Can LLMs Help Create Grammar?: Automating Grammar Creation for Endangered Languages with In-Context Learning

TL;DR

This paper investigates how Large Language Models can assist in creating grammatical rules and lexical data for endangered languages using in-context learning, demonstrating promising results with minimal data.

Contribution

It introduces a novel approach using LLMs and in-context learning to generate grammatical information for low-resource languages without training new models.

Findings

LLMs can generate coherent grammatical rules and lexical entries

The approach works with limited bilingual data and parallel sentences

Challenges include potential biases towards English grammar

Abstract

Yes! In the present-day documenting and preserving endangered languages, the application of Large Language Models (LLMs) presents a promising approach. This paper explores how LLMs, particularly through in-context learning, can assist in generating grammatical information for low-resource languages with limited amount of data. We takes Moklen as a case study to evaluate the efficacy of LLMs in producing coherent grammatical rules and lexical entries using only bilingual dictionaries and parallel sentences of the unknown language without building the model from scratch. Our methodology involves organising the existing linguistic data and prompting to efficiently enable to generate formal XLE grammar. Our results demonstrate that LLMs can successfully capture key grammatical structures and lexical information, although challenges such as the potential for English grammatical biases remain. This study highlights the potential of LLMs to enhance language documentation efforts, providing a cost-effective solution for generating linguistic data and contributing to the preservation of endangered languages.