Works · Framework Demo
Knowledge-graph RAG answers look confident even when the retrieved path is weak or the reasoning is fragile. Ca2KG calibrates trust by re-answering the question under counterfactual interventions — assuming the retrieved path is weak, then simulating a reasoning failure — and combines the results with a panel-based re-scoring step into a single Calibrated Confidence Index (CCI).
How it works
The question is answered normally over the retrieved knowledge-graph path.
Re-answers while assuming the retrieved path is weak — tests reliance on retrieval quality.
Simulates a reasoning failure to see whether the answer holds up regardless.
All three outputs are aggregated into one Calibrated Confidence Index that decides trust.
Worked example
Illustrative scores in the shape of the paper's calibration signals — not a live model call.