GPT-4o and Gemma-2 generate Portuguese reading-comprehension MCQs whose expert and psychometric quality is comparable to human-authored items, while a two-step small-model pipeline underperforms.
Title resolution pending
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.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
From Model to Classroom: Evaluating Generated MCQs for Portuguese with Narrative and Difficulty Concerns
GPT-4o and Gemma-2 generate Portuguese reading-comprehension MCQs whose expert and psychometric quality is comparable to human-authored items, while a two-step small-model pipeline underperforms.