https://w3id.org/np/RA9UhFFrfgd2Uu4NfZsny8CxPYI-w5YdYgs8B41DKAIs0/Head https://w3id.org/np/RA9UhFFrfgd2Uu4NfZsny8CxPYI-w5YdYgs8B41DKAIs0 http://www.nanopub.org/nschema#hasAssertion https://w3id.org/np/RA9UhFFrfgd2Uu4NfZsny8CxPYI-w5YdYgs8B41DKAIs0/assertion https://w3id.org/np/RA9UhFFrfgd2Uu4NfZsny8CxPYI-w5YdYgs8B41DKAIs0 http://www.nanopub.org/nschema#hasProvenance https://w3id.org/np/RA9UhFFrfgd2Uu4NfZsny8CxPYI-w5YdYgs8B41DKAIs0/provenance https://w3id.org/np/RA9UhFFrfgd2Uu4NfZsny8CxPYI-w5YdYgs8B41DKAIs0 http://www.nanopub.org/nschema#hasPublicationInfo https://w3id.org/np/RA9UhFFrfgd2Uu4NfZsny8CxPYI-w5YdYgs8B41DKAIs0/pubinfo https://w3id.org/np/RA9UhFFrfgd2Uu4NfZsny8CxPYI-w5YdYgs8B41DKAIs0 http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://www.nanopub.org/nschema#Nanopublication https://w3id.org/np/RA9UhFFrfgd2Uu4NfZsny8CxPYI-w5YdYgs8B41DKAIs0/assertion https://doi.org/10.48550/arXiv.2503.16131 http://purl.org/dc/terms/title MKG-Rank: Enhancing Large Language Models with Knowledge Graph for Multilingual Medical Question Answering https://doi.org/10.48550/arXiv.2503.16131 http://purl.org/spar/cito/describes https://neverblink.eu/ontologies/llm-kg/methods#CachingMechanism https://doi.org/10.48550/arXiv.2503.16131 http://purl.org/spar/cito/describes https://neverblink.eu/ontologies/llm-kg/methods#DeclarativeConversion https://doi.org/10.48550/arXiv.2503.16131 http://purl.org/spar/cito/describes https://neverblink.eu/ontologies/llm-kg/methods#MKGRank https://doi.org/10.48550/arXiv.2503.16131 http://purl.org/spar/cito/describes https://neverblink.eu/ontologies/llm-kg/methods#MultiAngleRanking https://doi.org/10.48550/arXiv.2503.16131 http://purl.org/spar/cito/describes https://neverblink.eu/ontologies/llm-kg/methods#SelfInformationMining https://doi.org/10.48550/arXiv.2503.16131 http://purl.org/spar/cito/describes https://neverblink.eu/ontologies/llm-kg/methods#WordLevelTranslationMechanism https://doi.org/10.48550/arXiv.2503.16131 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#BM25 https://doi.org/10.48550/arXiv.2503.16131 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#MedCPTCrossEncoder https://doi.org/10.48550/arXiv.2503.16131 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#UMLSBertEmbeddings https://doi.org/10.48550/arXiv.2503.16131 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#BM25 http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#BM25 http://www.w3.org/2000/01/rdf-schema#label BM25 https://neverblink.eu/ontologies/llm-kg/methods#CachingMechanism http://purl.org/dc/terms/subject https://neverblink.eu/ontologies/llm-kg/categories#KGEnhancedLLMInference https://neverblink.eu/ontologies/llm-kg/methods#CachingMechanism http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#CachingMechanism http://www.w3.org/2000/01/rdf-schema#comment This mechanism optimizes the retrieval of external medical KGs by storing previously retrieved KGs in a local knowledge base. It significantly reduces retrieval times during LLM inference, directly contributing to the efficiency of the overall KG-enhanced LLM system. https://neverblink.eu/ontologies/llm-kg/methods#CachingMechanism http://www.w3.org/2000/01/rdf-schema#label Caching Mechanism https://neverblink.eu/ontologies/llm-kg/methods#CachingMechanism https://neverblink.eu/ontologies/llm-kg/hasTopCategory https://neverblink.eu/ontologies/llm-kg/top-categories#KGEnhancedLLM https://neverblink.eu/ontologies/llm-kg/methods#DeclarativeConversion http://purl.org/dc/terms/subject https://neverblink.eu/ontologies/llm-kg/categories#KGEnhancedLLMInference https://neverblink.eu/ontologies/llm-kg/methods#DeclarativeConversion http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#DeclarativeConversion http://www.w3.org/2000/01/rdf-schema#comment This mechanism converts raw medical KG triplets into LLM-digestible declarative sentences. It allows the LLM to better integrate and reason with external knowledge during inference, improving its ability to utilize the provided medical facts. https://neverblink.eu/ontologies/llm-kg/methods#DeclarativeConversion http://www.w3.org/2000/01/rdf-schema#label Declarative Conversion https://neverblink.eu/ontologies/llm-kg/methods#DeclarativeConversion https://neverblink.eu/ontologies/llm-kg/hasTopCategory https://neverblink.eu/ontologies/llm-kg/top-categories#KGEnhancedLLM https://neverblink.eu/ontologies/llm-kg/methods#MKGRank http://purl.org/dc/terms/subject https://neverblink.eu/ontologies/llm-kg/categories#KGEnhancedLLMInference https://neverblink.eu/ontologies/llm-kg/methods#MKGRank http://purl.org/spar/fabio/hasURL https://anonymous.4open.science/r/MKG-Rank-6B72 https://neverblink.eu/ontologies/llm-kg/methods#MKGRank http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#MKGRank http://www.w3.org/2000/01/rdf-schema#comment This framework enhances English-centric LLMs to perform multilingual medical QA by integrating comprehensive external medical knowledge graphs during the inference stage. It bridges language gaps and provides relevant, up-to-date knowledge to LLMs for better reasoning. https://neverblink.eu/ontologies/llm-kg/methods#MKGRank http://www.w3.org/2000/01/rdf-schema#label MKG-Rank https://neverblink.eu/ontologies/llm-kg/methods#MKGRank https://neverblink.eu/ontologies/llm-kg/hasTopCategory https://neverblink.eu/ontologies/llm-kg/top-categories#KGEnhancedLLM https://neverblink.eu/ontologies/llm-kg/methods#MedCPTCrossEncoder http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#MedCPTCrossEncoder http://www.w3.org/2000/01/rdf-schema#label MedCPT Cross Encoder https://neverblink.eu/ontologies/llm-kg/methods#MultiAngleRanking http://purl.org/dc/terms/subject https://neverblink.eu/ontologies/llm-kg/categories#KGEnhancedLLMInference https://neverblink.eu/ontologies/llm-kg/methods#MultiAngleRanking http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#MultiAngleRanking http://www.w3.org/2000/01/rdf-schema#comment This strategy selects the most relevant medical triplets from retrieved KGs by ranking them based on similarity with the question (using UMLS-BERT embeddings) and further filtering with a MedCPT Cross Encoder. It ensures the LLM receives high-quality, pertinent information for accurate inference. https://neverblink.eu/ontologies/llm-kg/methods#MultiAngleRanking http://www.w3.org/2000/01/rdf-schema#label Multi-Angle Ranking https://neverblink.eu/ontologies/llm-kg/methods#MultiAngleRanking https://neverblink.eu/ontologies/llm-kg/hasTopCategory https://neverblink.eu/ontologies/llm-kg/top-categories#KGEnhancedLLM https://neverblink.eu/ontologies/llm-kg/methods#SelfInformationMining http://purl.org/dc/terms/subject https://neverblink.eu/ontologies/llm-kg/categories#KGEnhancedLLMInference https://neverblink.eu/ontologies/llm-kg/methods#SelfInformationMining http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#SelfInformationMining http://www.w3.org/2000/01/rdf-schema#comment When external KG retrieval is ineffective, this method employs the BM25 algorithm to extract relevant world knowledge from the LLM's own internal representations. It acts as a fallback strategy to ensure the LLM consistently has background information for medical QA, enhancing its robustness during inference. https://neverblink.eu/ontologies/llm-kg/methods#SelfInformationMining http://www.w3.org/2000/01/rdf-schema#label Self-Information Mining https://neverblink.eu/ontologies/llm-kg/methods#SelfInformationMining https://neverblink.eu/ontologies/llm-kg/hasTopCategory https://neverblink.eu/ontologies/llm-kg/top-categories#KGEnhancedLLM https://neverblink.eu/ontologies/llm-kg/methods#UMLSBertEmbeddings http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#UMLSBertEmbeddings http://www.w3.org/2000/01/rdf-schema#label UMLS-BERT embeddings https://neverblink.eu/ontologies/llm-kg/methods#WordLevelTranslationMechanism http://purl.org/dc/terms/subject https://neverblink.eu/ontologies/llm-kg/categories#KGEnhancedLLMInference https://neverblink.eu/ontologies/llm-kg/methods#WordLevelTranslationMechanism http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#WordLevelTranslationMechanism http://www.w3.org/2000/01/rdf-schema#comment This mechanism, part of MKG-Rank, extracts medical entities from multilingual questions and options using an LLM, then translates them into English. This enables the LLM to leverage English-centric KGs for multilingual QA, enhancing its performance during inference. https://neverblink.eu/ontologies/llm-kg/methods#WordLevelTranslationMechanism http://www.w3.org/2000/01/rdf-schema#label Word-level Translation Mechanism https://neverblink.eu/ontologies/llm-kg/methods#WordLevelTranslationMechanism https://neverblink.eu/ontologies/llm-kg/hasTopCategory https://neverblink.eu/ontologies/llm-kg/top-categories#KGEnhancedLLM https://w3id.org/np/RA9UhFFrfgd2Uu4NfZsny8CxPYI-w5YdYgs8B41DKAIs0/provenance https://w3id.org/np/RA9UhFFrfgd2Uu4NfZsny8CxPYI-w5YdYgs8B41DKAIs0/assertion http://www.w3.org/ns/prov#wasAttributedTo https://neverblink.eu/ontologies/llm-kg/agent https://w3id.org/np/RA9UhFFrfgd2Uu4NfZsny8CxPYI-w5YdYgs8B41DKAIs0/assertion http://www.w3.org/ns/prov#wasDerivedFrom https://doi.org/10.48550/arXiv.2503.16131 https://w3id.org/np/RA9UhFFrfgd2Uu4NfZsny8CxPYI-w5YdYgs8B41DKAIs0/pubinfo https://w3id.org/np/RA9UhFFrfgd2Uu4NfZsny8CxPYI-w5YdYgs8B41DKAIs0 http://purl.org/dc/terms/created 2026-02-26T15:55:27.464Z https://w3id.org/np/RA9UhFFrfgd2Uu4NfZsny8CxPYI-w5YdYgs8B41DKAIs0 http://purl.org/dc/terms/creator https://neverblink.eu/ontologies/llm-kg/agent https://w3id.org/np/RA9UhFFrfgd2Uu4NfZsny8CxPYI-w5YdYgs8B41DKAIs0 http://purl.org/nanopub/x/hasNanopubType https://neverblink.eu/ontologies/llm-kg/PaperAssessmentResult https://w3id.org/np/RA9UhFFrfgd2Uu4NfZsny8CxPYI-w5YdYgs8B41DKAIs0 http://www.w3.org/2000/01/rdf-schema#label LLM-KG assessment for paper 10.48550/arXiv.2503.16131 https://w3id.org/np/RA9UhFFrfgd2Uu4NfZsny8CxPYI-w5YdYgs8B41DKAIs0/sig http://purl.org/nanopub/x/hasAlgorithm RSA https://w3id.org/np/RA9UhFFrfgd2Uu4NfZsny8CxPYI-w5YdYgs8B41DKAIs0/sig http://purl.org/nanopub/x/hasPublicKey MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAwNz2QK3SEifno78S7+48zUB0xpTex3mAzW73ZimHqNcdEMU5/apslrGrTHGFAt/Chocgo++r6JQp5ygY7NyJHGWdaIqnt85pjX4PbNfLAvapyUO00qZP34fY61w4eZ9UMtleWEsmZKRtQPyJ8ODl46i/rfPuZlcJGpM9Nmy5mpGWuepqIEvF4a/t7pLVeCEDFSYXT+yaiygt6ynIK5f7TtEDhZpeUf/Q74WhMPJXm4yTU/hqOX4IW+50kWHNArGGZwUaXwzyG6M3Zd6UMModryGkLqS4H/MSE3ZA1Ylnms7BfWLEXhMWlaKi6HRV4nGRDLhxVSi9LSRi3LWKLhNIIQIDAQAB https://w3id.org/np/RA9UhFFrfgd2Uu4NfZsny8CxPYI-w5YdYgs8B41DKAIs0/sig http://purl.org/nanopub/x/hasSignature N2UbPmY5xFtgVOnItcOMYoJbF1sO6k2Ix2/gm5wQngPckyNYrDlQPa5oii1fbKkm3cToZsokZDhdYD7t8Ut/TFP2VR8PNODfRBaVkrKb3N+WrJAwHCLyA3DzkBxww7zqv2B0eYlwJjmwdSNAFR+DyBvpj9SboJL58MX4b0nm//u4g+EwPehDRmlaXafGrMZnML5CUY0U1FkmBe4LlqSHBM+NtooVpnS2/nz1KA4BK7GxrB7xejXB2MZOtfh/OMh3B1b9aJ64uB1wdlVuJhPEmGabeXFepE6RxUo0huyMuwHR8NtEjogX+ZkD4qiYCycN/KbOlYi/rESa6e94J1O3fw== https://w3id.org/np/RA9UhFFrfgd2Uu4NfZsny8CxPYI-w5YdYgs8B41DKAIs0/sig http://purl.org/nanopub/x/hasSignatureTarget https://w3id.org/np/RA9UhFFrfgd2Uu4NfZsny8CxPYI-w5YdYgs8B41DKAIs0 https://w3id.org/np/RA9UhFFrfgd2Uu4NfZsny8CxPYI-w5YdYgs8B41DKAIs0/sig http://purl.org/nanopub/x/signedBy https://neverblink.eu/ontologies/llm-kg/agent