Evaluating Prompting Strategies for Grammatical Error Correction Based on Language Proficiency

TL;DR

This paper investigates how different prompting strategies and model fine-tuning affect grammatical error correction in English learners, revealing that overcorrection is more common in advanced learners and that certain methods may reduce recall.

Contribution

It introduces an analysis of LLM performance on GEC tasks tailored to learners' proficiency levels, highlighting the impact of prompting and fine-tuning on correction accuracy.

Findings

Overcorrection occurs mainly in advanced learners' writing.

Fine-tuning and few-shot prompting can decrease recall.

Proficiency level influences GEC model performance.

Abstract

The writing examples of English language learners may be different from those of native speakers. Given that there is a significant differences in second language (L2) learners' error types by their proficiency levels, this paper attempts to reduce overcorrection by examining the interaction between LLM's performance and L2 language proficiency. Our method focuses on zero-shot and few-shot prompting and fine-tuning models for GEC for learners of English as a foreign language based on the different proficiency. We investigate GEC results and find that overcorrection happens primarily in advanced language learners' writing (proficiency C) rather than proficiency A (a beginner level) and proficiency B (an intermediate level). Fine-tuned LLMs, and even few-shot prompting with writing examples of English learners, actually tend to exhibit decreased recall measures. To make our claim concrete, we conduct a comprehensive examination of GEC outcomes and their evaluation results based on language proficiency.