TRACE is a framework that improves multi-hop KGQA by maintaining semantic continuity through path narratives and reusable experiential priors combined via dual-feedback re-ranking.
Transfernet: An effective and transparent framework for multi-hop question answering over relation graph
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2representative citing papers
NeuroSymActive claims state-of-the-art KGQA accuracy (WebQSP 87.1, CWQ 62.5 Hits@1) by coupling differentiable neural-symbolic reasoning with uncertainty-guided MCTS and active human queries.
citing papers explorer
-
TRACE: An Experiential Framework for Coherent Multi-hop Knowledge Graph Question Answering
TRACE is a framework that improves multi-hop KGQA by maintaining semantic continuity through path narratives and reusable experiential priors combined via dual-feedback re-ranking.
-
NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answering
NeuroSymActive claims state-of-the-art KGQA accuracy (WebQSP 87.1, CWQ 62.5 Hits@1) by coupling differentiable neural-symbolic reasoning with uncertainty-guided MCTS and active human queries.