From Standard English to Singlish: A Retrieval-Augmented Approach for Code-Switched Creole Generation in Large Language Models

TL;DR

This paper introduces a retrieval-augmented generation framework that externalizes dialectal knowledge into a lexicon, enabling controlled code-switching in large language models without fine-tuning.

Contribution

It presents a novel RAG approach for code-switching that leverages external lexical resources, improving control and preserving quality in dialectal language generation.

Findings

RAG performs minimal lexical substitutions with high semantic preservation.

Zero-shot prompting induces extensive paraphrasing.

Human evaluation shows RAG and zero-shot prompting are equally natural.

Abstract

Code-switching in contact varieties like Singaporean English (Singlish) challenges natural language generation due to limited parallel data and rapid lexical evolution. We propose a retrieval-augmented generation (RAG) framework that externalizes dialectal knowledge into a curated lexicon, enabling controlled lexical code-switching without fine-tuning. Our approach retrieves candidate Singlish expressions and guides generation through sparse lexical substitution. Human evaluation with 164 Singaporean participants found RAG and zero-shot prompting equally natural and appropriate. Automatic analyses reveal different transformation regimes: zero-shot prompting induces extensive paraphrasing (median 23 token edits), whereas RAG performs minimal substitutions (median 1 edit) with higher semantic preservation (mean cosine similarity 0.978 vs. 0.926). Our results demonstrate that externalizing code-switching into lexical resources enables control and auditability without sacrificing perceived quality, offering practical advantages for rapidly evolving contact varieties.