Nanopublication

ID

https://w3id.org/np/RAc58JpiapZ5zAyfUwsYdlqphJCRwdkrzCx-VY3IqaxOg
Formats

Content

@prefix this: <https://w3id.org/np/RAc58JpiapZ5zAyfUwsYdlqphJCRwdkrzCx-VY3IqaxOg> .
@prefix sub: <https://w3id.org/np/RAc58JpiapZ5zAyfUwsYdlqphJCRwdkrzCx-VY3IqaxOg/> .
@prefix np: <http://www.nanopub.org/nschema#> .
@prefix dct: <http://purl.org/dc/terms/> .
@prefix xsd: <http://www.w3.org/2001/XMLSchema#> .
@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .
@prefix prov: <http://www.w3.org/ns/prov#> .
@prefix npx: <http://purl.org/nanopub/x/> .

sub:Head {
  this: a np:Nanopublication;
    np:hasAssertion sub:assertion;
    np:hasProvenance sub:provenance;
    np:hasPublicationInfo sub:pubinfo .
}

sub:assertion {
  <https://doi.org/10.48550/arXiv.2406.03746> a prov:Entity;
    dct:title "Efficient Knowledge Infusion via KG-LLM Alignment";
    <http://purl.org/spar/cito/describes> <https://neverblink.eu/ontologies/llm-kg/methods#EfficientLlmKgConstruction>,
      <https://neverblink.eu/ontologies/llm-kg/methods#EnhancedLlmWithKnowledgePrelearningAndFeedback>;
    <http://purl.org/spar/cito/discusses> <https://neverblink.eu/ontologies/llm-kg/methods#AutoKg>,
      <https://neverblink.eu/ontologies/llm-kg/methods#ChainRag>, <https://neverblink.eu/ontologies/llm-kg/methods#ContinualPretraining>,
      <https://neverblink.eu/ontologies/llm-kg/methods#Gap>, <https://neverblink.eu/ontologies/llm-kg/methods#LoraBasedSft>,
      <https://neverblink.eu/ontologies/llm-kg/methods#Pive>, <https://neverblink.eu/ontologies/llm-kg/methods#Rag>,
      <https://neverblink.eu/ontologies/llm-kg/methods#WebBrain> .
  
  <https://neverblink.eu/ontologies/llm-kg/methods#AutoKg> a <http://purl.org/spar/fabio/Workflow>;
    rdfs:label "AutoKG" .
  
  <https://neverblink.eu/ontologies/llm-kg/methods#ChainRag> a <http://purl.org/spar/fabio/Workflow>;
    rdfs:label "ChainRAG" .
  
  <https://neverblink.eu/ontologies/llm-kg/methods#ContinualPretraining> a <http://purl.org/spar/fabio/Workflow>;
    rdfs:label "Continual pre-training" .
  
  <https://neverblink.eu/ontologies/llm-kg/methods#EfficientLlmKgConstruction> a <http://purl.org/spar/fabio/Workflow>;
    dct:subject <https://neverblink.eu/ontologies/llm-kg/categories#LLMAugmentedKGConstruction>;
    rdfs:comment "This method describes an LLM-based workflow for efficiently constructing domain-specific knowledge graphs. It involves fine-tuning an LLM for knowledge triples extraction from unsupervised corpora, followed by post-processing for error removal and entity resolution. This directly addresses the problem of knowledge mismatch by building a tailored KG.";
    rdfs:label "Efficient construction of domain KGs";
    <https://neverblink.eu/ontologies/llm-kg/hasTopCategory> <https://neverblink.eu/ontologies/llm-kg/top-categories#LLMAugmentedKG> .
  
  <https://neverblink.eu/ontologies/llm-kg/methods#EnhancedLlmWithKnowledgePrelearningAndFeedback>
    a <http://purl.org/spar/fabio/Workflow>;
    dct:subject <https://neverblink.eu/ontologies/llm-kg/categories#SynergizedReasoning>;
    rdfs:comment "ELPF is a modular, three-stage KG-LLM alignment framework designed to enhance LLM's capability to utilize KG information and reduce hallucinations. It includes K-LoRA for pre-learning KG infusion and domain linguistic style, supervised fine-tuning with KG retrieval, and Alignment with Knowledge Graph Feedback (AKGF) where KGs act as automated evaluators for DPO-based fine-tuning. The framework synergizes LLMs and KGs to improve reasoning and factual correctness.";
    rdfs:label "Enhanced LLM with Knowledge Pre-learning and Feedback (ELPF)";
    <https://neverblink.eu/ontologies/llm-kg/hasTopCategory> <https://neverblink.eu/ontologies/llm-kg/top-categories#SynergizedLLMKG> .
  
  <https://neverblink.eu/ontologies/llm-kg/methods#Gap> a <http://purl.org/spar/fabio/Workflow>;
    rdfs:label "GAP" .
  
  <https://neverblink.eu/ontologies/llm-kg/methods#LoraBasedSft> a <http://purl.org/spar/fabio/Workflow>;
    rdfs:label "LoRA-based SFT" .
  
  <https://neverblink.eu/ontologies/llm-kg/methods#Pive> a <http://purl.org/spar/fabio/Workflow>;
    rdfs:label "PiVe" .
  
  <https://neverblink.eu/ontologies/llm-kg/methods#Rag> a <http://purl.org/spar/fabio/Workflow>;
    rdfs:label "RAG" .
  
  <https://neverblink.eu/ontologies/llm-kg/methods#WebBrain> a <http://purl.org/spar/fabio/Workflow>;
    rdfs:label "WebBrain" .
}

sub:provenance {
  sub:assertion prov:wasAttributedTo <https://neverblink.eu/ontologies/llm-kg/agent>;
    prov:wasDerivedFrom <https://doi.org/10.48550/arXiv.2406.03746> .
}

sub:pubinfo {
  this: dct:created "2026-02-26T15:55:58.094Z"^^xsd:dateTime;
    dct:creator <https://neverblink.eu/ontologies/llm-kg/agent>;
    npx:hasNanopubType <https://neverblink.eu/ontologies/llm-kg/PaperAssessmentResult>;
    rdfs:label "LLM-KG assessment for paper 10.48550/arXiv.2406.03746" .
  
  sub:sig npx:hasAlgorithm "RSA";
    npx:hasPublicKey "MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAwNz2QK3SEifno78S7+48zUB0xpTex3mAzW73ZimHqNcdEMU5/apslrGrTHGFAt/Chocgo++r6JQp5ygY7NyJHGWdaIqnt85pjX4PbNfLAvapyUO00qZP34fY61w4eZ9UMtleWEsmZKRtQPyJ8ODl46i/rfPuZlcJGpM9Nmy5mpGWuepqIEvF4a/t7pLVeCEDFSYXT+yaiygt6ynIK5f7TtEDhZpeUf/Q74WhMPJXm4yTU/hqOX4IW+50kWHNArGGZwUaXwzyG6M3Zd6UMModryGkLqS4H/MSE3ZA1Ylnms7BfWLEXhMWlaKi6HRV4nGRDLhxVSi9LSRi3LWKLhNIIQIDAQAB";
    npx:hasSignature "nyZ/k6RXuZhNLuRq0jPEnKJt5FWlDcsXgcCxcF0U7n4Jn8Z8abYLKW/hIzYba5e2Qq5PcWMAn/9uKwgjvnZFJdDlBx0IziZvfNYG/xnfE41QV4jKHrsNktPtt82DpNBrDljJ3SFHO4yIAXUPu4ZVWOzP2eaAfZnPFdey/H2Ku3s18DvLs9YBz9dvcKwuOGbpLGsIeBqVB4XGM0S4FIvYquyIfBzNrJnliTtHC4bKvciQcyzOSOPpSSquRux5/Wds2RhC1h4PGnIcpHsR6iaV3/u1cI240WnhBFz1GmPF5y1HiATKvbFglTKHyFltssR5oByCLWCEYf/Kox1/ZghAWQ==";
    npx:hasSignatureTarget this:;
    npx:signedBy <https://neverblink.eu/ontologies/llm-kg/agent> .
}