A continuous monitor compares an LLM-built knowledge graph with a rule-built knowledge graph from the same news stream and flags structural drift as possible hallucination.
Mitigating large language model hallucinations via autonomous knowledge graph-based retrofitting, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Continuous Monitoring of Large-Scale Generative AI via Deterministic Knowledge Graph Structures
A continuous monitor compares an LLM-built knowledge graph with a rule-built knowledge graph from the same news stream and flags structural drift as possible hallucination.