Benchmarking LLM Guardrails in Handling Multilingual Toxicity
This work addresses the challenge of ensuring safe and trustworthy LLMs in multilingual applications, but it is incremental as it benchmarks existing methods without proposing new solutions.
The paper tackled the problem of evaluating how well existing guardrails for Large Language Models handle toxic content across multiple languages, finding that they are ineffective and lack robustness against jailbreaking techniques.
With the ubiquity of Large Language Models (LLMs), guardrails have become crucial to detect and defend against toxic content. However, with the increasing pervasiveness of LLMs in multilingual scenarios, their effectiveness in handling multilingual toxic inputs remains unclear. In this work, we introduce a comprehensive multilingual test suite, spanning seven datasets and over ten languages, to benchmark the performance of state-of-the-art guardrails. We also investigates the resilience of guardrails against recent jailbreaking techniques, and assess the impact of in-context safety policies and language resource availability on guardrails' performance. Our findings show that existing guardrails are still ineffective at handling multilingual toxicity and lack robustness against jailbreaking prompts. This work aims to identify the limitations of guardrails and to build a more reliable and trustworthy LLMs in multilingual scenarios.