CPR improves empirical coverage rate by 34% and reduces average prediction set size by 40% in KGQA benchmarks via query-level path calibration and RCVNet for discriminative nonconformity scores.
Proceedings of the ACM on Web Conference 2025 , pages=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
LogosKG delivers a novel hardware-aligned system for efficient multi-hop retrieval on billion-edge knowledge graphs without sacrificing fidelity, demonstrated via biomedical KG-LLM applications.
GNN generalization depends explicitly on graph structural complexity measured by effective edges, with a new regularization method shown to balance underfitting and overfitting.
citing papers explorer
-
Conformal Path Reasoning: Trustworthy Knowledge Graph Question Answering via Path-Level Calibration
CPR improves empirical coverage rate by 34% and reduces average prediction set size by 40% in KGQA benchmarks via query-level path calibration and RCVNet for discriminative nonconformity scores.
-
LogosKG: Hardware-Optimized Scalable and Interpretable Knowledge Graph Retrieval
LogosKG delivers a novel hardware-aligned system for efficient multi-hop retrieval on billion-edge knowledge graphs without sacrificing fidelity, demonstrated via biomedical KG-LLM applications.
-
Rethinking Generalization in Graph Neural Networks: A Structural Complexity Perspective
GNN generalization depends explicitly on graph structural complexity measured by effective edges, with a new regularization method shown to balance underfitting and overfitting.