SOURCE-LINKED INTELLIGENCE

Larger Context Window, Fewer Overcorrections: Optimizing Prompts and Batching for Minimal-Edit Grammatical Error Correction

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Minimal-edit Grammatical Error Correction (GEC) is a challenging task for zero- and few-shot prompted Large Language Models (LLMs), which systematically overcorrect and degrade $F_{0.5}$ by rewriting well-formed spans. While fine-tuning provides an effective solution, it imposes substantial infrastructure demands. We introduce a prompt-based approach that closes the gap to fine-tuned models through three advances in GEC prompting methodology. First, we introduce taxonomy-based instructions to enforce minimal-edit constraints with a comprehensive list of grammatical error rules, equipping the L

Read original source ↗ Open in workspace

recordType

paper

region

Global