Beyond Reference-Based Evaluation: Reward Models for Meta-Evaluation of Grammatical Error Correction

arXiv:2609.21231 · cs.CL · Submitted 2026-09-18 · Read on arXiv

cs.CL

Submitted: 2026-09-18

Updated: 2026-09-27

Comments: 5 pages

License: http://creativecommons.org/licenses/by/4.0/

The gist: Reference-based metrics for Grammatical Error Correction (GEC) such as M squared and ERRANT assume that the reference set enumerates all valid edits, and therefore often penalize corrections that are

Terminology

Abstract

Reference-based metrics for Grammatical Error Correction (GEC) such as M squared and ERRANT assume that the reference set enumerates all valid edits, and therefore often penalize corrections that are grammatical and meaning-preserving but phrased differently. We introduce RM-EVAL, 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. Beyond evaluation, we show that the same reward model can be used as a learning signal to improve GEC generation via Reward-Guided Text Generation (RGTG), which keeps a base GEC model frozen and performs online, reward-driven decoding. Across SEEDA, RM-EVAL achieves strong agreement with human rankings, and RGTG yields consistent gains in reward and external validation, demonstrating a unified framework for both assessing and enhancing GEC systems without relying on gold references.

Sources

Related papers