GovTech Singapore has launched LionGuard 2, an upgraded content moderation guardrail designed for Singapore’s multilingual large-language models (LLMs). Content moderation guardrails act as filters or constraints that prevent LLMs from generating harmful, biased, or inappropriate content. LionGuard 2 now supports all four of Singapore’s official languages—English, Chinese, Malay, and partially Tamil—addressing the nation’s unique linguistic landscape, including colloquial Singlish and frequent code-switching. The model has demonstrated significant improvements in accuracy, achieving an F1 score of 87%, up from 58.4% in its predecessor, and is currently deployed on the Singapore government’s AI Guardian platform. LionGuard 2 is available as an open-source API service for any text-centric LLM system, facilitating broader adoption and ensuring robust content moderation across various applications.
Click here for the official article/release
Disclaimer
The Legal Wire takes all necessary precautions to ensure that the materials, information, and documents on its website, including but not limited to articles, newsletters, reports, and blogs (“Materials”), are accurate and complete. Nevertheless, these Materials are intended solely for general informational purposes and do not constitute legal advice. They may not necessarily reflect the current laws or regulations. The Materials should not be interpreted as legal advice on any specific matter. Furthermore, the content and interpretation of the Materials and the laws discussed within are subject to change.
