Can Code-Switched Texts Activate a Knowledge Switch in LLMs? A Case Study on English-Korean Code-Switching
This addresses the challenge of limited resources for low-resource languages in multilingual LLMs, though it is incremental as it builds on existing multilingual abilities.
The study investigated whether code-switching can activate knowledge in large language models for low-resource language tasks, using a synthetic English-Korean dataset, and found that code-switching effectively activates knowledge, especially in language-specific domains.
Recent large language models (LLMs) demonstrate multilingual abilities, yet they are English-centric due to dominance of English in training corpora. The limited resource for low-resource languages remains a crucial challenge. Code-switching (CS), a phenomenon where multilingual speakers alternate between languages in a discourse, can convey subtle cultural and linguistic nuances that can be otherwise lost in translation and elicits language-specific knowledge in human communications. In light of this, we investigate whether code-switching can activate, or identify and leverage knowledge for reasoning when LLMs solve low-resource language tasks. To facilitate the research, we first present EnKoQA, a synthetic English-Korean CS question-answering dataset. We provide comprehensive analysis on a variety of multilingual LLMs by subdividing activation process into knowledge identification and knowledge leveraging. Our results demonstrate that compared to English text, CS can faithfully activate knowledge inside LLMs especially on language-specific domains, suggesting the potential of code-switching on low-resource language tasks.