How I Aligned Your Model: Scaling Up Multilingual Safety Training with Templates

Max Neuwinger, Hanna Yukhymenko, Imanol Schlag

How I Aligned Your Model: Scaling Up Multilingual Safety Training with Templates: 7 upvotes on Hugging Face Daily Papers, #27 of 38 papers on 2026-11-05. Day-by-day upvote history.

Upvotes over time

It had 7 upvotes by its first day, 8 upvotes by the next day, 8 upvotes by day 3, 7 upvotes by day 7, and has 7 now. It ranked #134 of 207 papers in its week and #201 of 340 in its month. Its code repository has 1 GitHub stars.

Safety alignment for Large Language Models is heavily focused on English with limited multilingual representation, particularly damaging low-resource language performance. Related open training datasets are often limited in size or do not follow region-localized harmful topics to broaden the scope of alignment beyond cultures. We propose a scalable template-based augmentation pipeline to produce massive multilingual refusal and benign corpora, extracting safe templates from harmful prompts, translating them and then filling in the slots with culturally authentic entities, both harmful and benign. As a result, we release MSafeTemp, a validated corpus spanning 60 languages useful for multilingual safety alignment and evaluation. Using the dataset, we show that English-only evaluation misjudges multilingual safety: for several models, attacks that fail in English succeed once translated, while culturally localized variants expose further failures that translation alone misses. We also confirm that augmenting safety training data through templates allows for higher diversity and quality of alignment, resulting in improved safety performance beyond English. MSafeTemp and the respective pipeline are aimed at facilitating research and development of safer and more responsible models for less-represented cultures.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.