Explanation based In-Context Demonstrations Retrieval for Multilingual Grammatical Error Correction

TL;DR

This paper introduces a novel retrieval method using grammatical error explanations to select effective in-context examples for multilingual grammatical error correction with large language models, improving performance without extra training.

Contribution

It proposes a new retrieval approach based on natural language explanations of errors, enhancing few-shot GEC performance across multiple languages without additional training.

Findings

Outperforms semantic and BM25 retrieval methods

Effective across five languages

No additional training or language adaptation needed

Abstract

Grammatical error correction (GEC) aims to correct grammatical, spelling, and semantic errors in natural language text. With the growing of large language models (LLMs), direct text generation has gradually become the focus of the GEC methods, and few-shot in-context learning presents a cost-effective solution. However, selecting effective in-context examples remains challenging, as the similarity between input texts does not necessarily correspond to similar grammatical error patterns. In this paper, we propose a novel retrieval method based on natural language grammatical error explanations (GEE) to address this issue. Our method retrieves suitable few-shot demonstrations by matching the GEE of the test input with that of pre-constructed database samples, where explanations for erroneous samples are generated by LLMs. We conducted multilingual GEC few-shot experiments on both major open-source and closed-source LLMs. Experiments across five languages show that our method outperforms existing semantic and BM25-based retrieval techniques, without requiring additional training or language adaptation. This also suggests that matching error patterns is key to selecting examples.