Qorgau: Evaluating LLM Safety in Kazakh-Russian Bilingual Contexts
This addresses safety risks for users in Kazakhstan, where bilingual contexts are often overlooked, though it is incremental as it extends existing evaluation methods to a new region.
The paper tackles the problem of evaluating LLM safety in bilingual contexts, specifically Kazakh and Russian, by introducing the Qorgau dataset and finding notable differences in safety performance compared to monolingual settings.
Large language models (LLMs) are known to have the potential to generate harmful content, posing risks to users. While significant progress has been made in developing taxonomies for LLM risks and safety evaluation prompts, most studies have focused on monolingual contexts, primarily in English. However, language- and region-specific risks in bilingual contexts are often overlooked, and core findings can diverge from those in monolingual settings. In this paper, we introduce Qorgau, a novel dataset specifically designed for safety evaluation in Kazakh and Russian, reflecting the unique bilingual context in Kazakhstan, where both Kazakh (a low-resource language) and Russian (a high-resource language) are spoken. Experiments with both multilingual and language-specific LLMs reveal notable differences in safety performance, emphasizing the need for tailored, region-specific datasets to ensure the responsible and safe deployment of LLMs in countries like Kazakhstan. Warning: this paper contains example data that may be offensive, harmful, or biased.