Prompting open-source and commercial language models for grammatical error correction of English learner text

TL;DR

This study evaluates the effectiveness of various open-source and commercial large language models in correcting English grammatical errors, revealing nuanced performance differences across models and benchmarks.

Contribution

It provides a comprehensive comparison of multiple LLMs on GEC benchmarks, highlighting conditions where open-source models outperform commercial ones and the impact of prompting strategies.

Findings

Commercial LLMs excel in fluency correction benchmarks.

Open-source models outperform commercial ones on minimal edit benchmarks.

Zero-shot prompting can be as effective as few-shot prompting.

Abstract

Thanks to recent advances in generative AI, we are able to prompt large language models (LLMs) to produce texts which are fluent and grammatical. In addition, it has been shown that we can elicit attempts at grammatical error correction (GEC) from LLMs when prompted with ungrammatical input sentences. We evaluate how well LLMs can perform at GEC by measuring their performance on established benchmark datasets. We go beyond previous studies, which only examined GPT* models on a selection of English GEC datasets, by evaluating seven open-source and three commercial LLMs on four established GEC benchmarks. We investigate model performance and report results against individual error types. Our results indicate that LLMs do not always outperform supervised English GEC models except in specific contexts -- namely commercial LLMs on benchmarks annotated with fluency corrections as opposed to minimal edits. We find that several open-source models outperform commercial ones on minimal edit benchmarks, and that in some settings zero-shot prompting is just as competitive as few-shot prompting.