Conformal Path Reasoning: Trustworthy Knowledge Graph Question Answering via Path-Level Calibration

TL;DR

This paper introduces Conformal Path Reasoning (CPR), a new framework for trustworthy knowledge graph question answering that guarantees coverage and produces more compact answer sets using path-level calibration and a discriminative scoring network.

Contribution

The paper proposes CPR, combining query-level conformal calibration with a novel scoring network, to improve coverage guarantees and answer set efficiency in KGQA.

Findings

CPR improves empirical coverage rate by 34%.

CPR reduces average prediction set size by 40%.

CPR outperforms conformal baselines on benchmarks.

Abstract

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.