SweEval: Do LLMs Really Swear? A Safety Benchmark for Testing Limits for Enterprise Use
This addresses the need for enterprises to mitigate reputational risks and ensure compliance when deploying LLMs across diverse regions, though it is incremental as it builds on existing safety benchmarking efforts.
The paper tackles the problem of ensuring Large Language Models (LLMs) generate safe and respectful responses for enterprise use by introducing SweEval, a benchmark that tests LLMs' compliance with inappropriate instructions to include swear words, evaluating their alignment with ethical and cultural standards.
Enterprise customers are increasingly adopting Large Language Models (LLMs) for critical communication tasks, such as drafting emails, crafting sales pitches, and composing casual messages. Deploying such models across different regions requires them to understand diverse cultural and linguistic contexts and generate safe and respectful responses. For enterprise applications, it is crucial to mitigate reputational risks, maintain trust, and ensure compliance by effectively identifying and handling unsafe or offensive language. To address this, we introduce SweEval, a benchmark simulating real-world scenarios with variations in tone (positive or negative) and context (formal or informal). The prompts explicitly instruct the model to include specific swear words while completing the task. This benchmark evaluates whether LLMs comply with or resist such inappropriate instructions and assesses their alignment with ethical frameworks, cultural nuances, and language comprehension capabilities. In order to advance research in building ethically aligned AI systems for enterprise use and beyond, we release the dataset and code: https://github.com/amitbcp/multilingual_profanity.