# Reliability Crisis of Reference-free Metrics for Grammatical Error Correction

arXiv: https://arxiv.org/abs/2509.25961 · HTML: https://mlsanity.com/paper/2509.25961/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 24 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Builds on (most cited first, 8 of 8)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [GECToR -- Grammatical Error Correction: Tag, Not Rewrite](https://mlsanity.com/paper/2005.12592/) (2020)
- [A Simple Recipe for Multilingual Grammatical Error Correction](https://mlsanity.com/paper/2106.03830/) (2021)
- [gec-metrics: A Unified Library for Grammatical Error Correction Evaluation](https://mlsanity.com/paper/2505.19388/) (2025)
- [Rethinking Evaluation Metrics for Grammatical Error Correction: Why Use a Different Evaluation Process than Human?](https://mlsanity.com/paper/2502.09416/) (2025)
- [IMPARA-GED: Grammatical Error Detection is Boosting Reference-free Grammatical Error Quality Estimator](https://mlsanity.com/paper/2506.02899/) (2025)

## Abstract (arXiv)

Reference-free evaluation metrics for grammatical error correction (GEC) have achieved high correlation with human judgments. However, these metrics are not designed to evaluate adversarial systems that aim to obtain unjustifiably high scores. The existence of such systems undermines the reliability of automatic evaluation, as it can mislead users in selecting appropriate GEC systems. In this study, we propose adversarial attack strategies for four reference-free metrics: SOME, Scribendi, IMPARA, and LLM-based metrics, and demonstrate that our adversarial systems outperform the current state-of-the-art. These findings highlight the need for more robust evaluation methods.