CPR uses query-level conformal calibration over path scores and a PUCT-trained RCVNet to achieve valid coverage guarantees and smaller prediction sets in KGQA, reporting 45% higher empirical coverage and 52% smaller sets than prior conformal baselines.
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 uses query-level conformal calibration over path scores and a PUCT-trained RCVNet to achieve valid coverage guarantees and smaller prediction sets in KGQA, reporting 45% higher empirical coverage and 52% smaller sets than prior conformal baselines.
-
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.