Knowledge Tree
Relations (1)
related 2.00 — strongly supporting 3 facts
The relationship exists because 'Automatic Graph Exploration' is a specific procedural method designed to interact with and traverse a 'Knowledge Graph' as described in [1] and [2], while [3] evaluates the performance of this exploration technique within the context of knowledge graph reasoning.
Facts (3)
Sources
Grounding LLM Reasoning with Knowledge Graphs - arXiv arxiv.org 3 facts
procedureThe Automatic Graph Exploration method for LLM-Knowledge Graph interaction incrementally searches the graph by interleaving language generation with structured retrieval, where the LLM generates a new thought based on previous thoughts and retrieved triples at each step.
claimThe agentic method generally outperformed automatic graph exploration in the experiments, indicating that targeted interventions on knowledge graph traversal enhance answer accuracy.
procedureThe 'Automatic Graph Exploration' pipeline for LLM and Knowledge Graph interaction involves automatically extracting entities from the LLM’s generated text and using them to guide iterative graph traversal with pruning, which progressively expands the reasoning chain.