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