Presents GraphInfer-Bench to demonstrate that no evaluated LLM-based method family closes the performance gap on graph inference tasks requiring multi-node reasoning, with plain GNNs matching or exceeding them.
Graphrag-bench: Challenging domain-specific reasoning for evaluating graph retrieval-augmented generation
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
LogicPoison attacks GraphRAG by using type-preserving entity swapping to disrupt global graph hubs and query-specific reasoning paths, bypassing defenses and degrading performance more effectively than prior attacks.
TIGRAG constructs token co-occurrence graphs for scalable graph-augmented RAG and uses iterative entity-driven retrieval to improve multi-hop QA performance over dense and prior graph methods.
MoG uses hub graphs for shared context and sparsely activates expert graphs with a topology-aware router, reporting over 20% relative gains on MuSiQue.
Ψ-RAG improves cross-document multi-hop QA performance using an adaptive hierarchical abstract tree and agent-powered hybrid retrieval, outperforming RAPTOR by 25.9% and HippoRAG 2 by 7.4% in average F1.
G-reasoner uses QuadGraph abstraction and a 34M-parameter graph foundation model integrated with LLMs to enable scalable reasoning over diverse graph-structured knowledge, outperforming baselines on six benchmarks.
Adding handwritten Cypher graph tools to an agentic RAG system roughly doubled factual-correctness precision and recall on MoNaCo complex questions and improved fine-grained truthfulness compared with vector-only RAG.
citing papers explorer
-
GraphInfer-Bench: Benchmarking LLM's Inference Capability on Graphs
Presents GraphInfer-Bench to demonstrate that no evaluated LLM-based method family closes the performance gap on graph inference tasks requiring multi-node reasoning, with plain GNNs matching or exceeding them.
-
LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation
LogicPoison attacks GraphRAG by using type-preserving entity swapping to disrupt global graph hubs and query-specific reasoning paths, bypassing defenses and degrading performance more effectively than prior attacks.
-
Efficient Retrieval-Augmented Generation via Token Co-occurrence Graphs
TIGRAG constructs token co-occurrence graphs for scalable graph-augmented RAG and uses iterative entity-driven retrieval to improve multi-hop QA performance over dense and prior graph methods.
-
MoG: Mixture of Experts for Graph-based Retrieval-Augmented Generation
MoG uses hub graphs for shared context and sparsely activates expert graphs with a topology-aware router, reporting over 20% relative gains on MuSiQue.
-
Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generation
Ψ-RAG improves cross-document multi-hop QA performance using an adaptive hierarchical abstract tree and agent-powered hybrid retrieval, outperforming RAPTOR by 25.9% and HippoRAG 2 by 7.4% in average F1.
-
G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledge
G-reasoner uses QuadGraph abstraction and a 34M-parameter graph foundation model integrated with LLMs to enable scalable reasoning over diverse graph-structured knowledge, outperforming baselines on six benchmarks.
-
Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation (long version)
Adding handwritten Cypher graph tools to an agentic RAG system roughly doubled factual-correctness precision and recall on MoNaCo complex questions and improved fine-grained truthfulness compared with vector-only RAG.