Arabic Dataset for LLM Safeguard Evaluation
This addresses the problem of LLM safety for Arabic users, but it is incremental as it adapts existing evaluation methods to a new linguistic and cultural context.
The authors tackled the under-explored safety of large language models (LLMs) in Arabic by creating a culturally specific dataset of 5,799 questions and a dual-perspective evaluation framework, revealing substantial disparities in safety performance across five LLMs.
The growing use of large language models (LLMs) has raised concerns regarding their safety. While many studies have focused on English, the safety of LLMs in Arabic, with its linguistic and cultural complexities, remains under-explored. Here, we aim to bridge this gap. In particular, we present an Arab-region-specific safety evaluation dataset consisting of 5,799 questions, including direct attacks, indirect attacks, and harmless requests with sensitive words, adapted to reflect the socio-cultural context of the Arab world. To uncover the impact of different stances in handling sensitive and controversial topics, we propose a dual-perspective evaluation framework. It assesses the LLM responses from both governmental and opposition viewpoints. Experiments over five leading Arabic-centric and multilingual LLMs reveal substantial disparities in their safety performance. This reinforces the need for culturally specific datasets to ensure the responsible deployment of LLMs.