An automated pipeline derives an ontology from PDFs via LLMs and graphs, reporting higher comprehensiveness and diversity win rates than vector RAG and GraphRAG, but the evaluation is circular and artifacts are missing.
Language models are few-shot learners,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
OntoRAG: Enhancing Question-Answering through Automated Ontology Derivation from Unstructured Knowledge Bases
An automated pipeline derives an ontology from PDFs via LLMs and graphs, reporting higher comprehensiveness and diversity win rates than vector RAG and GraphRAG, but the evaluation is circular and artifacts are missing.