245Z https://w3id.org/np/RAS-0OM11mapYuyVaN1gXkHnZWCvmVxg4EjoeYc1gQzpo http://purl.org/dc/terms/creator https://neverblink.eu/ontologies/llm-kg/agent https://w3id.org/np/RAS-0OM11mapYuyVaN1gXkHnZWCvmVxg4EjoeYc1gQzpo http://purl.org/nanopub/x/hasNanopubType https://neverblink.eu/ontologies/llm-kg/PaperAssessmentResult https://w3id.org/np/RAS-0OM11mapYuyVaN1gXkHnZWCvmVxg4EjoeYc1gQzpo http://www.w3.org/2000/01/rdf-schema#label LLM-KG assessment for paper 10.48550/arXiv.2405.20139 https://w3id.org/np/RAS-0OM11mapYuyVaN1gXkHnZWCvmVxg4EjoeYc1gQzpo/sig http://purl.org/nanopub/x/hasAlgorithm RSA https://w3id.org/np/RAS-0OM11mapYuyVaN1gXkHnZWCvmVxg4EjoeYc1gQzpo/sig http://purl.org/nanopub/x/hasPublicKey MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAwNz2QK3SEifno78S7+48zUB0xpTex3mAzW73ZimHqNcdEMU5/apslrGrTHGFAt/Chocgo++r6JQp5ygY7NyJHGWdaIqnt85pjX4PbNfLAvapyUO00qZP34fY61w4eZ9UMtleWEsmZKRtQPyJ8ODl46i/rfPuZlcJGpM9Nmy5mpGWuepqIEvF4a/t7pLVeCEDFSYXT+yaiygt6ynIK5f7TtEDhZpeUf/Q74WhMPJXm4yTU/hqOX4IW+50kWHNArGGZwUaXwzyG6M3Zd6UMModryGkLqS4H/MSE3ZA1Ylnms7BfWLEXhMWlaKi6HRV4nGRDLhxVSi9LSRi3LWKLhNIIQIDAQAB https://w3id.org/np/RAS-0OM11mapYuyVaN1gXkHnZWCvmVxg4EjoeYc1gQzpo/sig http://purl.org/nanopub/x/hasSignature BKsB5zCOEzTtCoNJXfgkuVcii70xQEEIZvULiMb7TOExh+jgJZmVp87Witiqu7hPU3K4GTylk5Tp5HVNrpvC8e69ReYOY61xQ5lT+VX/ZUhb2FazXHRyZxPL1ARcVYsQfSKstOKRT6ycrm0iDRXYwbUpCpdc1eVQMOMitTdAEpAU2VdsOK/8KUKHNuiiLaDMG8bA7w3G5GCrovB1TKBUjssZSzA4IpzSk5xRm3o3q6gSavmRcnZFIQlxbv2Vaqp+mTR11RYHDglRXf5yrUbzRv5hgKOO+u6BCOPiD/Y+khvj2gsvniKj/XEbnvw4e3lcMs3XXU+ju7F35A9fPTXLEg== https://w3id.org/np/RAS-0OM11mapYuyVaN1gXkHnZWCvmVxg4EjoeYc1gQzpo/sig http://purl.org/nanopub/x/hasSignatureTarget https://w3id.org/np/RAS-0OM11mapYuyVaN1gXkHnZWCvmVxg4EjoeYc1gQzpo https://w3id.org/np/RAS-0OM11mapYuyVaN1gXkHnZWCvmVxg4EjoeYc1gQzpo/sig http://purl.org/nanopub/x/signedBy https://neverblink.eu/ontologies/llm-kg/agent