Develops a theoretical perspective showing no hard rule can perfectly reject false unsupported trajectories while retaining true-but-unobserved ones under incomplete graph evidence, and characterizes soft grounding as KL-regularized deformation of the LLM prior.
IEEE Transactions on Knowledge and Data Engineering36, 7 (2024), 3580–3599
14 Pith papers cite this work, alongside 954 external citations. Polarity classification is still indexing.
14
Pith papers citing it
954
external citations · external index
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Graph-PRefLexOR fine-tunes graph-native models with GRPO to organize reasoning into phases, yielding 40-65% gains in traceable hypothesis generation and 2-3x semantic diversity on 100 materials science questions.
OPI introduces a relation-centric ontology graph enabling bidirectional retrieval and iterative refinement, yielding Hit@1/F1 gains of 4.6/5.0 on WebQSP and 8.9/3.3 on CWQ plus near-saturated Hit@1 on MetaQA.
The authors introduce a three-part ontology-based verification system for AI agents that generates regulatory and adversarial test scenarios and issues machine-verifiable trust certificates, with pilot results indicating improved coverage over baselines in four industries.
Structured schema.org metadata still gives dataset-retrieval agents a large precision advantage for machine-actionable data.
GraphMind builds and evolves action-centric workflow graphs from traces, navigates them via multi-agent LLM reasoning, and adapts via ATR, outperforming baselines on 93 incidents with 8x less context and 26% lower hallucination in production deployment.
An extended annotation scheme with new categories and attributes plus a Gemma-300M-based multi-head classifier achieves 81.6% macro F1 on personal fact classification, outperforming few-shot LLM baselines by nearly 9 points with lower compute.
Proposes forward replay of target hidden states from the first editing layer instead of backward spreading, claiming equivalent complexity but higher accuracy for LLM parameter editing.
AF-Retriever delivers state-of-the-art zero- and one-shot results on three STaRK QA benchmarks by using LLM extraction, vector similarity, incremental scope expansion, and hybrid retrieval.
OMAGR decomposes queries into ontology-aligned anchors for parallel multi-dimensional graph retrieval, outperforming baselines on Context Precision and Faithfulness in the new TrafficLaw-QA dataset of 200 questions.
Ontology-grounded tool architectures eliminate hallucination of domain identifiers in industrial AI agents by enforcing semantic constraints through a typed relational configuration and three-operation interface.
GS-Quant generates coarse-to-fine discrete codes for KG entities via semantic hierarchy injection and causal sequence reconstruction, enabling LLMs to perform knowledge graph completion by treating the codes as vocabulary tokens.
BifrostRAG combines dual knowledge graphs with hybrid retrieval to improve multi-hop question answering on construction safety regulations, reporting 87.3% F1 on a custom dataset.
pykci transforms CityGML 2.0 datasets into a compact, spatially indexed Neo4j knowledge graph supporting LLM text-to-Cypher queries, demonstrated on Hamburg LoD2 data with lossless round-trip to CityGML.
citing papers explorer
-
Grounding LLM Reasoning under Incomplete Graph Evidence
Develops a theoretical perspective showing no hard rule can perfectly reject false unsupported trajectories while retaining true-but-unobserved ones under incomplete graph evidence, and characterizes soft grounding as KL-regularized deformation of the LLM prior.
-
Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination
Graph-PRefLexOR fine-tunes graph-native models with GRPO to organize reasoning into phases, yielding 40-65% gains in traceable hypothesis generation and 2-3x semantic diversity on 100 materials science questions.
-
Ontology-Guided Evidence Path Inference for Multi-hop Knowledge Graph Question Answering
OPI introduces a relation-centric ontology graph enabling bidirectional retrieval and iterative refinement, yielding Hit@1/F1 gains of 4.6/5.0 on WebQSP and 8.9/3.3 on CWQ plus near-saturated Hit@1 on MetaQA.
-
Toward Pre-Deployment Assurance for Enterprise AI Agents: Ontology-Grounded Simulation and Trust Certification
The authors introduce a three-part ontology-based verification system for AI agents that generates regulatory and adversarial test scenarios and issues machine-verifiable trust certificates, with pilot results indicating improved coverage over baselines in four industries.
-
Do Data Agents Need Semantic Metadata? A Comparative Study in Agentic Data Retrieval
Structured schema.org metadata still gives dataset-retrieval agents a large precision advantage for machine-actionable data.
-
GraphMind: From Operational Traces to Self-Evolving Workflow Automation
GraphMind builds and evolves action-centric workflow graphs from traces, navigates them via multi-agent LLM reasoning, and adapts via ATR, outperforming baselines on 93 incidents with 8x less context and 26% lower hallucination in production deployment.
-
An Annotation Scheme and Classifier for Personal Facts in Dialogue
An extended annotation scheme with new categories and attributes plus a Gemma-300M-based multi-head classifier achieves 81.6% macro F1 on personal fact classification, outperforming few-shot LLM baselines by nearly 9 points with lower compute.
-
From Backward Spreading to Forward Replay: Revisiting Target Construction in LLM Parameter Editing
Proposes forward replay of target hidden states from the first editing layer instead of backward spreading, claiming equivalent complexity but higher accuracy for LLM parameter editing.
-
Autofocus Retrieval: An Effective Pipeline for Multi-Hop Question Answering With Semi-Structured Knowledge
AF-Retriever delivers state-of-the-art zero- and one-shot results on three STaRK QA benchmarks by using LLM extraction, vector similarity, incremental scope expansion, and hybrid retrieval.
-
An Ontology-Guided Multi-Anchor Graph Retrieval Framework for Traffic Legal Liability Determination
OMAGR decomposes queries into ontology-aligned anchors for parallel multi-dimensional graph retrieval, outperforming baselines on Context Precision and Faithfulness in the new TrafficLaw-QA dataset of 200 questions.
-
The Semantic Training Gap: Ontology-Grounded Tool Architectures for Industrial AI Agent Systems
Ontology-grounded tool architectures eliminate hallucination of domain identifiers in industrial AI agents by enforcing semantic constraints through a typed relational configuration and three-operation interface.
-
GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completion
GS-Quant generates coarse-to-fine discrete codes for KG entities via semantic hierarchy injection and causal sequence reconstruction, enabling LLMs to perform knowledge graph completion by treating the codes as vocabulary tokens.
-
Bridging Dual Knowledge Graphs for Multi-Hop Question Answering in Construction Safety
BifrostRAG combines dual knowledge graphs with hybrid retrieval to improve multi-hop question answering on construction safety regulations, reporting 87.3% F1 on a custom dataset.
-
pykci: A Compact Urban Knowledge Graph for Semantic and Spatial Queries using LLMs
pykci transforms CityGML 2.0 datasets into a compact, spatially indexed Neo4j knowledge graph supporting LLM text-to-Cypher queries, demonstrated on Hamburg LoD2 data with lossless round-trip to CityGML.