CLaRO is a data-driven CNL using 93 templates and 41 variants that covers about 90% of unseen competency questions for ontologies, while also flagging invalid questions.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2verdicts
UNVERDICTED 2representative citing papers
LLM-generated competency questions exhibit distinct profiles in readability, relevance, and complexity that vary by model type and use case.
citing papers explorer
-
CLaRO: a Data-driven CNL for Specifying Competency Questions
CLaRO is a data-driven CNL using 93 templates and 41 variants that covers about 90% of unseen competency questions for ontologies, while also flagging invalid questions.
-
Characterising LLM-Generated Competency Questions: a Cross-Domain Empirical Study using Open and Closed Models
LLM-generated competency questions exhibit distinct profiles in readability, relevance, and complexity that vary by model type and use case.