Linguistics Theory Meets LLM: Code-Switched Text Generation via Equivalence Constrained Large Language Models
This work addresses the problem of generating linguistically valid and fluent code-switched text for NLP applications, representing a novel integration of linguistic theory with LLMs rather than an incremental advance.
The paper tackles the challenge of generating natural code-switched text by integrating Equivalence Constraint Theory with large language models, resulting in significant improvements in quality over baseline LLMs as measured by human judgments and automatic metrics.
Code-switching, the phenomenon of alternating between two or more languages in a single conversation, presents unique challenges for Natural Language Processing (NLP). Most existing research focuses on either syntactic constraints or neural generation, with few efforts to integrate linguistic theory with large language models (LLMs) for generating natural code-switched text. In this paper, we introduce EZSwitch, a novel framework that combines Equivalence Constraint Theory (ECT) with LLMs to produce linguistically valid and fluent code-switched text. We evaluate our method using both human judgments and automatic metrics, demonstrating a significant improvement in the quality of generated code-switching sentences compared to baseline LLMs. To address the lack of suitable evaluation metrics, we conduct a comprehensive correlation study of various automatic metrics against human scores, revealing that current metrics often fail to capture the nuanced fluency of code-switched text. Additionally, we create CSPref, a human preference dataset based on human ratings and analyze model performance across ``hard`` and ``easy`` examples. Our findings indicate that incorporating linguistic constraints into LLMs leads to more robust and human-aligned generation, paving the way for scalable code-switching text generation across diverse language pairs.