Code and scripts for training Finnish text quality evaluation models inspired by ARGENT
See the original ARGENT publication:
Xinyue Zhang, Agathe Zecevic, Sebastian Zeki, and Angus Roberts. 2025. ARGENT: Automatic Reference-free Evaluation for Open-Ended Text Generation without Source Inputs. In Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM²), pages 82–98, Vienna, Austria and virtual meeting. Association for Computational Linguistics.