Taxonomy-Adaptive Moderation Model with Robust Guardrails for Large Language Models
By: Mahesh Kumar Nandwana , Youngwan Lim , Joseph Liu and more
Large Language Models (LLMs) are typically aligned for safety during the post-training phase; however, they may still generate inappropriate outputs that could potentially pose risks to users. This challenge underscores the need for robust safeguards that operate across both model inputs and outputs. In this work, we introduce Roblox Guard 1.0, a state-of-the-art instruction fine-tuned LLM designed to enhance the safety of LLM systems through comprehensive input-output moderation, using a pipeline of LLMs to enhance moderation capability. Built on the Llama-3.1-8B-Instruct backbone, our model is instruction fine-tuned to generalize across previously unseen safety taxonomies and demonstrates strong performance on out-of-domain safety benchmarks. The instruction fine-tuning process uses a mix of synthetic and open-source safety datasets, augmented with chain-of-thought (CoT) rationales and input inversion to enhance contextual understanding and decision making. To support systematic evaluation, we also release RobloxGuard-Eval, a new benchmark featuring an extensible safety taxonomy to assess the effectiveness of LLM guardrails and moderation frameworks.
Similar Papers
Evaluating the Robustness of Large Language Model Safety Guardrails Against Adversarial Attacks
Cryptography and Security
Makes AI safer from bad instructions.
Protect: Towards Robust Guardrailing Stack for Trustworthy Enterprise LLM Systems
Computation and Language
Keeps AI safe with text, pictures, and sounds.
Towards Safer AI Moderation: Evaluating LLM Moderators Through a Unified Benchmark Dataset and Advocating a Human-First Approach
Artificial Intelligence
Makes AI understand hate and bias better.