https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs/Head https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs http://www.nanopub.org/nschema#hasAssertion https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs/assertion https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs http://www.nanopub.org/nschema#hasProvenance https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs/provenance https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs http://www.nanopub.org/nschema#hasPublicationInfo https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs/pubinfo https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://www.nanopub.org/nschema#Nanopublication https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs/assertion https://doi.org/10.48550/arXiv.2402.06764 http://purl.org/dc/terms/title GLaM: Fine-Tuning Large Language Models for Domain Knowledge Graph Alignment via Neighborhood Partitioning and Generative Subgraph Encoding https://doi.org/10.48550/arXiv.2402.06764 http://purl.org/spar/cito/describes https://neverblink.eu/ontologies/llm-kg/methods#GLaMLLMSummarization https://doi.org/10.48550/arXiv.2402.06764 http://purl.org/spar/cito/describes https://neverblink.eu/ontologies/llm-kg/methods#GLaMNodeDescriptorsAdjacencySummarization https://doi.org/10.48550/arXiv.2402.06764 http://purl.org/spar/cito/describes https://neverblink.eu/ontologies/llm-kg/methods#GLaMRelationalGrouping https://doi.org/10.48550/arXiv.2402.06764 http://purl.org/spar/cito/describes https://neverblink.eu/ontologies/llm-kg/methods#GLaMTriples https://doi.org/10.48550/arXiv.2402.06764 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#FewShotPrompting https://doi.org/10.48550/arXiv.2402.06764 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#GNNLLMJointModelCoupling https://doi.org/10.48550/arXiv.2402.06764 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#GNNLLMSoftPrompting https://doi.org/10.48550/arXiv.2402.06764 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#RetrievalAugmentedGeneration https://doi.org/10.48550/arXiv.2402.06764 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#FewShotPrompting http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#FewShotPrompting http://www.w3.org/2000/01/rdf-schema#label Few-Shot Prompting https://neverblink.eu/ontologies/llm-kg/methods#GLaMLLMSummarization http://purl.org/dc/terms/subject https://neverblink.eu/ontologies/llm-kg/categories#KGEnhancedLLMPretraining https://neverblink.eu/ontologies/llm-kg/methods#GLaMLLMSummarization http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#GLaMLLMSummarization http://www.w3.org/2000/01/rdf-schema#comment 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. https://neverblink.eu/ontologies/llm-kg/methods#GLaMLLMSummarization http://www.w3.org/2000/01/rdf-schema#label GLaM (LLM Summarization) https://neverblink.eu/ontologies/llm-kg/methods#GLaMLLMSummarization https://neverblink.eu/ontologies/llm-kg/hasTopCategory https://neverblink.eu/ontologies/llm-kg/top-categories#KGEnhancedLLM https://neverblink.eu/ontologies/llm-kg/methods#GLaMNodeDescriptorsAdjacencySummarization http://purl.org/dc/terms/subject https://neverblink.eu/ontologies/llm-kg/categories#KGEnhancedLLMPretraining https://neverblink.eu/ontologies/llm-kg/methods#GLaMNodeDescriptorsAdjacencySummarization http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#GLaMNodeDescriptorsAdjacencySummarization http://www.w3.org/2000/01/rdf-schema#comment 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. https://neverblink.eu/ontologies/llm-kg/methods#GLaMNodeDescriptorsAdjacencySummarization http://www.w3.org/2000/01/rdf-schema#label GLaM (Node Descriptors, Adjacency Lists, and Summarization Combination) https://neverblink.eu/ontologies/llm-kg/methods#GLaMNodeDescriptorsAdjacencySummarization https://neverblink.eu/ontologies/llm-kg/hasTopCategory https://neverblink.eu/ontologies/llm-kg/top-categories#KGEnhancedLLM https://neverblink.eu/ontologies/llm-kg/methods#GLaMRelationalGrouping http://purl.org/dc/terms/subject https://neverblink.eu/ontologies/llm-kg/categories#KGEnhancedLLMPretraining https://neverblink.eu/ontologies/llm-kg/methods#GLaMRelationalGrouping http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#GLaMRelationalGrouping http://www.w3.org/2000/01/rdf-schema#comment 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. https://neverblink.eu/ontologies/llm-kg/methods#GLaMRelationalGrouping http://www.w3.org/2000/01/rdf-schema#label GLaM (Relational Grouping) https://neverblink.eu/ontologies/llm-kg/methods#GLaMRelationalGrouping https://neverblink.eu/ontologies/llm-kg/hasTopCategory https://neverblink.eu/ontologies/llm-kg/top-categories#KGEnhancedLLM https://neverblink.eu/ontologies/llm-kg/methods#GLaMTriples http://purl.org/dc/terms/subject https://neverblink.eu/ontologies/llm-kg/categories#KGEnhancedLLMPretraining https://neverblink.eu/ontologies/llm-kg/methods#GLaMTriples http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#GLaMTriples http://www.w3.org/2000/01/rdf-schema#comment 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. https://neverblink.eu/ontologies/llm-kg/methods#GLaMTriples http://www.w3.org/2000/01/rdf-schema#label GLaM (Triples) https://neverblink.eu/ontologies/llm-kg/methods#GLaMTriples https://neverblink.eu/ontologies/llm-kg/hasTopCategory https://neverblink.eu/ontologies/llm-kg/top-categories#KGEnhancedLLM https://neverblink.eu/ontologies/llm-kg/methods#GNNLLMJointModelCoupling http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#GNNLLMJointModelCoupling http://www.w3.org/2000/01/rdf-schema#label GNN-LLM Joint Model Coupling https://neverblink.eu/ontologies/llm-kg/methods#GNNLLMSoftPrompting http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#GNNLLMSoftPrompting http://www.w3.org/2000/01/rdf-schema#label GNN-LLM Soft Prompting https://neverblink.eu/ontologies/llm-kg/methods#RetrievalAugmentedGeneration http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#RetrievalAugmentedGeneration http://www.w3.org/2000/01/rdf-schema#label Retrieval Augmented Generation (RAG) https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs/provenance https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs/assertion http://www.w3.org/ns/prov#wasAttributedTo https://neverblink.eu/ontologies/llm-kg/agent https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs/assertion http://www.w3.org/ns/prov#wasDerivedFrom https://doi.org/10.48550/arXiv.2402.06764 https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs/pubinfo https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs http://purl.org/dc/terms/created 2026-02-26T15:57:20.083Z https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs http://purl.org/dc/terms/creator https://neverblink.eu/ontologies/llm-kg/agent https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs http://purl.org/nanopub/x/hasNanopubType https://neverblink.eu/ontologies/llm-kg/PaperAssessmentResult https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs http://www.w3.org/2000/01/rdf-schema#label LLM-KG assessment for paper 10.48550/arXiv.2402.06764 https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs/sig http://purl.org/nanopub/x/hasAlgorithm RSA https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs/sig http://purl.org/nanopub/x/hasPublicKey MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAwNz2QK3SEifno78S7+48zUB0xpTex3mAzW73ZimHqNcdEMU5/apslrGrTHGFAt/Chocgo++r6JQp5ygY7NyJHGWdaIqnt85pjX4PbNfLAvapyUO00qZP34fY61w4eZ9UMtleWEsmZKRtQPyJ8ODl46i/rfPuZlcJGpM9Nmy5mpGWuepqIEvF4a/t7pLVeCEDFSYXT+yaiygt6ynIK5f7TtEDhZpeUf/Q74WhMPJXm4yTU/hqOX4IW+50kWHNArGGZwUaXwzyG6M3Zd6UMModryGkLqS4H/MSE3ZA1Ylnms7BfWLEXhMWlaKi6HRV4nGRDLhxVSi9LSRi3LWKLhNIIQIDAQAB https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs/sig http://purl.org/nanopub/x/hasSignature u6dPlUuTUn1QedW6Fo7ljSYw2G4COewda0DpI0s95BWkF2vMzjoMKMokBVugNbLAF7WgBfWLNdwTqbnSBYf9xRted+aca4PBWgEF/7gswieTkJn0cmbIkRP85Fl+j9VWoAgVzb4c5Zu8KcI3cXo5W7LLfNx6yCW1fgamArf4JmksrxJIsftt9gcgHTJKFMt3XsI0WBTmVF3hcrJqj4tf/vAOIiuEnHkcMK2hOk4+0BAjf9MXAKG1b5ufatAxOHCQxqwe4dTz7da/ClVar+D0yMszjGQHpWfsEPcVvWz6hxmK2/0PueA/cKu4mrpSyACehPyNjjEwIqWSKn/XqMqzCg== https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs/sig http://purl.org/nanopub/x/hasSignatureTarget https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs https://w3id.org/np/RA_6CsM56gRUw5F1G7StJvgSiaBjwqwa4vg4dp4Pez6fs/sig http://purl.org/nanopub/x/signedBy https://neverblink.eu/ontologies/llm-kg/agent