https://w3id.org/np/RABN_pVgYslZsBu3ht_4e01O9aF_9fiHbSiz4qTIW2R9k/Head https://w3id.org/np/RABN_pVgYslZsBu3ht_4e01O9aF_9fiHbSiz4qTIW2R9k http://www.nanopub.org/nschema#hasAssertion https://w3id.org/np/RABN_pVgYslZsBu3ht_4e01O9aF_9fiHbSiz4qTIW2R9k/assertion https://w3id.org/np/RABN_pVgYslZsBu3ht_4e01O9aF_9fiHbSiz4qTIW2R9k http://www.nanopub.org/nschema#hasProvenance https://w3id.org/np/RABN_pVgYslZsBu3ht_4e01O9aF_9fiHbSiz4qTIW2R9k/provenance https://w3id.org/np/RABN_pVgYslZsBu3ht_4e01O9aF_9fiHbSiz4qTIW2R9k http://www.nanopub.org/nschema#hasPublicationInfo https://w3id.org/np/RABN_pVgYslZsBu3ht_4e01O9aF_9fiHbSiz4qTIW2R9k/pubinfo https://w3id.org/np/RABN_pVgYslZsBu3ht_4e01O9aF_9fiHbSiz4qTIW2R9k http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://www.nanopub.org/nschema#Nanopublication https://w3id.org/np/RABN_pVgYslZsBu3ht_4e01O9aF_9fiHbSiz4qTIW2R9k/assertion https://doi.org/10.48550/arXiv.2406.02110 http://purl.org/dc/terms/title UniOQA: A Unified Framework for Knowledge Graph Question Answering with Large Language Models https://doi.org/10.48550/arXiv.2406.02110 http://purl.org/spar/cito/describes https://neverblink.eu/ontologies/llm-kg/methods#DynamicDecisionAlgorithm https://doi.org/10.48550/arXiv.2406.02110 http://purl.org/spar/cito/describes https://neverblink.eu/ontologies/llm-kg/methods#EntityAndRelationReplacementAlgorithm https://doi.org/10.48550/arXiv.2406.02110 http://purl.org/spar/cito/describes https://neverblink.eu/ontologies/llm-kg/methods#GRAGProcess https://doi.org/10.48550/arXiv.2406.02110 http://purl.org/spar/cito/describes https://neverblink.eu/ontologies/llm-kg/methods#UniOQA https://doi.org/10.48550/arXiv.2406.02110 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#BinaryLogicCombinationRule https://doi.org/10.48550/arXiv.2406.02110 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#ChainOfThought https://doi.org/10.48550/arXiv.2406.02110 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#InContextLearning https://doi.org/10.48550/arXiv.2406.02110 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#RetrievalAugmentedGeneration https://doi.org/10.48550/arXiv.2406.02110 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#Seq2Seq https://doi.org/10.48550/arXiv.2406.02110 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#Seq2SeqWithAttention https://doi.org/10.48550/arXiv.2406.02110 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#Seq2SeqWithCopy https://doi.org/10.48550/arXiv.2406.02110 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#TextToCQL https://doi.org/10.48550/arXiv.2406.02110 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#BinaryLogicCombinationRule http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#BinaryLogicCombinationRule http://www.w3.org/2000/01/rdf-schema#label Binary Logic Combination Rule (BNA) https://neverblink.eu/ontologies/llm-kg/methods#ChainOfThought http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#ChainOfThought http://www.w3.org/2000/01/rdf-schema#label Chain-of-Thought (COT) https://neverblink.eu/ontologies/llm-kg/methods#DynamicDecisionAlgorithm http://purl.org/dc/terms/subject https://neverblink.eu/ontologies/llm-kg/categories#SynergizedReasoning https://neverblink.eu/ontologies/llm-kg/methods#DynamicDecisionAlgorithm http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#DynamicDecisionAlgorithm http://www.w3.org/2000/01/rdf-schema#comment This algorithm serves to optimally combine the answers obtained from the two parallel workflows of UniOQA (Translator and Searcher). By dynamically selecting the better answer based on an F1 score criterion, it represents a synergized approach to reasoning, integrating results derived from both LLM-generated queries and LLM-augmented KG retrieval to yield the final, most accurate answer. https://neverblink.eu/ontologies/llm-kg/methods#DynamicDecisionAlgorithm http://www.w3.org/2000/01/rdf-schema#label Dynamic Decision Algorithm (DDA) https://neverblink.eu/ontologies/llm-kg/methods#DynamicDecisionAlgorithm https://neverblink.eu/ontologies/llm-kg/hasTopCategory https://neverblink.eu/ontologies/llm-kg/top-categories#SynergizedLLMKG https://neverblink.eu/ontologies/llm-kg/methods#EntityAndRelationReplacementAlgorithm http://purl.org/dc/terms/subject https://neverblink.eu/ontologies/llm-kg/categories#LLMAugmentedKGQuestionAnswering https://neverblink.eu/ontologies/llm-kg/methods#EntityAndRelationReplacementAlgorithm http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#EntityAndRelationReplacementAlgorithm http://www.w3.org/2000/01/rdf-schema#comment This algorithm uses an LLM (Baichuan2-7B with a crafted instruction) to select and replace entities and relations in the generated Cypher Query Language (CQL) to align them with the knowledge graph. Its purpose is to enhance the executability and accuracy of the CQL, directly improving the performance of Knowledge Graph Question Answering by refining the query before execution. https://neverblink.eu/ontologies/llm-kg/methods#EntityAndRelationReplacementAlgorithm http://www.w3.org/2000/01/rdf-schema#label Entity and Relation Replacement (ERR) algorithm https://neverblink.eu/ontologies/llm-kg/methods#EntityAndRelationReplacementAlgorithm https://neverblink.eu/ontologies/llm-kg/hasTopCategory https://neverblink.eu/ontologies/llm-kg/top-categories#LLMAugmentedKG https://neverblink.eu/ontologies/llm-kg/methods#GRAGProcess http://purl.org/dc/terms/subject https://neverblink.eu/ontologies/llm-kg/categories#LLMAugmentedKGQuestionAnswering https://neverblink.eu/ontologies/llm-kg/methods#GRAGProcess http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#GRAGProcess http://www.w3.org/2000/01/rdf-schema#comment GRAG (Knowledge Graph Retrieval-Augmented Generation) is a process that employs an LLM, combined with traditional information retrieval from the knowledge graph (retrieving relevant subgraphs), to directly generate answers to natural language questions. This directly uses LLMs to improve the task of question answering over KGs. https://neverblink.eu/ontologies/llm-kg/methods#GRAGProcess http://www.w3.org/2000/01/rdf-schema#label GRAG Process https://neverblink.eu/ontologies/llm-kg/methods#GRAGProcess https://neverblink.eu/ontologies/llm-kg/hasTopCategory https://neverblink.eu/ontologies/llm-kg/top-categories#LLMAugmentedKG https://neverblink.eu/ontologies/llm-kg/methods#InContextLearning http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#InContextLearning http://www.w3.org/2000/01/rdf-schema#label In-Context Learning (ICL) https://neverblink.eu/ontologies/llm-kg/methods#RetrievalAugmentedGeneration http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#RetrievalAugmentedGeneration http://www.w3.org/2000/01/rdf-schema#label Retrieval-Augmented Generation (RAG) https://neverblink.eu/ontologies/llm-kg/methods#Seq2Seq http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#Seq2Seq http://www.w3.org/2000/01/rdf-schema#label Seq2Seq https://neverblink.eu/ontologies/llm-kg/methods#Seq2SeqWithAttention http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#Seq2SeqWithAttention http://www.w3.org/2000/01/rdf-schema#label Seq2Seq+Attention https://neverblink.eu/ontologies/llm-kg/methods#Seq2SeqWithCopy http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#Seq2SeqWithCopy http://www.w3.org/2000/01/rdf-schema#label Seq2Seq+Copy https://neverblink.eu/ontologies/llm-kg/methods#TextToCQL http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#TextToCQL http://www.w3.org/2000/01/rdf-schema#label Text-to-CQL https://neverblink.eu/ontologies/llm-kg/methods#UniOQA http://purl.org/dc/terms/subject https://neverblink.eu/ontologies/llm-kg/categories#SynergizedReasoning https://neverblink.eu/ontologies/llm-kg/methods#UniOQA http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#UniOQA http://www.w3.org/2000/01/rdf-schema#comment UniOQA is presented as a "unified framework" that integrates two parallel workflows (Translator for CQL generation and Searcher for direct retrieval) and a "dynamic decision algorithm" to synthesize their outputs. This explicit combination and optimization of answers from both LLM-derived queries and KG-based retrieval constitutes a synergized approach to reasoning for Knowledge Graph Question Answering. https://neverblink.eu/ontologies/llm-kg/methods#UniOQA http://www.w3.org/2000/01/rdf-schema#label UniOQA https://neverblink.eu/ontologies/llm-kg/methods#UniOQA https://neverblink.eu/ontologies/llm-kg/hasTopCategory https://neverblink.eu/ontologies/llm-kg/top-categories#SynergizedLLMKG https://w3id.org/np/RABN_pVgYslZsBu3ht_4e01O9aF_9fiHbSiz4qTIW2R9k/provenance https://w3id.org/np/RABN_pVgYslZsBu3ht_4e01O9aF_9fiHbSiz4qTIW2R9k/assertion http://www.w3.org/ns/prov#wasAttributedTo https://neverblink.eu/ontologies/llm-kg/agent https://w3id.org/np/RABN_pVgYslZsBu3ht_4e01O9aF_9fiHbSiz4qTIW2R9k/assertion http://www.w3.org/ns/prov#wasDerivedFrom https://doi.org/10.48550/arXiv.2406.02110 https://w3id.org/np/RABN_pVgYslZsBu3ht_4e01O9aF_9fiHbSiz4qTIW2R9k/pubinfo https://w3id.org/np/RABN_pVgYslZsBu3ht_4e01O9aF_9fiHbSiz4qTIW2R9k http://purl.org/dc/terms/created 2026-02-26T15:41:54.048Z https://w3id.org/np/RABN_pVgYslZsBu3ht_4e01O9aF_9fiHbSiz4qTIW2R9k http://purl.org/dc/terms/creator https://neverblink.eu/ontologies/llm-kg/agent https://w3id.org/np/RABN_pVgYslZsBu3ht_4e01O9aF_9fiHbSiz4qTIW2R9k http://purl.org/nanopub/x/hasNanopubType https://neverblink.eu/ontologies/llm-kg/PaperAssessmentResult https://w3id.org/np/RABN_pVgYslZsBu3ht_4e01O9aF_9fiHbSiz4qTIW2R9k http://www.w3.org/2000/01/rdf-schema#label LLM-KG assessment for paper 10.48550/arXiv.2406.02110 https://w3id.org/np/RABN_pVgYslZsBu3ht_4e01O9aF_9fiHbSiz4qTIW2R9k/sig http://purl.org/nanopub/x/hasAlgorithm RSA https://w3id.org/np/RABN_pVgYslZsBu3ht_4e01O9aF_9fiHbSiz4qTIW2R9k/sig http://purl.org/nanopub/x/hasPublicKey MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAwNz2QK3SEifno78S7+48zUB0xpTex3mAzW73ZimHqNcdEMU5/apslrGrTHGFAt/Chocgo++r6JQp5ygY7NyJHGWdaIqnt85pjX4PbNfLAvapyUO00qZP34fY61w4eZ9UMtleWEsmZKRtQPyJ8ODl46i/rfPuZlcJGpM9Nmy5mpGWuepqIEvF4a/t7pLVeCEDFSYXT+yaiygt6ynIK5f7TtEDhZpeUf/Q74WhMPJXm4yTU/hqOX4IW+50kWHNArGGZwUaXwzyG6M3Zd6UMModryGkLqS4H/MSE3ZA1Ylnms7BfWLEXhMWlaKi6HRV4nGRDLhxVSi9LSRi3LWKLhNIIQIDAQAB https://w3id.org/np/RABN_pVgYslZsBu3ht_4e01O9aF_9fiHbSiz4qTIW2R9k/sig http://purl.org/nanopub/x/hasSignature vZ1vFLfpcYOEOHuZcwmW5a7buHOtUSuG2xgJskMmSM6XIqQD49K2Y5+PAewLqaez4mV7uOgbZuZ0kILolBSbwyYb5iOGQIOpxgldJXy3/9K64RBuDozbAHqWenQQLq/zh0UmWCWoBIHrfd4M0hH7Ewjqqk3DUBNrQyKJSj+00wE3oQXzt2vjZ8xbu1mzyzxNgw8C7Ws+SxMn0GH1QZIuUHktIhpn16RXtIeJ2uETQrvSWGyCs675EcxJDSYROmUJrGWEhjMo2s3W988X48d8DQbj8p2RwbsNrpqEQ51dCft3k8OzByieLGuLsjYoQ4cOUBOq1bjeBFWEj+SCZ3P/AA== https://w3id.org/np/RABN_pVgYslZsBu3ht_4e01O9aF_9fiHbSiz4qTIW2R9k/sig http://purl.org/nanopub/x/hasSignatureTarget https://w3id.org/np/RABN_pVgYslZsBu3ht_4e01O9aF_9fiHbSiz4qTIW2R9k https://w3id.org/np/RABN_pVgYslZsBu3ht_4e01O9aF_9fiHbSiz4qTIW2R9k/sig http://purl.org/nanopub/x/signedBy https://neverblink.eu/ontologies/llm-kg/agent