This work investigates cross-lingual safety transfer in four African languages, Twi, Hausa, Amharic, and Swahili, using LoDNA, a new safety dataset that pairs literal translations with culturally localized prompts to demonstrate superficial safety alignment.
Abstract
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. We investigate cross-lingual safety transfer in four African languages, Twi, Hausa, Amharic, and Swahili, using LoDNA, a new safety dataset that pairs literal translations with culturally localized prompts. To move beyond generation-based evaluation, we propose a latent geometric framework that probes hidden-state refusal representations in LLMs. Our experimental results show that cross-lingual safety transfer is severely limited; harmful prompts retain less than 10% of the English refusal signal across most language-model pairs. Literal and localized prompts are semantically aligned (cosine 0.95-0.996) but drift across layers, suggesting models encode the concepts without routing them to safety mechanisms. These findings demonstrate that current multilingual safety alignment is superficial, providing strong evidence against the assumption of a universal, language-agnostic harm manifold within the specific low-resource languages studied. Warning: This paper contains example data that may be offensive or harmful.
It is shown that English-only safety evaluations are insufficient; they require accounting for script family, perturbation type, and per-language alignment coverage, and a geometric mechanistic analysis of refusal failure across language tiers.
Current safety alignment training for Large Language Models (LLMs) are heavily English-centric. When such safety filters fail for non-English languages, the consequences are immediate and user-facing: voice assistants and spoken dialogue systems may produce stereotype-reinforcing outputs, bypassing the standard English-focused safety alignments and propagating harmful bias to non-English speaking communities. For spoken language technologies deployed across India's linguistically diverse population, this represents a critical failure mode. To address this cross-lingual gap, we introduce INCLUDE (Indian Cultural Lens for Understanding and Detecting Embedded Biases), a multilingual evaluation benchmark designed to quantify Indian-centric socio-cultural biases. INCLUDE consists of 2,604 prompts spanning six prompt languages: English, Hindi, Bengali, Marathi, Tamil, and Hinglish (Hindi-English code-mix). We evaluate ten open- and closed-source LLMs against this benchmark, analyzing 14,988 bias scores. Our statistical results reveal two key findings. First, Bengali yielded the highest average bias score in open-source models. Second, English demonstrated a notable reversal, producing the lowest bias in open-source models but the highest bias in closed-source models.
The findings suggest that activation steering may provide a practical, low- cost mechanism for extending English-derived safety signals to other languages, and introduce a multilingual translation-and-evaluation pipeline to facilitate future work on cross-lingual safety interventions.
Emma V. Stein, Dominik Meier, Terry Ruas et al.· 0 citations
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. In this paper, we conduct a Systematic Literature Review (SLR) of LLM safety alignment in low-resource languages by adopting the PRISMA 2020 methodology. Out of roughly 1,500 papers identified from Semantic Scholar, arXiv, and OpenAlex, 50 relevant studies have been selected and analyzed. Our review is organized around four themes: safety alignment methods, multilingual safety risks, evaluation benchmarks, and cross-lingual transferability. We further propose a taxonomy of safety alignment approaches based on three adaptation mechanisms: data adaptation, objective optimization, and mechanistic alignment. Across literature, translated English benchmarks fail to sufficiently represent culturally rooted harms, and multilingual models are more vulnerable to cross-lingual jailbreaks, code-switching attacks, and safety degradation in underrepresented languages. These failures are driven by several key factors, including uneven multilingual pre-training coverage, insufficient native-language preference data, poor transfer of safety representations, and a lack of culturally aware evaluation frameworks. The review also notes that many low-resource languages, especially African languages, have fewer safety benchmarks available than other multilingual regions. Overall, the results reveal a persistent multilingual safety gap, and suggest that future progress will require culturally grounded benchmarks, participatory data collection, balanced multilingual pre-training, and scalable multilingual alignment methods.
Valdini Douglace Lemofouet, Blessing Ngozi Uzor, Paula Chikaodinaka Anyanwu et al.· 0 citations
SurakshaEval is introduced, a novel safety benchmark composed of human-written prompts spanning real-world scenarios, explicitly designed for ten major Indian languages - Assamese, Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Punjabi, Tamil, and Telugu - along with English.
Debopriyo Banerjee, K. R. Kavitha, Angana Borah et al.· 0 citations
This work investigates the impact of cross-lingual prompt injection attacks on LLM-based relevance judgments using TREC Deep Learning collections and two open-weight models under established prompting frameworks, and demonstrates that multilingual query-based injections are highly effective in inflating relevance scores while simultaneously evading existing prompt-injection defenses.
