arXiv:2602. 13452v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly proposed for crisis preparedness and response, particularly for multilingual communication.
By Belu Ticona, Antonis Anastasopoulos
The article investigates whether commercial machine translation (MT) tools—Google Translate, Microsoft Translator, GPT, Gemini, and Claude—are ready to support communication during crises or pandemics. Using the TICO-19 dataset, which contains pandemic-related sentences in high-priority low-resource languages, the study evaluates the usability of translations produced by these systems. The goal is to determine how effectively these MT tools can bridge language gaps between governments, aid providers, medical professionals, and affected communities.
By Vipasha Bansal, William D. Lewis, Nicole Mihaylova, Elizabeth Brown, Benjamin Pong
arXiv:2610.32842v1 Announce Type: new
Abstract: It is essential that we communicate with the entirety of an affected population during a crisis, including those who do not speak a region's dominant l...
By Jen Wilson, Vipasha Bansal, William D. Lewis
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
The paper introduces MSafeTemp, a large multilingual safety alignment corpus covering 60 languages, created via a template-based augmentation pipeline that extracts safe templates from harmful prompts, translates them, and fills slots with culturally authentic entities. The authors demonstrate that evaluating safety solely in English can misjudge multilingual performance, as attacks that fail in English may succeed when translated, and culturally localized variants reveal additional failures. They also show that augmenting safety training data with these templates improves safety performance beyond English.
By Max Neuwinger, Hanna Yukhymenko, Imanol Schlag
The paper introduces MMSAFE, a multi-layer framework designed to identify safety-degrading data in multilingual large language models. It shows that safety signals are distributed across multiple layers and only partially shared across languages, unlike the single-layer assumption used in monolingual settings. Experiments demonstrate that MMSAFE reduces harmful-response rates by 60% compared to random filtering and outperforms the best single-layer baseline across various models, languages, and safety benchmarks.
By Jiakun Li, Guowei Song, Sijia Li, Xingwei He, Hongzheng Chai, Yuan Yuan