CrisiLangs is a multilingual extension of the CrisiText dataset, adding Italian, Bulgarian, German, and Greek translations of warning messages for 1,000 crisis events, resulting in 5,000 event‑message pairs across five languages. The resource was used to fine‑tune a multilingual model, which outperformed a zero‑shot baseline on ROUGE‑L, BLEU, and BERTScore in every language and configuration. Human preference studies showed that low decoding temperatures were favored across all languages, while the impact of emergency guidelines varied by language.
arXiv:2602. 13452v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly proposed for crisis preparedness and response, particularly for multilingual communication.
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.
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...
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.
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.
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.
The paper introduces a framework to evaluate and diagnose the robustness of low‑resource multilingual text‑to‑speech systems when faced with complex text inputs such as numbers, dates, named entities, long sentences, code‑switched expressions, and punctuation structures. It assesses robustness across content consistency, language consistency, and generation stability, and proposes automatic metrics (character error rate, language ID accuracy, duration abnormal rate) along with a lightweight Text Risk Score (TRS) that predicts synthesis risk from interpretable text features. Experiments on Thai, Vietnamese, Swahili, and Indonesian TTS systems reveal distinct failure patterns and show that TRS correlates positively with content and duration errors, offering a low‑cost pre‑synthesis risk indicator.
The paper investigates how large language models (LLMs) can be bypassed by translating harmful requests from English into low‑resource languages. By testing ten popular LLMs across 79 languages, the authors find that safe English completions often fail to remain safe after translation, with bypass rates between 21.9% and 44.4%. The risk is unevenly distributed across language families and varies significantly between models, making it hard to rank models by safety consistently.
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.
arXiv:2610.08601v1 Announce Type: new Abstract: Emergency messaging such as extreme-weather reports and earthquake instructions can involve high stakes, to the extent that translation errors can lead...
IndicSafeEval is a new evaluation framework that tests the safety robustness of large language models against persuasion-based jailbreak attacks in Indian languages. The benchmark covers ten safety-critical content categories, six persuasive strategies, and four languages—Hindi, Bengali, Marathi, and Punjabi—producing 7,200 adversarial prompts. Experiments show that model safety varies significantly across languages, prompt styles, and risk categories, highlighting gaps in current English-centric safety assessments.
arXiv:2610.26474v2 Announce Type: replace Abstract: Large language models (LLMs) designed to interact with users are typically trained to respond appropriately to harmful or toxic content. However, e...