Structured prompting with lexical constraints lets LLMs produce Arabic text that closely matches target CEFR readability levels according to an automatic predictor.
arXiv preprint arXiv:2310.10623 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A reference-free proxy scoring framework combined with GIRB calibration produces better-aligned evaluation metrics for summarization and outperforms baselines across seven datasets.
citing papers explorer
-
Can LLMs Control Readability? A Multi-Dimensional Evaluation Framework for CEFR-Controlled Arabic Generation
Structured prompting with lexical constraints lets LLMs produce Arabic text that closely matches target CEFR readability levels according to an automatic predictor.
-
Calibrating Model-Based Evaluation Metrics for Summarization
A reference-free proxy scoring framework combined with GIRB calibration produces better-aligned evaluation metrics for summarization and outperforms baselines across seven datasets.