concept

Chain of Exploration

Also known as: CoE, Chain of Exploration, Chain of Explorations

Facts (13)

Sources

KG-RAG: Bridging the Gap Between Knowledge and Creativity - arXiv arxiv.org arXiv May 20, 2024 7 facts

measurementThe Chain of Explorations (CoE) system currently has an average response time of 30 seconds due to multiple calls to the Azure API, which could be reduced to 3 seconds using Groq hardware.

claimThe authors of the KG-RAG paper introduced the Chain of Explorations method to perform precise, contextually relevant lookups within the structured knowledge of Knowledge Graphs.

claimThe Chain of Explorations (CoE) is a method for knowledge graph question answering (KGQA) that systematically extracts pertinent information from a knowledge graph by performing a sequential traversal of nodes and relationships.

measurementThe Chain of Explorations (CoE) system currently has an average response time of 30 seconds due to multiple calls to the Azure API, which could be reduced to 3 seconds using Groq hardware.

procedureThe CoE (Chain of Exploration) method begins by using a few-shot learning prompt combined with a user query to guide a planner in creating a strategic exploration plan across a knowledge graph.

claimThe authors of the KG-RAG paper introduced the Chain of Explorations method to perform precise, contextually relevant lookups within the structured knowledge of Knowledge Graphs.

KG-IRAG: A Knowledge Graph-Based Iterative Retrieval-Augmented ... arxiv.org arXiv Mar 18, 2025 4 facts

referenceThe KG-IRAG system is compared against two other RAG methods: a standard RAG method without exploration (where LLMs decide the data needed, retrieve it, and then process it) and KG-RAG, which utilizes a Chain of Exploration for Knowledge Graph retrieval as described by Sanmartin (2024).

claimTechniques such as Chain of Knowledge (CoK), G-Retriever, and Chain of Explorations have been developed to enhance the precision and efficiency of data retrieval from knowledge graphs.

claimThe KG-RAG system utilizes a limited length exploration plan and Chain-of-Exploration (CoE) for multi-hop relation retrieval, but it struggles with temporal data, often stopping exploration prematurely and resulting in insufficient data for answering queries.

referenceThe study evaluated three Retrieval-Augmented Generation (RAG) systems: 1) a Standard Graph-RAG system where LLMs determine necessary data, retrieve it, and provide an answer; 2) KG-RAG (Sanmartin, 2024), which uses a Chain of Exploration to retrieve data step-by-step over three steps; and 3) the proposed KG-IRAG system.

Large Language Models Meet Knowledge Graphs for Question ... arxiv.org arXiv Sep 22, 2025 1 fact

claimKG-RAG (Sanmartin, 2024) utilizes a "Chain-of-Explorations" (CoE) method to rank and select the most relevant nodes or relationships based on vector similarity, which are then provided to Large Language Models to generate final answers.

KG-RAG: Bridging the Gap Between Knowledge and Creativity - arXiv arxiv.org arXiv May 20, 2024 1 fact

referenceThe Chain of Explorations (CoE) is a retrieval algorithm that utilizes Large Language Model reasoning to sequentially explore nodes and relationships within a Knowledge Graph.