@inproceedings{dunca-etal-2025-mulbere,
    title = "{MULBERE}: Multilingual Jailbreak Robustness Using Targeted Latent Adversarial Training",
    author = "Dunca, Anastasia  and
      Sharma, Maanas Kumar  and
      Munoz, Olivia  and
      Rosales, Victor",
    editor = "Zhang, Chen  and
      Allaway, Emily  and
      Shen, Hua  and
      Miculicich, Lesly  and
      Li, Yinqiao  and
      M'hamdi, Meryem  and
      Limkonchotiwat, Peerat  and
      Bai, Richard He  and
      T.y.s.s., Santosh  and
      Han, Sophia Simeng  and
      Thapa, Surendrabikram  and
      Rim, Wiem Ben",
    booktitle = "Proceedings of the 9th Widening NLP Workshop",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.winlp-main.27/",
    pages = "175--181",
    ISBN = "979-8-89176-351-7",
    abstract = "Jailbreaking, the phenomenon where specific prompts cause LLMs to assist with harmful requests, remains a critical challenge in NLP, particularly in non-English and lower-resourced languages. To address this, we introduce MULBERE, a method that extends the method of Targeted Latent Adversarial Training (T-LAT) to a multilingual context. We first create and share a multilingual jailbreak dataset spanning high-, medium-, and low-resource languages, and then fine-tune LLaMA-2-7b-chat with interleaved T-LAT for jailbreak robustness and chat examples for model performance. Our evaluations show that MULBERE reduces average multilingual jailbreak success rates by 75{\%} compared to the base LLaMA safety training and 71{\%} compared to English-only T-LAT while maintaining or improving standard LLM performance."
}