https://w3id.org/np/RApQFB3_XfMcKvx6FxeY0MufsIpv3ebHcOx4gni4tqfxA/Head https://w3id.org/np/RApQFB3_XfMcKvx6FxeY0MufsIpv3ebHcOx4gni4tqfxA http://www.nanopub.org/nschema#hasAssertion https://w3id.org/np/RApQFB3_XfMcKvx6FxeY0MufsIpv3ebHcOx4gni4tqfxA/assertion https://w3id.org/np/RApQFB3_XfMcKvx6FxeY0MufsIpv3ebHcOx4gni4tqfxA http://www.nanopub.org/nschema#hasProvenance https://w3id.org/np/RApQFB3_XfMcKvx6FxeY0MufsIpv3ebHcOx4gni4tqfxA/provenance https://w3id.org/np/RApQFB3_XfMcKvx6FxeY0MufsIpv3ebHcOx4gni4tqfxA http://www.nanopub.org/nschema#hasPublicationInfo https://w3id.org/np/RApQFB3_XfMcKvx6FxeY0MufsIpv3ebHcOx4gni4tqfxA/pubinfo https://w3id.org/np/RApQFB3_XfMcKvx6FxeY0MufsIpv3ebHcOx4gni4tqfxA http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://www.nanopub.org/nschema#Nanopublication https://w3id.org/np/RApQFB3_XfMcKvx6FxeY0MufsIpv3ebHcOx4gni4tqfxA/assertion https://doi.org/10.48550/arXiv.2601.19447 http://purl.org/dc/terms/title KG-CRAFT: Knowledge Graph-based Contrastive Reasoning with LLMs for Enhancing Automated Fact-checking https://doi.org/10.48550/arXiv.2601.19447 http://purl.org/spar/cito/describes https://neverblink.eu/ontologies/llm-kg/methods#kg-craft https://doi.org/10.48550/arXiv.2601.19447 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#co-gat-electra https://doi.org/10.48550/arXiv.2601.19447 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#cofced https://doi.org/10.48550/arXiv.2601.19447 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#corxfact https://doi.org/10.48550/arXiv.2601.19447 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#defend https://doi.org/10.48550/arXiv.2601.19447 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#factl-lama https://doi.org/10.48550/arXiv.2601.19447 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#factl-lama-know https://doi.org/10.48550/arXiv.2601.19447 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#fire https://doi.org/10.48550/arXiv.2601.19447 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#genfe https://doi.org/10.48550/arXiv.2601.19447 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#genfe-mt https://doi.org/10.48550/arXiv.2601.19447 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#graphcheck https://doi.org/10.48550/arXiv.2601.19447 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#graphfc https://doi.org/10.48550/arXiv.2601.19447 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#ika https://doi.org/10.48550/arXiv.2601.19447 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#l-defense https://doi.org/10.48550/arXiv.2601.19447 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#mla-roberta https://doi.org/10.48550/arXiv.2601.19447 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#multivers https://doi.org/10.48550/arXiv.2601.19447 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#pacar https://doi.org/10.48550/arXiv.2601.19447 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#programfc https://doi.org/10.48550/arXiv.2601.19447 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#sbert-fc https://doi.org/10.48550/arXiv.2601.19447 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#teller https://doi.org/10.48550/arXiv.2601.19447 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#co-gat-electra http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#co-gat-electra http://www.w3.org/2000/01/rdf-schema#comment CO-GAT (ELECTRA) is discussed as a competing method for claim verification that applies graph attention over scientific evidence, utilizing a pre-trained ELECTRA encoder. https://neverblink.eu/ontologies/llm-kg/methods#co-gat-electra http://www.w3.org/2000/01/rdf-schema#label CO-GAT (ELECTRA) https://neverblink.eu/ontologies/llm-kg/methods#cofced http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#cofced http://www.w3.org/2000/01/rdf-schema#comment CofCED is discussed as a traditional automated fact-checking (AFC) baseline that introduced a hierarchical encoder with cascaded evidence selectors to process reports from multiple sources for claim verification. https://neverblink.eu/ontologies/llm-kg/methods#cofced http://www.w3.org/2000/01/rdf-schema#label CofCED https://neverblink.eu/ontologies/llm-kg/methods#corxfact http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#corxfact http://www.w3.org/2000/01/rdf-schema#comment CorXFact is discussed as an LLM-based fact-checking approach that simulates human fact-checking principles by analyzing claim-evidence correlations. https://neverblink.eu/ontologies/llm-kg/methods#corxfact http://www.w3.org/2000/01/rdf-schema#label CorXFact https://neverblink.eu/ontologies/llm-kg/methods#defend http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#defend http://www.w3.org/2000/01/rdf-schema#comment dEFEND is discussed as a traditional automated fact-checking (AFC) baseline method that employs a sentence-comment co-attention network to jointly analyze news content and user comments for claim verification. https://neverblink.eu/ontologies/llm-kg/methods#defend http://www.w3.org/2000/01/rdf-schema#label dEFEND https://neverblink.eu/ontologies/llm-kg/methods#factl-lama http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#factl-lama http://www.w3.org/2000/01/rdf-schema#comment FactL-LaMA is discussed as a specialized LLM-based fact-checking method that combines instruction-following with external evidence retrieval, implemented as a Low-Rank Adaptation (LoRA) fine-tuned Llama 2 7B. https://neverblink.eu/ontologies/llm-kg/methods#factl-lama http://www.w3.org/2000/01/rdf-schema#label FactL-LaMA https://neverblink.eu/ontologies/llm-kg/methods#factl-lama-know http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#factl-lama-know http://www.w3.org/2000/01/rdf-schema#comment FactL-LaMA-Know is discussed as a specialized LLM-based fact-checking method that augments the FactL-LaMA model with external knowledge sources to improve fact-checking accuracy. https://neverblink.eu/ontologies/llm-kg/methods#factl-lama-know http://www.w3.org/2000/01/rdf-schema#label FactL-LaMA-Know https://neverblink.eu/ontologies/llm-kg/methods#fire http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#fire http://www.w3.org/2000/01/rdf-schema#comment FIRE is discussed as a recent LLM-based fact-checking approach that proposes an iterative verification method aiming to improve scalability and efficiency in assessing claims. https://neverblink.eu/ontologies/llm-kg/methods#fire http://www.w3.org/2000/01/rdf-schema#label FIRE https://neverblink.eu/ontologies/llm-kg/methods#genfe http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#genfe http://www.w3.org/2000/01/rdf-schema#comment GenFE is discussed as a traditional automated fact-checking (AFC) baseline that performs joint optimization of veracity prediction and explanation generation, showing improved classification and output quality. https://neverblink.eu/ontologies/llm-kg/methods#genfe http://www.w3.org/2000/01/rdf-schema#label GenFE https://neverblink.eu/ontologies/llm-kg/methods#genfe-mt http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#genfe-mt http://www.w3.org/2000/01/rdf-schema#comment GenFE-MT is discussed as a traditional automated fact-checking (AFC) baseline that performs joint optimization of veracity prediction and explanation generation, showing improved classification and output quality. https://neverblink.eu/ontologies/llm-kg/methods#genfe-mt http://www.w3.org/2000/01/rdf-schema#label GenFE-MT https://neverblink.eu/ontologies/llm-kg/methods#graphcheck http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#graphcheck http://www.w3.org/2000/01/rdf-schema#comment GraphCheck is discussed as a recent LLM-based verifier that incorporates lightweight graph signals and instruction-style prompting for fact-checking. https://neverblink.eu/ontologies/llm-kg/methods#graphcheck http://www.w3.org/2000/01/rdf-schema#label GraphCheck https://neverblink.eu/ontologies/llm-kg/methods#graphfc http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#graphfc http://www.w3.org/2000/01/rdf-schema#comment GraphFC is discussed as a competing method for claim verification that encodes the report structure with an explicit graph and graph reasoning components. https://neverblink.eu/ontologies/llm-kg/methods#graphfc http://www.w3.org/2000/01/rdf-schema#label GraphFC https://neverblink.eu/ontologies/llm-kg/methods#ika http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#ika http://www.w3.org/2000/01/rdf-schema#comment IKA is discussed as an LLM-based fact-checking framework that builds a graph of positive and negative examples from labelled data to enhance fact-checking and explanation capabilities. https://neverblink.eu/ontologies/llm-kg/methods#ika http://www.w3.org/2000/01/rdf-schema#label IKA https://neverblink.eu/ontologies/llm-kg/methods#kg-craft http://purl.org/dc/terms/subject https://neverblink.eu/ontologies/llm-kg/categories#KGEnhancedLLMInference https://neverblink.eu/ontologies/llm-kg/methods#kg-craft http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#kg-craft http://www.w3.org/2000/01/rdf-schema#comment KG-CRAFT is a novel method that enhances LLM performance in automated fact-checking. It leverages knowledge graphs to construct structured contrastive questions from claims and reports, which then guide an LLM to generate evidence-based summaries for veracity assessment during the inference stage. This process enables LLMs to access and reason with contextualized knowledge more effectively. https://neverblink.eu/ontologies/llm-kg/methods#kg-craft http://www.w3.org/2000/01/rdf-schema#label KG-CRAFT https://neverblink.eu/ontologies/llm-kg/methods#kg-craft https://neverblink.eu/ontologies/llm-kg/hasTopCategory https://neverblink.eu/ontologies/llm-kg/top-categories#KGEnhancedLLM https://neverblink.eu/ontologies/llm-kg/methods#l-defense http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#l-defense http://www.w3.org/2000/01/rdf-schema#comment L-Defense is discussed as a specialized LLM-based fact-checking framework that leverages the wisdom of crowds by partitioning evidence into competing narratives for robust claim verification using LLMs like Llama 2 7B and ChatGPT 3.5 Turbo. https://neverblink.eu/ontologies/llm-kg/methods#l-defense http://www.w3.org/2000/01/rdf-schema#label L-Defense https://neverblink.eu/ontologies/llm-kg/methods#mla-roberta http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#mla-roberta http://www.w3.org/2000/01/rdf-schema#comment MLA (RoBERTa) is discussed as a competing method for claim verification that uses a sequence inference model with self-attention at token and sentence levels, powered by a pre-trained RoBERTa encoder. https://neverblink.eu/ontologies/llm-kg/methods#mla-roberta http://www.w3.org/2000/01/rdf-schema#label MLA (RoBERTa) https://neverblink.eu/ontologies/llm-kg/methods#multivers http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#multivers http://www.w3.org/2000/01/rdf-schema#comment MULTIVERS is discussed as a competing method for claim verification that leverages a multi-task learning approach for scientific verification and rationale extraction from abstracts. https://neverblink.eu/ontologies/llm-kg/methods#multivers http://www.w3.org/2000/01/rdf-schema#label MULTIVERS https://neverblink.eu/ontologies/llm-kg/methods#pacar http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#pacar http://www.w3.org/2000/01/rdf-schema#comment PACAR is discussed as a competing prompting-based approach for fact verification that aggregates evidence with consistency-oriented reasoning using large language models. https://neverblink.eu/ontologies/llm-kg/methods#pacar http://www.w3.org/2000/01/rdf-schema#label PACAR https://neverblink.eu/ontologies/llm-kg/methods#programfc http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#programfc http://www.w3.org/2000/01/rdf-schema#comment ProgramFC is discussed as a competing method for claim verification that formulates fact verification as a programmatic pipeline with modular steps for evidence usage and decision-making. https://neverblink.eu/ontologies/llm-kg/methods#programfc http://www.w3.org/2000/01/rdf-schema#label ProgramFC https://neverblink.eu/ontologies/llm-kg/methods#sbert-fc 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-fc http://www.w3.org/2000/01/rdf-schema#comment SBERT-FC is discussed as a traditional automated fact-checking (AFC) baseline method that uses SBERT to encode claims and documents, performing verification via supervised classifiers and providing explainability analysis. https://neverblink.eu/ontologies/llm-kg/methods#sbert-fc http://www.w3.org/2000/01/rdf-schema#label SBERT-FC https://neverblink.eu/ontologies/llm-kg/methods#teller http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#teller http://www.w3.org/2000/01/rdf-schema#comment TELLER is discussed as an LLM-based fact-checking framework that is a dual-system approach integrating human expertise with LLM reasoning to emphasize trustworthiness. https://neverblink.eu/ontologies/llm-kg/methods#teller http://www.w3.org/2000/01/rdf-schema#label TELLER https://w3id.org/np/RApQFB3_XfMcKvx6FxeY0MufsIpv3ebHcOx4gni4tqfxA/provenance https://w3id.org/np/RApQFB3_XfMcKvx6FxeY0MufsIpv3ebHcOx4gni4tqfxA/assertion http://www.w3.org/ns/prov#wasAttributedTo https://neverblink.eu/ontologies/llm-kg/agent https://w3id.org/np/RApQFB3_XfMcKvx6FxeY0MufsIpv3ebHcOx4gni4tqfxA/assertion http://www.w3.org/ns/prov#wasDerivedFrom https://doi.org/10.48550/arXiv.2601.19447 https://w3id.org/np/RApQFB3_XfMcKvx6FxeY0MufsIpv3ebHcOx4gni4tqfxA/pubinfo https://w3id.org/np/RApQFB3_XfMcKvx6FxeY0MufsIpv3ebHcOx4gni4tqfxA http://purl.org/dc/terms/created 2026-03-13T16:08:16.428Z https://w3id.org/np/RApQFB3_XfMcKvx6FxeY0MufsIpv3ebHcOx4gni4tqfxA http://purl.org/dc/terms/creator https://neverblink.eu/ontologies/llm-kg/agent https://w3id.org/np/RApQFB3_XfMcKvx6FxeY0MufsIpv3ebHcOx4gni4tqfxA http://purl.org/nanopub/x/hasNanopubType https://neverblink.eu/ontologies/llm-kg/PaperAssessmentResult https://w3id.org/np/RApQFB3_XfMcKvx6FxeY0MufsIpv3ebHcOx4gni4tqfxA http://purl.org/nanopub/x/supersedes https://w3id.org/np/RAWAHIxoaUsGqS5tkJf2hWOoBuz5tOddbhuGDhfRGFdrY https://w3id.org/np/RApQFB3_XfMcKvx6FxeY0MufsIpv3ebHcOx4gni4tqfxA http://www.w3.org/2000/01/rdf-schema#label LLM-KG assessment for paper 10.48550/arXiv.2601.19447 https://w3id.org/np/RApQFB3_XfMcKvx6FxeY0MufsIpv3ebHcOx4gni4tqfxA/sig http://purl.org/nanopub/x/hasAlgorithm RSA https://w3id.org/np/RApQFB3_XfMcKvx6FxeY0MufsIpv3ebHcOx4gni4tqfxA/sig http://purl.org/nanopub/x/hasPublicKey MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAwNz2QK3SEifno78S7+48zUB0xpTex3mAzW73ZimHqNcdEMU5/apslrGrTHGFAt/Chocgo++r6JQp5ygY7NyJHGWdaIqnt85pjX4PbNfLAvapyUO00qZP34fY61w4eZ9UMtleWEsmZKRtQPyJ8ODl46i/rfPuZlcJGpM9Nmy5mpGWuepqIEvF4a/t7pLVeCEDFSYXT+yaiygt6ynIK5f7TtEDhZpeUf/Q74WhMPJXm4yTU/hqOX4IW+50kWHNArGGZwUaXwzyG6M3Zd6UMModryGkLqS4H/MSE3ZA1Ylnms7BfWLEXhMWlaKi6HRV4nGRDLhxVSi9LSRi3LWKLhNIIQIDAQAB https://w3id.org/np/RApQFB3_XfMcKvx6FxeY0MufsIpv3ebHcOx4gni4tqfxA/sig http://purl.org/nanopub/x/hasSignature Vd3waP8e4zJi2Pk1git+rh/78E7EK+nKm7KEAnnDs8XqfEGUbt2GyK54kfWA7dh0twJrike2REjpnCoHnLjoZsxyJMw1x+Nh2uUzvkMFHKz+d3Ul23abkTUlEeKEZZa/BMByBoRg33e7eBuNpdER+3eVNLV4GUFoVF1DT1WaHIWTCesshHTez4lyb1gewCYhOycAJMlFLoMbG5HXXmQy5bfuY7qf7rDn7JKK0/qEnR0e0UUpe9Azq0aBx9LtZe6WfhnSHtmdlnvYeqYUqUfxPhor4cMeqoMgW5/UUse1XCauu7Na/C5ms35GBjZRfrlGrSUt5bp2zZIrCi0wXYUg0A== https://w3id.org/np/RApQFB3_XfMcKvx6FxeY0MufsIpv3ebHcOx4gni4tqfxA/sig http://purl.org/nanopub/x/hasSignatureTarget https://w3id.org/np/RApQFB3_XfMcKvx6FxeY0MufsIpv3ebHcOx4gni4tqfxA https://w3id.org/np/RApQFB3_XfMcKvx6FxeY0MufsIpv3ebHcOx4gni4tqfxA/sig http://purl.org/nanopub/x/signedBy https://neverblink.eu/ontologies/llm-kg/agent