mlsanityData to 13 Oct 2026

GPT-3.5 for Grammatical Error Correction

arXiv 2405.08469 ↗First posted 14 May 2024cs.CL cs.AIcited by 18

Not on the map. Why?

Abstract (arXiv)

This paper investigates the application of GPT-3.5 for Grammatical Error Correction (GEC) in multiple languages in several settings: zero-shot GEC, fine-tuning for GEC, and using GPT-3.5 to re-rank correction hypotheses generated by other GEC models. In the zero-shot setting, we conduct automatic evaluations of the corrections proposed by GPT-3.5 using several methods: estimating grammaticality with language models (LMs), the Scribendi test, and comparing the semantic embeddings of sentences. GPT-3.5 has a known tendency to over-correct erroneous sentences and propose alternative corrections. For several languages, such as Czech, German, Russian, Spanish, and Ukrainian, GPT-3.5 substantially alters the source sentences, including their semantics, which presents significant challenges for evaluation with reference-based metrics. For English, GPT-3.5 demonstrates high recall, generates fluent corrections, and generally preserves sentence semantics. However, human evaluation for both English and Russian reveals that, despite its strong error-detection capabilities, GPT-3.5 struggles with several error types, including punctuation mistakes, tense errors, syntactic dependencies between words, and lexical compatibility at the sentence level.

Key facts. Cited by 18 papers in the map (data through 13 Oct 2026). Builds on 29 of its 50 references that are in the map. First posted on arXiv 14 May 2024.

Builds on

29 of 50 references.

References · 29

  1. 2020Language Models are Few-Shot Learnerscited by 32,320
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,107
  3. 2022Large Language Models are Zero-Shot Reasonerscited by 4,348
  4. 2020Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillationcited by 591
  5. 2016Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependenciescited by 351
  6. 2019Assessing BERT's Syntactic Abilitiescited by 191
  7. 2020GECToR -- Grammatical Error Correction: Tag, Not Rewritecited by 177
  8. 2021A Simple Recipe for Multilingual Grammatical Error Correctioncited by 108
  9. 2019Encode, Tag, Realize: High-Precision Text Editingcited by 99
  10. 2017JFLEG: A Fluency Corpus and Benchmark for Grammatical Error Correctioncited by 97
  11. 2023Is ChatGPT a Highly Fluent Grammatical Error Correction System? A Comprehensive Evaluationcited by 97
  12. 2023ChatGPT or Grammarly? Evaluating ChatGPT on Grammatical Error Correction Benchmarkcited by 77
17 more
  1. 2020Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correctioncited by 59
  2. 2020Seq2Edits: Sequence Transduction Using Span-level Edit Operationscited by 58
  3. 2018Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Taskcited by 56
  4. 2019An Empirical Study of Incorporating Pseudo Data into Grammatical Error Correctioncited by 55
  5. 2019Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Datacited by 50
  6. 2023Exploring Effectiveness of GPT-3 in Grammatical Error Correction: A Study on Performance and Controllability in Prompt-Based Methodscited by 37
  7. 2018A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correctioncited by 36
  8. 2021LM-Critic: Language Models for Unsupervised Grammatical Error Correctioncited by 33
  9. 2023Multi-Task Instruction Tuning of LLaMa for Specific Scenarios: A Preliminary Study on Writing Assistancecited by 33
  10. 2019Grammatical Error Correction in Low-Resource Scenarioscited by 28
  11. 2019A Neural Grammatical Error Correction System Built On Better Pre-training and Sequential Transfer Learningcited by 26
  12. 2020Data Weighted Training Strategies for Grammatical Error Correctioncited by 26
  13. 2021UA-GEC: Grammatical Error Correction and Fluency Corpus for the Ukrainian Languagecited by 19
  14. 2017A Nested Attention Neural Hybrid Model for Grammatical Error Correctioncited by 12
  15. 2019Grammatical Error Correction and Style Transfer via Zero-shot Monolingual Translationcited by 7
  16. 2021Grammatical Error Correction as GAN-like Sequence Labelingcited by 6
  17. 2020Adversarial Grammatical Error Correctioncited by 4

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 2; 2025: 9; 2026: 7.

18 papers.

Sort:

By area:

  1. 2025Enhancing Text Editing for Grammatical Error Correction: Arabic as a Case Studycited by 9
  2. 2024LLMs in Education: Novel Perspectives, Challenges, and Opportunitiescited by 7
  3. 2025Opportunities and Challenges of LLMs in Education: An NLP Perspectivecited by 6
  4. 2025Personalized Query Auto-Completion for Long and Short-Term Interests with Adaptive Detoxification Generationcited by 4
  5. 2024Grammatical Error Feedback: An Implicit Evaluation Approachcited by 2
  6. 2025Exploring the Feasibility of Multilingual Grammatical Error Correction with a Single LLM up to 9B parameters: A Comparative Study of 17 Modelscited by 2
  7. 2025Comparing human and LLM proofreading in L2 writing: Impact on lexical and syntactic featurescited by 2
  8. 2025APIO: Automatic Prompt Induction and Optimization for Grammatical Error Correction and Text Simplificationcited by 2
  9. 2025Leveraging What's Overfixed: Post-Correction via LLM Grammatical Error Overcorrectioncited by 2
  10. 2026Edit-level Majority Voting Mitigates Over-Correction in LLM-based Grammatical Error Correctioncited by 1
  11. 2026How Far Can Prompting Go for Minimal-Edit Ukrainian Grammatical Error Correction?cited by 1
  12. 2025Time Is Effort: Estimating Human Post-Editing Time for Grammar Error Correction Tool Evaluationcited by 0
6 more
  1. 2025When the Gold Standard Isn't Necessarily Standard: Challenges of Evaluating the Translation of User-Generated Contentcited by 0
  2. 2026Grammatical Error Correction Evaluation by Optimally Transporting Edit Representationcited by 0
  3. 2026Exploiting the English Grammar Profile for L2 grammatical analysis with LLMscited by 0
  4. 2026CoCoGEC: Counterfactual Generation for Robust Grammatical Error Correctioncited by 0
  5. 2026Larger Context Window, Fewer Overcorrections: Optimizing Prompts and Batching for Minimal-Edit Grammatical Error Correctioncited by 0
  6. 2026Don't Count the Edits, Judge by the Outcome Alone: Reward-Based Evaluation for Grammatical Error Correctioncited by 0