Multi-Dimensional Evaluation of LLMs for Grammatical Error Correction

• URL: http://arxiv.org/abs/2605.07635v1
• Date: Fri, 08 May 2026 12:01:42 GMT
• Title: Multi-Dimensional Evaluation of LLMs for Grammatical Error Correction
• Abstract summary: We evaluate latest-generation Large Language Models (LLMs) on edit precision, fluency preservation, and meaning retention.<n>We show fine-tuned GPT-4o achieves state-of-the-art performance across all three dimensions.<n>We show that reference-based metrics underestimate GEC performance with 73.76% of GPT-4o corrections different from gold standards being equally valid or even superior.
• Score: 16.867521502670296
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automated assistants for Grammatical Error Correction are now embedded in educational platforms serving millions of learners, yet three critical gaps remain in this domain: (1) latest-generation Large Language Models (LLMs) lack comprehensive evaluation on grammar correction tasks; (2) whether combining these LLMs improves correction quality is unexplored; and (3) the extent to which reference-based metrics underestimate GEC system performance has not been adequately quantified. In this study, first, we evaluate latest-generation LLMs on edit precision, fluency preservation, and meaning retention, showing fine-tuned GPT-4o achieves state-of-the-art performance across all three dimensions. Second, through grammatical error type analysis we demonstrate that individual LLMs exhibit highly similar error correction patterns ($ρ=0.947$). Third, we show that reference-based metrics underestimate GEC performance with 73.76% of GPT-4o corrections different from gold standards being equally valid or even superior. These GEC evaluation findings equip educators with guidance for selecting GEC assistants that enhance rather than constrain student linguistic development. We make our data, code, and models publicly available.

Related papers

• Encode Errors: Representational Retrieval of In-Context Demonstrations for Multilingual Grammatical Error Correction [28.920985595976873]
  Grammatical Error Correction (GEC) involves detecting and correcting the wrong usage of grammar.<n>Large language models (LLMs) with in-context learning (ICL) capabilities have shown significant progress on various natural language processing (NLP) tasks.<n>This is mainly due to the challenge of retrieving suitable in-context demonstrations that capture error patterns instead of semantic similarity.
  arXiv  Detail & Related papers  (2026-06-13T18:00:26Z)
• MQM-APE: Toward High-Quality Error Annotation Predictors with Automatic Post-Editing in LLM Translation Evaluators [53.91199933655421]
  Large Language Models (LLMs) have shown significant potential as judges for Machine Translation (MT) quality assessment.<n>We introduce a universal and training-free framework, $textbfMQM-APE, based on the idea of filtering out non-impactful errors.<n>Experiments show that our approach consistently improves both the reliability and quality of error spans against GEMBA-MQM.
  arXiv  Detail & Related papers  (2024-09-22T06:43:40Z)
• CLEME2.0: Towards Interpretable Evaluation by Disentangling Edits for Grammatical Error Correction [29.017965285565765]
  We introduce **CLEME2.0**, a reference-based metric describing hit-correction, wrong-correction, under-correction, and over-correction.<n>Experiments on two human judgment datasets and six reference datasets demonstrate the effectiveness and robustness of our method.
  arXiv  Detail & Related papers  (2024-07-01T03:35:58Z)
• Large Language Models Are State-of-the-Art Evaluator for Grammatical Error Correction [14.822205658480813]
  Large Language Models (LLMs) have been reported to outperform existing automatic evaluation metrics in some tasks. This study investigates the performance of LLMs in grammatical error correction (GEC) evaluation by employing prompts inspired by previous research.
  arXiv  Detail & Related papers  (2024-03-26T09:43:15Z)
• LM-Combiner: A Contextual Rewriting Model for Chinese Grammatical Error Correction [49.0746090186582]
  Over-correction is a critical problem in Chinese grammatical error correction (CGEC) task. Recent work using model ensemble methods can effectively mitigate over-correction and improve the precision of the GEC system. We propose the LM-Combiner, a rewriting model that can directly modify the over-correction of GEC system outputs without a model ensemble.
  arXiv  Detail & Related papers  (2024-03-26T06:12:21Z)
• Rethinking the Roles of Large Language Models in Chinese Grammatical Error Correction [62.409807640887834]
  Chinese Grammatical Error Correction (CGEC) aims to correct all potential grammatical errors in the input sentences. LLMs' performance as correctors on CGEC remains unsatisfactory due to its challenging task focus. We rethink the roles of LLMs in the CGEC task so that they can be better utilized and explored in CGEC.
  arXiv  Detail & Related papers  (2024-02-18T01:40:34Z)
• Machine Translation Meta Evaluation through Translation Accuracy Challenge Sets [92.38654521870444]
  We introduce ACES, a contrastive challenge set spanning 146 language pairs. This dataset aims to discover whether metrics can identify 68 translation accuracy errors. We conduct a large-scale study by benchmarking ACES on 50 metrics submitted to the WMT 2022 and 2023 metrics shared tasks.
  arXiv  Detail & Related papers  (2024-01-29T17:17:42Z)
• Evaluation of really good grammatical error correction [0.0]
  Grammatical Error Correction (GEC) encompasses various models with distinct objectives. Traditional evaluation methods fail to fully capture the full range of system capabilities and objectives.
  arXiv  Detail & Related papers  (2023-08-17T13:45:35Z)
• Analyzing the Performance of GPT-3.5 and GPT-4 in Grammatical Error Correction [28.58384091374763]
  GPT-3 and GPT-4 models are powerful, achieving high performance on a variety of Natural Language Processing tasks. We perform experiments testing the capabilities of a GPT-3.5 model (text-davinci-003) and a GPT-4 model (gpt-4-0314) on major GEC benchmarks. We report the performance of our best prompt on the BEA-2019 and JFLEG datasets, finding that the GPT models can perform well in a sentence-level revision setting.
  arXiv  Detail & Related papers  (2023-03-25T03:08:49Z)
• LM-Critic: Language Models for Unsupervised Grammatical Error Correction [128.9174409251852]
  We show how to leverage a pretrained language model (LM) in defining an LM-Critic, which judges a sentence to be grammatical. We apply this LM-Critic and BIFI along with a large set of unlabeled sentences to bootstrap realistic ungrammatical / grammatical pairs for training a corrector.
  arXiv  Detail & Related papers  (2021-09-14T17:06:43Z)
• A Self-Refinement Strategy for Noise Reduction in Grammatical Error Correction [54.569707226277735]
  Existing approaches for grammatical error correction (GEC) rely on supervised learning with manually created GEC datasets. There is a non-negligible amount of "noise" where errors were inappropriately edited or left uncorrected. We propose a self-refinement method where the key idea is to denoise these datasets by leveraging the prediction consistency of existing models.
  arXiv  Detail & Related papers  (2020-10-07T04:45:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.