top | item 44655646

Open-Source LLM Helps Safeguard Text Generation Prompts and Responses

2 points| moneil971 | 7 months ago |corp.roblox.com

1 comment

order

moneil971|7 months ago

Roblox’s LLM is currently outperforming popular LLM guardrail models on standard benchmarks. Roblox open-sourced both the LLM weights and the RoGuard-Eval benchmarking dataset.