https://w3id.org/np/RAL9lCutINBZpB6ZX96HCrdh0H7OCOK8uXfJkz9iBg2I8/Head https://w3id.org/np/RAL9lCutINBZpB6ZX96HCrdh0H7OCOK8uXfJkz9iBg2I8 http://www.nanopub.org/nschema#hasAssertion https://w3id.org/np/RAL9lCutINBZpB6ZX96HCrdh0H7OCOK8uXfJkz9iBg2I8/assertion https://w3id.org/np/RAL9lCutINBZpB6ZX96HCrdh0H7OCOK8uXfJkz9iBg2I8 http://www.nanopub.org/nschema#hasProvenance https://w3id.org/np/RAL9lCutINBZpB6ZX96HCrdh0H7OCOK8uXfJkz9iBg2I8/provenance https://w3id.org/np/RAL9lCutINBZpB6ZX96HCrdh0H7OCOK8uXfJkz9iBg2I8 http://www.nanopub.org/nschema#hasPublicationInfo https://w3id.org/np/RAL9lCutINBZpB6ZX96HCrdh0H7OCOK8uXfJkz9iBg2I8/pubinfo https://w3id.org/np/RAL9lCutINBZpB6ZX96HCrdh0H7OCOK8uXfJkz9iBg2I8 http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://www.nanopub.org/nschema#Nanopublication https://w3id.org/np/RAL9lCutINBZpB6ZX96HCrdh0H7OCOK8uXfJkz9iBg2I8/assertion https://doi.org/10.48550/arXiv.2405.19266 http://purl.org/dc/terms/title PediatricsGPT: Large Language Models as Chinese Medical Assistants for Pediatric Applications https://doi.org/10.48550/arXiv.2405.19266 http://purl.org/spar/cito/describes https://neverblink.eu/ontologies/llm-kg/methods#hybridInstructionPretrainingMechanism https://doi.org/10.48550/arXiv.2405.19266 http://purl.org/spar/cito/describes https://neverblink.eu/ontologies/llm-kg/methods#knowledgeEnhancedPromptForCptCorpus https://doi.org/10.48550/arXiv.2405.19266 http://purl.org/spar/cito/describes https://neverblink.eu/ontologies/llm-kg/methods#rolePlayingDrivenInstructionBuildingRule https://doi.org/10.48550/arXiv.2405.19266 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#baichuan2Chat https://doi.org/10.48550/arXiv.2405.19266 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#chatGPT https://doi.org/10.48550/arXiv.2405.19266 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#discMedLLM https://doi.org/10.48550/arXiv.2405.19266 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#gPT4 https://doi.org/10.48550/arXiv.2405.19266 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#huatuoGPT https://doi.org/10.48550/arXiv.2405.19266 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#huatuoGPTII https://doi.org/10.48550/arXiv.2405.19266 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#llama31 https://doi.org/10.48550/arXiv.2405.19266 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#meditron https://doi.org/10.48550/arXiv.2405.19266 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#rLHF https://doi.org/10.48550/arXiv.2405.19266 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#vanillaDPO https://doi.org/10.48550/arXiv.2405.19266 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#vanillaSingleLoRA https://doi.org/10.48550/arXiv.2405.19266 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#zhongjing https://doi.org/10.48550/arXiv.2405.19266 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#baichuan2Chat http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#baichuan2Chat http://www.w3.org/2000/01/rdf-schema#label Baichuan2-7B/13B (Chat) https://neverblink.eu/ontologies/llm-kg/methods#chatGPT http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#chatGPT http://www.w3.org/2000/01/rdf-schema#label ChatGPT https://neverblink.eu/ontologies/llm-kg/methods#discMedLLM http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#discMedLLM http://www.w3.org/2000/01/rdf-schema#label DISC-MedLLM (13B) https://neverblink.eu/ontologies/llm-kg/methods#gPT4 http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#gPT4 http://www.w3.org/2000/01/rdf-schema#label GPT-4 https://neverblink.eu/ontologies/llm-kg/methods#huatuoGPT http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#huatuoGPT http://www.w3.org/2000/01/rdf-schema#label HuatuoGPT (13B) https://neverblink.eu/ontologies/llm-kg/methods#huatuoGPTII http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#huatuoGPTII http://www.w3.org/2000/01/rdf-schema#label HuatuoGPT-II (13B) https://neverblink.eu/ontologies/llm-kg/methods#hybridInstructionPretrainingMechanism http://purl.org/dc/terms/subject https://neverblink.eu/ontologies/llm-kg/categories#KGEnhancedLLMPretraining https://neverblink.eu/ontologies/llm-kg/methods#hybridInstructionPretrainingMechanism http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#hybridInstructionPretrainingMechanism http://www.w3.org/2000/01/rdf-schema#comment This method is introduced during the Continuous Pre-training (CPT) phase of PediatricsGPT. It leverages data from PedCorpus (which incorporates knowledge graph resources) by assembling instruction data into completion forms and assimilating them into plain texts. This mechanism explicitly aims to bridge knowledge discrepancies and enhance the LLM's medical domain adaptation during pre-training. https://neverblink.eu/ontologies/llm-kg/methods#hybridInstructionPretrainingMechanism http://www.w3.org/2000/01/rdf-schema#label Hybrid Instruction Pre-training Mechanism https://neverblink.eu/ontologies/llm-kg/methods#hybridInstructionPretrainingMechanism https://neverblink.eu/ontologies/llm-kg/hasTopCategory https://neverblink.eu/ontologies/llm-kg/top-categories#KGEnhancedLLM https://neverblink.eu/ontologies/llm-kg/methods#knowledgeEnhancedPromptForCptCorpus http://purl.org/dc/terms/subject https://neverblink.eu/ontologies/llm-kg/categories#KGEnhancedLLMPretraining https://neverblink.eu/ontologies/llm-kg/methods#knowledgeEnhancedPromptForCptCorpus http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#knowledgeEnhancedPromptForCptCorpus http://www.w3.org/2000/01/rdf-schema#comment This method uses specific prompts to transform structured instruction data from the KG-inclusive PedCorpus dataset into comprehensive medical knowledge texts. These texts are integrated into the PedCorpus-CPT dataset. This process directly enriches the continuous pre-training corpus for the LLM, thereby improving its knowledge expression during pre-training. https://neverblink.eu/ontologies/llm-kg/methods#knowledgeEnhancedPromptForCptCorpus http://www.w3.org/2000/01/rdf-schema#label Knowledge-enhanced Prompt for CPT Corpus https://neverblink.eu/ontologies/llm-kg/methods#knowledgeEnhancedPromptForCptCorpus https://neverblink.eu/ontologies/llm-kg/hasTopCategory https://neverblink.eu/ontologies/llm-kg/top-categories#KGEnhancedLLM https://neverblink.eu/ontologies/llm-kg/methods#llama31 http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#llama31 http://www.w3.org/2000/01/rdf-schema#label Llama3.1-8B https://neverblink.eu/ontologies/llm-kg/methods#meditron http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#meditron http://www.w3.org/2000/01/rdf-schema#label Meditron-7B https://neverblink.eu/ontologies/llm-kg/methods#rLHF http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#rLHF http://www.w3.org/2000/01/rdf-schema#label RLHF https://neverblink.eu/ontologies/llm-kg/methods#rolePlayingDrivenInstructionBuildingRule http://purl.org/dc/terms/subject https://neverblink.eu/ontologies/llm-kg/categories#KGEnhancedLLMPretraining https://neverblink.eu/ontologies/llm-kg/methods#rolePlayingDrivenInstructionBuildingRule http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#rolePlayingDrivenInstructionBuildingRule http://www.w3.org/2000/01/rdf-schema#comment This rule describes a method within PedCorpus construction that uses GPT-4 API to generate specialized pediatric instructions. It explicitly extracts knowledge from pediatric textbooks, guidelines, and knowledge graphs to create high-quality, professional, and humanistic instruction data. This KG-enhanced data then feeds into the LLM's pre-training and fine-tuning phases, thereby enhancing the LLM's knowledge. https://neverblink.eu/ontologies/llm-kg/methods#rolePlayingDrivenInstructionBuildingRule http://www.w3.org/2000/01/rdf-schema#label Role-playing-driven Instruction Building Rule https://neverblink.eu/ontologies/llm-kg/methods#rolePlayingDrivenInstructionBuildingRule https://neverblink.eu/ontologies/llm-kg/hasTopCategory https://neverblink.eu/ontologies/llm-kg/top-categories#KGEnhancedLLM https://neverblink.eu/ontologies/llm-kg/methods#vanillaDPO http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#vanillaDPO http://www.w3.org/2000/01/rdf-schema#label Vanilla DPO https://neverblink.eu/ontologies/llm-kg/methods#vanillaSingleLoRA http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#vanillaSingleLoRA http://www.w3.org/2000/01/rdf-schema#label Vanilla single LoRA https://neverblink.eu/ontologies/llm-kg/methods#zhongjing http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#zhongjing http://www.w3.org/2000/01/rdf-schema#label Zhongjing (13B) https://w3id.org/np/RAL9lCutINBZpB6ZX96HCrdh0H7OCOK8uXfJkz9iBg2I8/provenance https://w3id.org/np/RAL9lCutINBZpB6ZX96HCrdh0H7OCOK8uXfJkz9iBg2I8/assertion http://www.w3.org/ns/prov#wasAttributedTo https://neverblink.eu/ontologies/llm-kg/agent https://w3id.org/np/RAL9lCutINBZpB6ZX96HCrdh0H7OCOK8uXfJkz9iBg2I8/assertion http://www.w3.org/ns/prov#wasDerivedFrom https://doi.org/10.48550/arXiv.2405.19266 https://w3id.org/np/RAL9lCutINBZpB6ZX96HCrdh0H7OCOK8uXfJkz9iBg2I8/pubinfo https://w3id.org/np/RAL9lCutINBZpB6ZX96HCrdh0H7OCOK8uXfJkz9iBg2I8 http://purl.org/dc/terms/created 2026-02-25T16:55:33.151Z https://w3id.org/np/RAL9lCutINBZpB6ZX96HCrdh0H7OCOK8uXfJkz9iBg2I8 http://purl.org/dc/terms/creator https://neverblink.eu/ontologies/llm-kg/agent https://w3id.org/np/RAL9lCutINBZpB6ZX96HCrdh0H7OCOK8uXfJkz9iBg2I8/sig http://purl.org/nanopub/x/hasAlgorithm RSA https://w3id.org/np/RAL9lCutINBZpB6ZX96HCrdh0H7OCOK8uXfJkz9iBg2I8/sig http://purl.org/nanopub/x/hasPublicKey MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAwNz2QK3SEifno78S7+48zUB0xpTex3mAzW73ZimHqNcdEMU5/apslrGrTHGFAt/Chocgo++r6JQp5ygY7NyJHGWdaIqnt85pjX4PbNfLAvapyUO00qZP34fY61w4eZ9UMtleWEsmZKRtQPyJ8ODl46i/rfPuZlcJGpM9Nmy5mpGWuepqIEvF4a/t7pLVeCEDFSYXT+yaiygt6ynIK5f7TtEDhZpeUf/Q74WhMPJXm4yTU/hqOX4IW+50kWHNArGGZwUaXwzyG6M3Zd6UMModryGkLqS4H/MSE3ZA1Ylnms7BfWLEXhMWlaKi6HRV4nGRDLhxVSi9LSRi3LWKLhNIIQIDAQAB https://w3id.org/np/RAL9lCutINBZpB6ZX96HCrdh0H7OCOK8uXfJkz9iBg2I8/sig http://purl.org/nanopub/x/hasSignature HGolHexCGe63LNvtwQc73gHBwNGU7tQ3tFAIilQEzlvWcmvms6kzSrou5fZSxrR3OqivbLdPYvO+PcMJ0nF/wVXD5mu5oN2IpE8HPLrw4wzjgxw+9iEgTNLeyKdhtUerNOC9Se72K+Dricd74q20DE2LMOpIF0ahe+2gsI27xN24EbjKpJYu+UP4e4uruhfltmPl8s8pg7I4tbb4Kha3u3M/FNarqBHjurYGZ/0a4QqnV455n2fpJ3m5eefSc7eBNaeIwfR95nHNU3xcxpZTmlHTEph1aaQb1HU7pyxKWSghrO3wjn3P4tlXGuy6Vn1mz0NUC/yxpF0Q/yOHWxB1qg== https://w3id.org/np/RAL9lCutINBZpB6ZX96HCrdh0H7OCOK8uXfJkz9iBg2I8/sig http://purl.org/nanopub/x/hasSignatureTarget https://w3id.org/np/RAL9lCutINBZpB6ZX96HCrdh0H7OCOK8uXfJkz9iBg2I8 https://w3id.org/np/RAL9lCutINBZpB6ZX96HCrdh0H7OCOK8uXfJkz9iBg2I8/sig http://purl.org/nanopub/x/signedBy https://neverblink.eu/ontologies/llm-kg/agent