科研速览 · Science Skim继续刷下去 · Keep skimming →
◇ arXiv2026-09-18· cs.CL

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

Ruotian Wu, Bill E. Johnson, Gene Saunders, Osama Hamzeh, Ankit Vadehra, Pascal Poupart

原始摘要(英文原文)· Original abstract
Reference-based metrics for Grammatical Error Correction (GEC) such as M$^2$ 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.
读原文 · Read the paper ↗

AI 追问PRO

登录后使用 AI 追问

讨论区

登录后参与讨论

相关论文 · Related

Beyond Reference-Based Evaluation: Reward Models for Meta-Evaluation of Grammatical Error Correction — 科研速览 Science Skim