arXiv:2608. 13695v1 Announce Type: cross Abstract: Large language model providers routinely cite multilingual safety benchmarks spanning a dozen or more languages as evidence that their models are safe for non-English-speaking users.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.
arXiv:2605. 17173v2 Announce Type: replace-cross Abstract: Large language models exhibit safety degradation in non-English languages.
arXiv:2608. 14626v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved substantial progress in safety alignment, yet their safety guarantees remain significantly weaker in low-resource and multilingual settings than in high-resource languages.
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.
arXiv:2608. 05163v1 Announce Type: cross Abstract: A common assumption holds that switching to a non-English language makes a multilingual RAG system easier to attack for personal information.
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.
arXiv:2607. 02079v1 Announce Type: cross Abstract: We present HaloGuard 1.