This model classifies questions in developer forums (e.g., Stack Overflow) as 'LQ_CLOSE' (low-quality), 'LQ_EDIT' (low-quality, require community edits), 'HQ' (high-quality).
@misc{pena2025benchmark,
author = {Fabian Peña and Steffen Herbold},
title = {Evaluating Large Language Models on Non-Code Software Engineering Tasks},
year = {2025}
}
