Work

Beyond Monolingual Assumptions: A Survey on Code-Switched NLP in the Era of Large Language Models across Modalities

Year: 2026

Type: conference-paper

Abstract: Amidst the rapid advances of large language models (LLMs), most LLMs still struggle with mixed-language inputs, limited Codeswitching (CSW) datasets, and evaluation biases, which hinder their deployment in multilingual societies.This survey provides the first comprehensive analysis of CSW-aware LLM research, reviewing 327 studies spanning five research areas, 15+ NLP tasks, 30+ datasets, and 80+ languages.We categorize recent advances by architecture, training strategy, and evaluation methodology, outlining how LLMs have reshaped CSW modeling and identifying the challenges that persist.The paper concludes with a roadmap that emphasizes the need for inclusive datasets, fair evaluation, and linguistically grounded models to achieve truly multilingual capabilities.1 * Work done while interning at IIT Gandhinagar.Maria Riveena Arul, Vigneshwaran Shanmugasundaram, S Rajalakshmi, Bharathi Raja Chakravarthi, and C. N

Source: Proceedings of the conference - Association for Computational Linguistics. Meeting

DOI: 10.18653/v1/2026.acl-long.386

Authors: Rajvee Sheth, Samridhi Raj Sinha, Mahavir Patil, Himanshu Beniwal, Mayank Singh

Institutions: Indian Institute of Technology Gandhinagar, Sardar Vallabhbhai National Institute of Technology Surat

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: Arthritis National Research Foundation, National Research Foundation

OpenAlex ID: W4416392994