Beyond Reference-Based Evaluation: Reward Models for Meta-Evaluation of Grammatical Error Correction
RM-EVAL is introduced, a reward model trained on human preference data from SEEDA, as a reference-free meta-evaluator that predicts human-like quality judgments at both full-sequence and partial-sequence levels and can be used as a learning signal to improve GEC generation via Reward-Guided Text Generation (RGTG), whic...