Adapting Multilingual Models to Code-Mixed Tasks via Model Merging
Published in CODS-IKDD 2025, 2025
We study how model merging can be used to adapt multilingual language models to code-mixed tasks, combining strengths of monolingual and multilingual resources without full retraining.
Recommended citation: P. Kodali, V. Shivkumar, S. Joshi, M. Choudhary, P. Kumaraguru. (2025). "Adapting Multilingual Models to Code-Mixed Tasks via Model Merging." CODS-IKDD 2025.