# How Far Can Prompting Go for Minimal-Edit Ukrainian Grammatical Error Correction?

arXiv: https://arxiv.org/abs/2606.09334 · HTML: https://mlsanity.com/paper/2606.09334/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 30 references that are in the map.
- First posted on arXiv 8 Jun 2026.

## Builds on (most cited first, 9 of 9)

- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization](https://mlsanity.com/paper/2310.16427/) (2023)
- [JFLEG: A Fluency Corpus and Benchmark for Grammatical Error Correction](https://mlsanity.com/paper/1702.04066/) (2017)
- [A Systematic Survey of Automatic Prompt Optimization Techniques](https://mlsanity.com/paper/2502.16923/) (2025)
- [Exploring Effectiveness of GPT-3 in Grammatical Error Correction: A Study on Performance and Controllability in Prompt-Based Methods](https://mlsanity.com/paper/2305.18156/) (2023)
- [GPT-3.5 for Grammatical Error Correction](https://mlsanity.com/paper/2405.08469/) (2024)
- [Adapting LLMs for Minimal-edit Grammatical Error Correction](https://mlsanity.com/paper/2506.13148/) (2025)
- [Spivavtor: An Instruction Tuned Ukrainian Text Editing Model](https://mlsanity.com/paper/2404.18880/) (2024)
- [Introducing OmniGEC: A Silver Multilingual Dataset for Grammatical Error Correction](https://mlsanity.com/paper/2509.14504/) (2025)

## Built on by (most cited first, 1 of 1)

- [Larger Context Window, Fewer Overcorrections: Optimizing Prompts and Batching for Minimal-Edit Grammatical Error Correction](https://mlsanity.com/paper/2609.10810/) (2026)

## Abstract (arXiv)

Fine-tuned Large Language Models (LLMs) dominate in Ukrainian grammatical error correction (GEC), while API-accessed LLMs remain nearly untested on minimal-edit benchmarks. We evaluate 11 commercial LLMs from four providers and one open-source Ukrainian model on the UNLP 2023 GEC-only benchmark, comparing zero-shot, few-shot, minimal-edits, and LLM-assisted prompt optimization strategies. Our best configuration (Gemini 3.1-Pro) reaches F0.5=69.22, closing over 90% of the gap to fine-tuned SOTA (F0.5=73.14). For zero-shot prompts, only Claude models benefit from Ukrainian instructions. However, the best overall results for all models use Ukrainian minimal-edits prompts, whose language-specific rules require Ukrainian to express precisely. LLM-assisted prompt optimization on top of minimal-edits + few-shot achieves the highest score. Detailed minimal-edits instructions yield the largest gains for punctuation and case errors but cause the model to abandon several low-frequency categories. Delving into error analysis, we identify five recurring overcorrection patterns tied to Ukrainian-specific linguistic phenomena. Code, prompts, and outputs are publicly available.