GPT-4o generates high-quality reading comprehension questions, but only 42.6% correctly target the specified bridging inference type.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Automatic Generation of Inference Making Questions for Reading Comprehension Assessments
GPT-4o generates high-quality reading comprehension questions, but only 42.6% correctly target the specified bridging inference type.