Multilingual large language models (LLMs) often exhibit language confusion, a tendency to generate responses in a dominant language irrespective of the prompt's language. To address this, we propose Smoothie-Qwen, a lightweight, post-hoc method that mitigates language bias without retraining. This technique selectively adjusts token-level output probabilities to effectively suppress undesired language generation. Applied to the Qwen model, our method reduces unintended Chinese output by over 95% while preserving task accuracy on multilingual benchmarks. This work provides a practical and efficient solution for enhancing the language controllability of LLMs, making them more reliable for global applications.
@article{arxiv.2507.05686,
title = {Smoothie-Qwen: Post-Hoc Smoothing to Reduce Language Bias in Multilingual LLMs},
author = {SeungWon Ji and Jungyup Lee and Jemin Kim and Sang Park and SeungJae Lee},
journal= {arXiv preprint arXiv:2507.05686},
year = {2025}
}