NS3 approximates joint ranking for EFO_k queries on KGs by merging free variables into hypernodes, pruning domains with dynamic budget B, and reducing to EFO_{k-1} queries, improving joint performance on three datasets while releasing a k=3 joint-ranking benchmark.
Complex logical reasoning over knowledge graphs using large language models
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
Introduces CVQ as a novel data type with a scalable synthesis pipeline from multi-modal KGs yielding 14 FOL-based query types, plus a two-stage training framework for MLLM visual reasoning.
EHRAG constructs structural hyperedges from sentence co-occurrence and semantic hyperedges from entity embedding clusters, then applies hybrid diffusion plus topic-aware PPR to retrieve top-k documents, outperforming baselines on four datasets with linear indexing cost and zero token overhead.
eMoT treats reasoning trajectories as dynamic memories with corrosion, symbolic Python anchoring, and consistency refinement, raising accuracy on Game of 24 to 100% and improving math benchmarks over CoT baselines with a lightweight model.
A survey proposing a holistic GraphRAG framework with components including query processor, retriever, organizer, generator, and data source, plus domain-tailored reviews, challenges, and future directions.
citing papers explorer
-
Neural Scalable Symbolic Search Framework for Complex Logical Queries with Multiple Free Variables
NS3 approximates joint ranking for EFO_k queries on KGs by merging free variables into hypernodes, pruning domains with dynamic budget B, and reducing to EFO_{k-1} queries, improving joint performance on three datasets while releasing a k=3 joint-ranking benchmark.
-
Symbolic and Abstractive Reasoning with Complex Visual Queries
Introduces CVQ as a novel data type with a scalable synthesis pipeline from multi-modal KGs yielding 14 FOL-based query types, plus a two-stage training framework for MLLM visual reasoning.
-
EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval
EHRAG constructs structural hyperedges from sentence co-occurrence and semantic hyperedges from entity embedding clusters, then applies hybrid diffusion plus topic-aware PPR to retrieve top-k documents, outperforming baselines on four datasets with linear indexing cost and zero token overhead.
-
eMoT: evolving Memory-of-Thought via Symbolic Anchoring and Memory Corrosion
eMoT treats reasoning trajectories as dynamic memories with corrosion, symbolic Python anchoring, and consistency refinement, raising accuracy on Game of 24 to 100% and improving math benchmarks over CoT baselines with a lightweight model.
-
Retrieval-Augmented Generation with Graphs (GraphRAG)
A survey proposing a holistic GraphRAG framework with components including query processor, retriever, organizer, generator, and data source, plus domain-tailored reviews, challenges, and future directions.