{"ID":2896899,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.05686","arxiv_id":"2507.05686","title":"Smoothie-Qwen: Post-Hoc Smoothing to Reduce Language Bias in Multilingual LLMs","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2507.05686","url_pdf":"https://arxiv.org/pdf/2507.05686v1","authors":"[\"SeungWon Ji\",\"Jungyup Lee\",\"Jemin Kim\",\"Sang Park\",\"SeungJae Lee\"]","published":"2025-07-08T05:30:51Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}