[
    {
        "@id": "https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs/pubinfo",
        "@graph": [
            {
                "@id": "https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs",
                "http://purl.org/dc/terms/created": [
                    {
                        "@value": "2026-02-26T15:57:20.083Z",
                        "@type": "http://www.w3.org/2001/XMLSchema#dateTime"
                    }
                ],
                "http://purl.org/dc/terms/creator": [
                    {
                        "@id": "https://neverblink.eu/ontologies/llm-kg/agent"
                    }
                ],
                "http://purl.org/nanopub/x/hasNanopubType": [
                    {
                        "@id": "https://neverblink.eu/ontologies/llm-kg/PaperAssessmentResult"
                    }
                ],
                "http://www.w3.org/2000/01/rdf-schema#label": [
                    {
                        "@value": "LLM-KG assessment for paper 10.48550/arXiv.2402.06764"
                    }
                ]
            },
            {
                "@id": "https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs/sig",
                "http://purl.org/nanopub/x/hasAlgorithm": [
                    {
                        "@value": "RSA"
                    }
                ],
                "http://purl.org/nanopub/x/hasPublicKey": [
                    {
                        "@value": "MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAwNz2QK3SEifno78S7+48zUB0xpTex3mAzW73ZimHqNcdEMU5/apslrGrTHGFAt/Chocgo++r6JQp5ygY7NyJHGWdaIqnt85pjX4PbNfLAvapyUO00qZP34fY61w4eZ9UMtleWEsmZKRtQPyJ8ODl46i/rfPuZlcJGpM9Nmy5mpGWuepqIEvF4a/t7pLVeCEDFSYXT+yaiygt6ynIK5f7TtEDhZpeUf/Q74WhMPJXm4yTU/hqOX4IW+50kWHNArGGZwUaXwzyG6M3Zd6UMModryGkLqS4H/MSE3ZA1Ylnms7BfWLEXhMWlaKi6HRV4nGRDLhxVSi9LSRi3LWKLhNIIQIDAQAB"
                    }
                ],
                "http://purl.org/nanopub/x/hasSignature": [
                    {
                        "@value": "u6dPlUuTUn1QedW6Fo7ljSYw2G4COewda0DpI0s95BWkF2vMzjoMKMokBVugNbLAF7WgBfWLNdwTqbnSBYf9xRted+aca4PBWgEF/7gswieTkJn0cmbIkRP85Fl+j9VWoAgVzb4c5Zu8KcI3cXo5W7LLfNx6yCW1fgamArf4JmksrxJIsftt9gcgHTJKFMt3XsI0WBTmVF3hcrJqj4tf/vAOIiuEnHkcMK2hOk4+0BAjf9MXAKG1b5ufatAxOHCQxqwe4dTz7da/ClVar+D0yMszjGQHpWfsEPcVvWz6hxmK2/0PueA/cKu4mrpSyACehPyNjjEwIqWSKn/XqMqzCg=="
                    }
                ],
                "http://purl.org/nanopub/x/hasSignatureTarget": [
                    {
                        "@id": "https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs"
                    }
                ],
                "http://purl.org/nanopub/x/signedBy": [
                    {
                        "@id": "https://neverblink.eu/ontologies/llm-kg/agent"
                    }
                ]
            }
        ]
    },
    {
        "@id": "https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs/provenance",
        "@graph": [
            {
                "@id": "https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs/assertion",
                "http://www.w3.org/ns/prov#wasAttributedTo": [
                    {
                        "@id": "https://neverblink.eu/ontologies/llm-kg/agent"
                    }
                ],
                "http://www.w3.org/ns/prov#wasDerivedFrom": [
                    {
                        "@id": "https://doi.org/10.48550/arXiv.2402.06764"
                    }
                ]
            }
        ]
    },
    {
        "@id": "https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs/Head",
        "@graph": [
            {
                "@id": "https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs",
                "http://www.nanopub.org/nschema#hasAssertion": [
                    {
                        "@id": "https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs/assertion"
                    }
                ],
                "http://www.nanopub.org/nschema#hasProvenance": [
                    {
                        "@id": "https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs/provenance"
                    }
                ],
                "http://www.nanopub.org/nschema#hasPublicationInfo": [
                    {
                        "@id": "https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs/pubinfo"
                    }
                ],
                "@type": [
                    "http://www.nanopub.org/nschema#Nanopublication"
                ]
            }
        ]
    },
    {
        "@id": "https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs/assertion",
        "@graph": [
            {
                "@id": "https://doi.org/10.48550/arXiv.2402.06764",
                "http://purl.org/dc/terms/title": [
                    {
                        "@value": "GLaM: Fine-Tuning Large Language Models for Domain Knowledge Graph Alignment via Neighborhood Partitioning and Generative Subgraph Encoding"
                    }
                ],
                "http://purl.org/spar/cito/describes": [
                    {
                        "@id": "https://neverblink.eu/ontologies/llm-kg/methods#GLaMLLMSummarization"
                    },
                    {
                        "@id": "https://neverblink.eu/ontologies/llm-kg/methods#GLaMNodeDescriptorsAdjacencySummarization"
                    },
                    {
                        "@id": "https://neverblink.eu/ontologies/llm-kg/methods#GLaMRelationalGrouping"
                    },
                    {
                        "@id": "https://neverblink.eu/ontologies/llm-kg/methods#GLaMTriples"
                    }
                ],
                "http://purl.org/spar/cito/discusses": [
                    {
                        "@id": "https://neverblink.eu/ontologies/llm-kg/methods#FewShotPrompting"
                    },
                    {
                        "@id": "https://neverblink.eu/ontologies/llm-kg/methods#GNNLLMJointModelCoupling"
                    },
                    {
                        "@id": "https://neverblink.eu/ontologies/llm-kg/methods#GNNLLMSoftPrompting"
                    },
                    {
                        "@id": "https://neverblink.eu/ontologies/llm-kg/methods#RetrievalAugmentedGeneration"
                    }
                ],
                "@type": [
                    "http://www.w3.org/ns/prov#Entity"
                ]
            },
            {
                "@id": "https://neverblink.eu/ontologies/llm-kg/methods#GLaMLLMSummarization",
                "http://purl.org/dc/terms/subject": [
                    {
                        "@id": "https://neverblink.eu/ontologies/llm-kg/categories#KGEnhancedLLMPretraining"
                    }
                ],
                "@type": [
                    "http://purl.org/spar/fabio/Workflow"
                ],
                "http://www.w3.org/2000/01/rdf-schema#comment": [
                    {
                        "@value": "This method leverages the LLM's generative capabilities to rewrite or summarize the encoded graph statements into more coherent representations for fine-tuning. The goal is to enhance semantic alignment between the KG and the LLM's vocabulary, thereby improving the LLM's factual recall and multi-hop reasoning after training."
                    }
                ],
                "http://www.w3.org/2000/01/rdf-schema#label": [
                    {
                        "@value": "GLaM (LLM Summarization)"
                    }
                ],
                "https://neverblink.eu/ontologies/llm-kg/hasTopCategory": [
                    {
                        "@id": "https://neverblink.eu/ontologies/llm-kg/top-categories#KGEnhancedLLM"
                    }
                ]
            },
            {
                "@id": "https://neverblink.eu/ontologies/llm-kg/methods#GLaMNodeDescriptorsAdjacencySummarization",
                "http://purl.org/dc/terms/subject": [
                    {
                        "@id": "https://neverblink.eu/ontologies/llm-kg/categories#KGEnhancedLLMPretraining"
                    }
                ],
                "@type": [
                    "http://purl.org/spar/fabio/Workflow"
                ],
                "http://www.w3.org/2000/01/rdf-schema#comment": [
                    {
                        "@value": "This method combines multiple encoding strategies, specifically using LLM's zero-shot capabilities to create text-based node descriptors from the k-hop context subgraph, utilizing adjacency lists, and performing summarization. This comprehensive approach aims to instill robust graph-based reasoning capabilities into the LLM via fine-tuning."
                    }
                ],
                "http://www.w3.org/2000/01/rdf-schema#label": [
                    {
                        "@value": "GLaM (Node Descriptors, Adjacency Lists, and Summarization Combination)"
                    }
                ],
                "https://neverblink.eu/ontologies/llm-kg/hasTopCategory": [
                    {
                        "@id": "https://neverblink.eu/ontologies/llm-kg/top-categories#KGEnhancedLLM"
                    }
                ]
            },
            {
                "@id": "https://neverblink.eu/ontologies/llm-kg/methods#GLaMRelationalGrouping",
                "http://purl.org/dc/terms/subject": [
                    {
                        "@id": "https://neverblink.eu/ontologies/llm-kg/categories#KGEnhancedLLMPretraining"
                    }
                ],
                "@type": [
                    "http://purl.org/spar/fabio/Workflow"
                ],
                "http://www.w3.org/2000/01/rdf-schema#comment": [
                    {
                        "@value": "This GLaM variant encodes the neighborhood subgraph by including the entire adjacency list of the central node or partitioning neighbors based on relation types. This strategy is used to fine-tune the LLM to better understand graph structure for improved knowledge expression."
                    }
                ],
                "http://www.w3.org/2000/01/rdf-schema#label": [
                    {
                        "@value": "GLaM (Relational Grouping)"
                    }
                ],
                "https://neverblink.eu/ontologies/llm-kg/hasTopCategory": [
                    {
                        "@id": "https://neverblink.eu/ontologies/llm-kg/top-categories#KGEnhancedLLM"
                    }
                ]
            },
            {
                "@id": "https://neverblink.eu/ontologies/llm-kg/methods#GLaMTriples",
                "http://purl.org/dc/terms/subject": [
                    {
                        "@id": "https://neverblink.eu/ontologies/llm-kg/categories#KGEnhancedLLMPretraining"
                    }
                ],
                "@type": [
                    "http://purl.org/spar/fabio/Workflow"
                ],
                "http://www.w3.org/2000/01/rdf-schema#comment": [
                    {
                        "@value": "This method is a specific implementation within the GLaM framework where the neighborhood subgraph is encoded into (source, relation, target) triples for fine-tuning. It aims to improve the LLM's factual reasoning by embedding graph knowledge directly into its parameters during the training phase."
                    }
                ],
                "http://www.w3.org/2000/01/rdf-schema#label": [
                    {
                        "@value": "GLaM (Triples)"
                    }
                ],
                "https://neverblink.eu/ontologies/llm-kg/hasTopCategory": [
                    {
                        "@id": "https://neverblink.eu/ontologies/llm-kg/top-categories#KGEnhancedLLM"
                    }
                ]
            },
            {
                "@id": "https://neverblink.eu/ontologies/llm-kg/methods#FewShotPrompting",
                "@type": [
                    "http://purl.org/spar/fabio/Workflow"
                ],
                "http://www.w3.org/2000/01/rdf-schema#label": [
                    {
                        "@value": "Few-Shot Prompting"
                    }
                ]
            },
            {
                "@id": "https://neverblink.eu/ontologies/llm-kg/methods#GNNLLMJointModelCoupling",
                "@type": [
                    "http://purl.org/spar/fabio/Workflow"
                ],
                "http://www.w3.org/2000/01/rdf-schema#label": [
                    {
                        "@value": "GNN-LLM Joint Model Coupling"
                    }
                ]
            },
            {
                "@id": "https://neverblink.eu/ontologies/llm-kg/methods#GNNLLMSoftPrompting",
                "@type": [
                    "http://purl.org/spar/fabio/Workflow"
                ],
                "http://www.w3.org/2000/01/rdf-schema#label": [
                    {
                        "@value": "GNN-LLM Soft Prompting"
                    }
                ]
            },
            {
                "@id": "https://neverblink.eu/ontologies/llm-kg/methods#RetrievalAugmentedGeneration",
                "@type": [
                    "http://purl.org/spar/fabio/Workflow"
                ],
                "http://www.w3.org/2000/01/rdf-schema#label": [
                    {
                        "@value": "Retrieval Augmented Generation (RAG)"
                    }
                ]
            }
        ]
    }
]