KGRAG-Ex retrieves answer-relevant paths through a knowledge graph, turns them into natural-language paragraphs, and explains each answer by removing individual graph nodes, edges, or sub-paths and observing whether the chosen answer changes.
Evaluating open-domain question answering in the era of large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
KGRAG-Ex: Explainable Retrieval-Augmented Generation with Knowledge Graph-based Perturbations
KGRAG-Ex retrieves answer-relevant paths through a knowledge graph, turns them into natural-language paragraphs, and explains each answer by removing individual graph nodes, edges, or sub-paths and observing whether the chosen answer changes.