Conformal Path Reasoning: Trustworthy Knowledge Graph Question Answering via Path-Level Calibration
This work addresses the need for reliable uncertainty quantification in KGQA, providing statistically guaranteed and compact answer sets for users requiring trustworthy AI systems.
Conformal Path Reasoning (CPR) improves coverage guarantees and reduces prediction set size in Knowledge Graph Question Answering by introducing query-level conformal calibration over path-level scores and a Residual Conformal Value Network for discriminative nonconformity scores, achieving a 34% increase in empirical coverage rate and a 40% reduction in average prediction set size.
Knowledge Graph Question Answering (KGQA) has shown promise for grounded and interpretable reasoning, yet existing approaches often fail to provide reliable coverage guarantees over retrieved answers. While Conformal Prediction (CP) offers a principled framework for producing prediction sets with statistical guarantees, prior methods suffer from critical limitations in both calibration validity and score discriminability, resulting in violated coverage guarantees and excessively large prediction sets. To address these pitfalls, we propose Conformal Path Reasoning (CPR), a trustworthy KGQA framework with two key innovations. First, we perform query-level conformal calibration over path-level scores, preserving the exchangeability while generating path prediction sets. Second, we introduce the Residual Conformal Value Network (RCVNet), a lightweight module trained via PUCT-guided exploration to learn discriminative path-level nonconformity scores. Experiments on benchmarks show that CPR significantly improves the Empirical Coverage Rate by 34% while reducing average prediction set size by 40% compared to conformal baselines. These results validate the efficacy of CPR in satisfying coverage guarantees with substantially more compact answer sets.