Re-RIGHT trains a 4B policy model with vocabulary coverage, semantic preservation, and coherence rewards to perform proficiency-aware lexical simplification in four languages without parallel corpora.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Right at My Level: A Unified Multilingual Framework for Proficiency-Aware Text Simplification
Re-RIGHT trains a 4B policy model with vocabulary coverage, semantic preservation, and coherence rewards to perform proficiency-aware lexical simplification in four languages without parallel corpora.