Knowledge Tree
Relations (1)
related 1.58 — strongly supporting 2 facts
The relationship is established because KG-IRAG is evaluated based on its susceptibility to hallucination, with [1] noting its performance on specific datasets, while [2] contrasts the hallucination risks of KG-IRAG against those found in baseline RAG systems.
Facts (2)
Sources
KG-IRAG: A Knowledge Graph-Based Iterative Retrieval-Augmented ... arxiv.org 2 facts
claimIn baseline RAG systems, hallucinations often lead to the generation of wrong answers due to the use of insufficient data, which is considered more harmful than the extra data retrieval observed in KG-IRAG.
measurementThe KG-IRAG system exhibits a higher tendency for hallucination when processing datasets containing many numerical values, such as the TrafficQA-TFNSW dataset.