@prefix this: . @prefix sub: . @prefix np: . @prefix dct: . @prefix xsd: . @prefix rdfs: . @prefix prov: . @prefix npx: . sub:Head { this: np:hasAssertion sub:assertion; np:hasProvenance sub:provenance; np:hasPublicationInfo sub:pubinfo; a np:Nanopublication . } sub:assertion { dct:title "MKG-Rank: Enhancing Large Language Models with Knowledge Graph for Multilingual Medical Question Answering"; , , , , , ; , , ; a prov:Entity . a ; rdfs:label "BM25" . dct:subject ; a ; rdfs: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."; rdfs:label "Caching Mechanism"; . dct:subject ; a ; rdfs: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."; rdfs:label "Declarative Conversion"; . dct:subject ; "https://anonymous.4open.science/r/MKG-Rank-6B72"^^xsd:anyURI; a ; rdfs: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."; rdfs:label "MKG-Rank"; . a ; rdfs:label "MedCPT Cross Encoder" . dct:subject ; a ; rdfs: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."; rdfs:label "Multi-Angle Ranking"; . dct:subject ; a ; rdfs: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."; rdfs:label "Self-Information Mining"; . a ; rdfs:label "UMLS-BERT embeddings" . dct:subject ; a ; rdfs: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."; rdfs:label "Word-level Translation Mechanism"; . } sub:provenance { sub:assertion prov:wasAttributedTo ; prov:wasDerivedFrom . } sub:pubinfo { this: dct:created "2026-02-26T15:55:27.464Z"^^xsd:dateTime; dct:creator ; npx:hasNanopubType ; rdfs:label "LLM-KG assessment for paper 10.48550/arXiv.2503.16131" . sub:sig npx:hasAlgorithm "RSA"; npx:hasPublicKey "MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAwNz2QK3SEifno78S7+48zUB0xpTex3mAzW73ZimHqNcdEMU5/apslrGrTHGFAt/Chocgo++r6JQp5ygY7NyJHGWdaIqnt85pjX4PbNfLAvapyUO00qZP34fY61w4eZ9UMtleWEsmZKRtQPyJ8ODl46i/rfPuZlcJGpM9Nmy5mpGWuepqIEvF4a/t7pLVeCEDFSYXT+yaiygt6ynIK5f7TtEDhZpeUf/Q74WhMPJXm4yTU/hqOX4IW+50kWHNArGGZwUaXwzyG6M3Zd6UMModryGkLqS4H/MSE3ZA1Ylnms7BfWLEXhMWlaKi6HRV4nGRDLhxVSi9LSRi3LWKLhNIIQIDAQAB"; npx:hasSignature "N2UbPmY5xFtgVOnItcOMYoJbF1sO6k2Ix2/gm5wQngPckyNYrDlQPa5oii1fbKkm3cToZsokZDhdYD7t8Ut/TFP2VR8PNODfRBaVkrKb3N+WrJAwHCLyA3DzkBxww7zqv2B0eYlwJjmwdSNAFR+DyBvpj9SboJL58MX4b0nm//u4g+EwPehDRmlaXafGrMZnML5CUY0U1FkmBe4LlqSHBM+NtooVpnS2/nz1KA4BK7GxrB7xejXB2MZOtfh/OMh3B1b9aJ64uB1wdlVuJhPEmGabeXFepE6RxUo0huyMuwHR8NtEjogX+ZkD4qiYCycN/KbOlYi/rESa6e94J1O3fw=="; npx:hasSignatureTarget this:; npx:signedBy . }