Safety alignment in large language models (LLMs) is largely developed in English, assuming these safeguards generalize across multilingual settings. However, this assumption remains underexplored and exposes a vulnerability in low-resource languages.
PRISM is a framework that evaluates how activation interventions transfer across precision, languages, and model scales to mitigate unsafe tool‑calling behaviors in language models. By leveraging lower‑resource settings such as quantized NF4 labels and cross‑lingual transfer, PRISM demonstrates that alignment improvements can be achieved with minimal scenarios and that these gains transfer to held‑out languages and larger models. The study shows that auxiliary supervision from compressed models and multilingual data can effectively uncover and reduce hazardous tool‑calling behaviors across different model families.
By Giovana Kerche Bon\'as, Thales Sales Almeida, Marcelo da Silva Reis, Rodrigo Nogueira, Marcos Meideiros Raimundo
arXiv:2607. 10112v1 Announce Type: cross Abstract: Safety alignment in large language models remains brittle across languages: prompts reliably refused in English can elicit harmful compliance in non-English and low-resource settings.
By Chigozirim Ifebi, Brent Kong, Ayushi Mehrotra
Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching. We show that this creates an epistemic gap in which models confidently generate harmful responses for inputs that fall outside the distribution of their safety training.
arXiv:2606. 28843v1 Announce Type: cross Abstract: Fine-tuning a large language model is a ubiquitous method for enhancing its capability on a specific downstream task.
By Will Hawkins, Kaivalya Rawal, Jonathan Rystr{\o}m, Stratis Tsirtsis, Zihao Fu, Greta Warren, Ryan Brown, Eoin Delaney, Sandra Wachter, Brent Mittelstadt, Chris Russell
arXiv:2606. 08451v1 Announce Type: cross Abstract: Safety-aligned large language models often exhibit sycophancy, which is the tendency to affirm users' opinions regardless of factual accuracy.
By Arya Shah, Himanshu Beniwal, Mayank Singh, Chaklam Silpasuwanchai