LionGuard 2: Building Lightweight, Data-Efficient & Localised Multilingual Content Moderators Paper โข 2507.15339 โข Published Jul 21, 2025 โข 1
Running 6 Responsible AI Benchmark ๐ 6 Evaluating safety, robustness & fairness for real use-cases
LionGuard: Building a Contextualized Moderation Classifier to Tackle Localized Unsafe Content Paper โข 2407.10995 โข Published Jun 24, 2024 โข 2
A Flexible Large Language Models Guardrail Development Methodology Applied to Off-Topic Prompt Detection Paper โข 2411.12946 โข Published Nov 20, 2024 โข 22
A Flexible Large Language Models Guardrail Development Methodology Applied to Off-Topic Prompt Detection Paper โข 2411.12946 โข Published Nov 20, 2024 โข 22