QRAKEN distills an RDF knowledge graph into TTQL pattern descriptions and a co-occurrence matrix, then uses them to prompt a language model and deterministically validate its SPARQL queries, reporting large gains on the CK25 benchmark.
Title resolution pending
7 Pith papers cite this work, alongside 83 external citations. Polarity classification is still indexing.
7
Pith papers citing it
83
external citations · external index
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
For Text-to-Cypher generation, the main source of recovery from single-pass failures is failure detection and rerouting, not feedback quality or parallel sampling.
KG-Guard augments knowledge graphs with a virtual question node and uses a graph encoder plus MLP to classify LLM-proposed answers as hallucinations or not, reporting superior F1 scores and downstream improvements on three benchmarks.
GRALAN uses question-focused subgraphs, a graph encoder, and a learned mediator to let a frozen LLM answer KG questions by classifying entities, reporting state-of-the-art or near-SOTA accuracy on several QA benchmarks.
STAR is a semantic-tuned and tail-adaptive retriever for GraphRAG that uses cross-attention interaction learning and path-weighted contrastive learning to mitigate Semantic Shortcut Bias and Long-Tail Path Bias, reporting 1.8% retrieval and 2.2% QA gains.
Offline walks over a knowledge graph, verbalized into text and retrieved by embedding similarity, let a single LLM call answer multi-hop questions competitively without any fine-tuning.
A survey of methods that enhance LLM inference by integrating external structured knowledge from tables and knowledge graphs.
citing papers explorer
-
Natural Language Questions as an Interface for Knowledge Graphs: QRAKEN Graph Distillation and Semantic Self-Healing
QRAKEN distills an RDF knowledge graph into TTQL pattern descriptions and a co-occurrence matrix, then uses them to prompt a language model and deterministically validate its SPARQL queries, reporting large gains on the CK25 benchmark.
-
What Drives Recovery in Agentic Text-to-Cypher? LAST-CQ: An LLM Agent Self-Refinement Framework
For Text-to-Cypher generation, the main source of recovery from single-pass failures is failure detection and rerouting, not feedback quality or parallel sampling.
-
KG-Guard: Graph-Based Hallucination Detection for Knowledge Base Question Answering
KG-Guard augments knowledge graphs with a virtual question node and uses a graph encoder plus MLP to classify LLM-proposed answers as hallucinations or not, reporting superior F1 scores and downstream improvements on three benchmarks.
-
The Graph Language: How Knowledge Graphs Speak to Large Language Models
GRALAN uses question-focused subgraphs, a graph encoder, and a learned mediator to let a frozen LLM answer KG questions by classifying entities, reporting state-of-the-art or near-SOTA accuracy on several QA benchmarks.
-
STAR: Semantic-Tuned and Tail-Adaptive Retriever for Graph-Augmented Generation
STAR is a semantic-tuned and tail-adaptive retriever for GraphRAG that uses cross-attention interaction learning and path-weighted contrastive learning to mitigate Semantic Shortcut Bias and Long-Tail Path Bias, reporting 1.8% retrieval and 2.2% QA gains.
-
Walk&Retrieve: Simple Yet Effective Zero-shot Retrieval-Augmented Generation via Knowledge Graph Walks
Offline walks over a knowledge graph, verbalized into text and retrieved by embedding similarity, let a single LLM call answer multi-hop questions competitively without any fine-tuning.
-
LLM Inference Enhanced by External Knowledge: A Survey
A survey of methods that enhance LLM inference by integrating external structured knowledge from tables and knowledge graphs.