https://w3id.org/np/RA3CyIg9XrQadn61m1lbmo8fh0F46iq4DUinlajefw74k/Head https://w3id.org/np/RA3CyIg9XrQadn61m1lbmo8fh0F46iq4DUinlajefw74k http://www.nanopub.org/nschema#hasAssertion https://w3id.org/np/RA3CyIg9XrQadn61m1lbmo8fh0F46iq4DUinlajefw74k/assertion https://w3id.org/np/RA3CyIg9XrQadn61m1lbmo8fh0F46iq4DUinlajefw74k http://www.nanopub.org/nschema#hasProvenance https://w3id.org/np/RA3CyIg9XrQadn61m1lbmo8fh0F46iq4DUinlajefw74k/provenance https://w3id.org/np/RA3CyIg9XrQadn61m1lbmo8fh0F46iq4DUinlajefw74k http://www.nanopub.org/nschema#hasPublicationInfo https://w3id.org/np/RA3CyIg9XrQadn61m1lbmo8fh0F46iq4DUinlajefw74k/pubinfo https://w3id.org/np/RA3CyIg9XrQadn61m1lbmo8fh0F46iq4DUinlajefw74k http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://www.nanopub.org/nschema#Nanopublication https://w3id.org/np/RA3CyIg9XrQadn61m1lbmo8fh0F46iq4DUinlajefw74k/assertion https://doi.org/10.48550/arXiv.2404.14741 http://purl.org/dc/terms/title Generate-on-Graph: Treat LLM as both Agent and KG for Incomplete Knowledge Graph Question Answering https://doi.org/10.48550/arXiv.2404.14741 http://purl.org/spar/cito/describes https://neverblink.eu/ontologies/llm-kg/methods#GenerateOnGraph https://doi.org/10.48550/arXiv.2404.14741 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#ChainOfThoughtPrompting https://doi.org/10.48550/arXiv.2404.14741 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#ChatKBQA https://doi.org/10.48550/arXiv.2404.14741 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#DecomP https://doi.org/10.48550/arXiv.2404.14741 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#GAG https://doi.org/10.48550/arXiv.2404.14741 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#KBBinder https://doi.org/10.48550/arXiv.2404.14741 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#ReAct https://doi.org/10.48550/arXiv.2404.14741 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#RoG https://doi.org/10.48550/arXiv.2404.14741 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#SelfConsistency https://doi.org/10.48550/arXiv.2404.14741 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#StandardPrompting https://doi.org/10.48550/arXiv.2404.14741 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#StructGPT https://doi.org/10.48550/arXiv.2404.14741 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#ToG https://doi.org/10.48550/arXiv.2404.14741 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#ChainOfThoughtPrompting http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#ChainOfThoughtPrompting http://www.w3.org/2000/01/rdf-schema#comment This method is used as a baseline for comparison. It aims to elicit complex reasoning from LLMs by encouraging them to generate intermediate reasoning steps, providing a stronger LLM-only baseline than standard prompting. https://neverblink.eu/ontologies/llm-kg/methods#ChainOfThoughtPrompting http://www.w3.org/2000/01/rdf-schema#label Chain-of-Thought (CoT) prompting https://neverblink.eu/ontologies/llm-kg/methods#ChatKBQA http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#ChatKBQA http://www.w3.org/2000/01/rdf-schema#comment This is a semantic parsing (SP) method for KGQA, used as a baseline. Similar to KB-BINDER, it converts natural language questions into executable queries for KGs, and its limitations under incomplete KGs are highlighted. https://neverblink.eu/ontologies/llm-kg/methods#ChatKBQA http://www.w3.org/2000/01/rdf-schema#label ChatKBQA https://neverblink.eu/ontologies/llm-kg/methods#DecomP http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#DecomP http://www.w3.org/2000/01/rdf-schema#comment This method is cited as a motivation for GoG's approach to problem decomposition. De-comP solves complex tasks by breaking them down into simpler sub-tasks, contributing to the structured reasoning in GoG. https://neverblink.eu/ontologies/llm-kg/methods#DecomP http://www.w3.org/2000/01/rdf-schema#label De-comP https://neverblink.eu/ontologies/llm-kg/methods#GAG http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#GAG http://www.w3.org/2000/01/rdf-schema#comment This method is mentioned as being similar to GoG, particularly in its utilization of the knowledge modeling ability of Large Language Models. It serves as a point of reference for existing techniques that leverage LLMs for knowledge tasks. https://neverblink.eu/ontologies/llm-kg/methods#GAG http://www.w3.org/2000/01/rdf-schema#label GAG https://neverblink.eu/ontologies/llm-kg/methods#GenerateOnGraph http://purl.org/dc/terms/subject https://neverblink.eu/ontologies/llm-kg/categories#SynergizedReasoning https://neverblink.eu/ontologies/llm-kg/methods#GenerateOnGraph http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#GenerateOnGraph http://www.w3.org/2000/01/rdf-schema#comment Generate-on-Graph (GoG) is a training-free method designed for Incomplete Knowledge Graph Question Answering (IKGQA). It uses a Thinking-Searching-Generating framework where the LLM acts as both an agent to explore KGs (Searching) and a KG to generate new factual triples (Generating) when knowledge is missing. This process represents a synergistic reasoning approach, dynamically combining LLM's internal knowledge and external KG facts. https://neverblink.eu/ontologies/llm-kg/methods#GenerateOnGraph http://www.w3.org/2000/01/rdf-schema#label Generate-on-Graph https://neverblink.eu/ontologies/llm-kg/methods#GenerateOnGraph https://neverblink.eu/ontologies/llm-kg/hasTopCategory https://neverblink.eu/ontologies/llm-kg/top-categories#SynergizedLLMKG https://neverblink.eu/ontologies/llm-kg/methods#KBBinder http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#KBBinder http://www.w3.org/2000/01/rdf-schema#comment This is a semantic parsing (SP) method for KGQA, used as a baseline. It transforms natural language questions into structured queries (e.g., SPARQL) which are then executed on the KG. Its performance is evaluated especially under the incomplete KG scenario. https://neverblink.eu/ontologies/llm-kg/methods#KBBinder http://www.w3.org/2000/01/rdf-schema#label KB-BINDER https://neverblink.eu/ontologies/llm-kg/methods#ReAct http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#ReAct http://www.w3.org/2000/01/rdf-schema#comment This method is cited as a motivation for GoG's "Thinking" component. ReAct treats LLMs as agents that interact with an environment and make decisions to retrieve information, inspiring GoG's interactive framework. https://neverblink.eu/ontologies/llm-kg/methods#ReAct http://www.w3.org/2000/01/rdf-schema#label ReAct https://neverblink.eu/ontologies/llm-kg/methods#RoG http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#RoG http://www.w3.org/2000/01/rdf-schema#comment This is a Retrieval Augmented (RA) method, specifically noted as the state-of-the-art among fine-tuned models for KGQA, and is used as a strong baseline for comparison. It generates relation paths as faithful plans to retrieve reasoning paths from KGs. https://neverblink.eu/ontologies/llm-kg/methods#RoG http://www.w3.org/2000/01/rdf-schema#label RoG https://neverblink.eu/ontologies/llm-kg/methods#SelfConsistency http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#SelfConsistency http://www.w3.org/2000/01/rdf-schema#comment This method is used as a baseline for comparison. It is a technique for improving the robustness of LLM reasoning by sampling multiple reasoning paths and taking a majority vote to arrive at a more reliable answer. https://neverblink.eu/ontologies/llm-kg/methods#SelfConsistency http://www.w3.org/2000/01/rdf-schema#label Self-Consistency (SC) https://neverblink.eu/ontologies/llm-kg/methods#StandardPrompting http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#StandardPrompting http://www.w3.org/2000/01/rdf-schema#comment This method is used as a baseline for comparison against the proposed Generate-on-Graph (GoG) method. It represents a simple, direct prompting approach to question answering without explicit KG integration beyond basic retrieval. https://neverblink.eu/ontologies/llm-kg/methods#StandardPrompting http://www.w3.org/2000/01/rdf-schema#label Standard Prompting (IO prompt) https://neverblink.eu/ontologies/llm-kg/methods#StructGPT http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#StructGPT http://www.w3.org/2000/01/rdf-schema#comment This is a Retrieval Augmented (RA) method for KGQA, used as a baseline for comparison. It retrieves information from KGs to guide LLMs in generating answers, and its performance is assessed under both complete and incomplete KG settings. https://neverblink.eu/ontologies/llm-kg/methods#StructGPT http://www.w3.org/2000/01/rdf-schema#label StructGPT https://neverblink.eu/ontologies/llm-kg/methods#ToG http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#ToG http://www.w3.org/2000/01/rdf-schema#comment This is a Retrieval Augmented (RA) method used as a key baseline for comparison. ToG treats the LLM as an agent to interactively explore relation paths on KGs, and its limitations are thoroughly analyzed and contrasted with the proposed GoG method, particularly in incomplete KG scenarios. https://neverblink.eu/ontologies/llm-kg/methods#ToG http://www.w3.org/2000/01/rdf-schema#label ToG https://w3id.org/np/RA3CyIg9XrQadn61m1lbmo8fh0F46iq4DUinlajefw74k/provenance https://w3id.org/np/RA3CyIg9XrQadn61m1lbmo8fh0F46iq4DUinlajefw74k/assertion http://www.w3.org/ns/prov#wasAttributedTo https://neverblink.eu/ontologies/llm-kg/agent https://w3id.org/np/RA3CyIg9XrQadn61m1lbmo8fh0F46iq4DUinlajefw74k/assertion http://www.w3.org/ns/prov#wasDerivedFrom https://doi.org/10.48550/arXiv.2404.14741 https://w3id.org/np/RA3CyIg9XrQadn61m1lbmo8fh0F46iq4DUinlajefw74k/pubinfo https://w3id.org/np/RA3CyIg9XrQadn61m1lbmo8fh0F46iq4DUinlajefw74k http://purl.org/dc/terms/created 2026-03-13T16:04:52.610Z https://w3id.org/np/RA3CyIg9XrQadn61m1lbmo8fh0F46iq4DUinlajefw74k http://purl.org/dc/terms/creator https://neverblink.eu/ontologies/llm-kg/agent https://w3id.org/np/RA3CyIg9XrQadn61m1lbmo8fh0F46iq4DUinlajefw74k http://purl.org/nanopub/x/hasNanopubType https://neverblink.eu/ontologies/llm-kg/PaperAssessmentResult https://w3id.org/np/RA3CyIg9XrQadn61m1lbmo8fh0F46iq4DUinlajefw74k http://purl.org/nanopub/x/supersedes https://w3id.org/np/RA01lfEQMelkkvSeHNCSfeEuP-2SJIbs_7ay-FrBiucHk https://w3id.org/np/RA3CyIg9XrQadn61m1lbmo8fh0F46iq4DUinlajefw74k http://www.w3.org/2000/01/rdf-schema#label LLM-KG assessment for paper 10.48550/arXiv.2404.14741 https://w3id.org/np/RA3CyIg9XrQadn61m1lbmo8fh0F46iq4DUinlajefw74k/sig http://purl.org/nanopub/x/hasAlgorithm RSA https://w3id.org/np/RA3CyIg9XrQadn61m1lbmo8fh0F46iq4DUinlajefw74k/sig http://purl.org/nanopub/x/hasPublicKey MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAwNz2QK3SEifno78S7+48zUB0xpTex3mAzW73ZimHqNcdEMU5/apslrGrTHGFAt/Chocgo++r6JQp5ygY7NyJHGWdaIqnt85pjX4PbNfLAvapyUO00qZP34fY61w4eZ9UMtleWEsmZKRtQPyJ8ODl46i/rfPuZlcJGpM9Nmy5mpGWuepqIEvF4a/t7pLVeCEDFSYXT+yaiygt6ynIK5f7TtEDhZpeUf/Q74WhMPJXm4yTU/hqOX4IW+50kWHNArGGZwUaXwzyG6M3Zd6UMModryGkLqS4H/MSE3ZA1Ylnms7BfWLEXhMWlaKi6HRV4nGRDLhxVSi9LSRi3LWKLhNIIQIDAQAB https://w3id.org/np/RA3CyIg9XrQadn61m1lbmo8fh0F46iq4DUinlajefw74k/sig http://purl.org/nanopub/x/hasSignature OHw1QKDESXiySRrGNoNPJ4FI4c0tBPSrAdZ0xYbNITwjyQp4aQkHVLQB43Y1dpSdWuu5Hl8aThvkkNschD42RIQTHskNwIzVJ+dRXZIDrBKVGTVwRXRt9M0OzdnESaFvk12CGBQyq0it4xSuilk0rhh07nXm8AtxIIw71k+HCPuK2A3Upb4f56ybcnkl0LKlV7qaPzKgTKlSjpEt6mjAZhenZamrN+mb5epqmZ3bRAVThZRo8EHsnMSeCPiDsKCTgxNymDjdESw/CN2ceCg8RBiW2eVCbEWs5iE5G/+t7wFWPqdkKviZRvBT9uiBKBarwES3O5rUSQrGlccVOZgGHA== https://w3id.org/np/RA3CyIg9XrQadn61m1lbmo8fh0F46iq4DUinlajefw74k/sig http://purl.org/nanopub/x/hasSignatureTarget https://w3id.org/np/RA3CyIg9XrQadn61m1lbmo8fh0F46iq4DUinlajefw74k https://w3id.org/np/RA3CyIg9XrQadn61m1lbmo8fh0F46iq4DUinlajefw74k/sig http://purl.org/nanopub/x/signedBy https://neverblink.eu/ontologies/llm-kg/agent