MDL
wildguard
allenai
Capability
—
percentile index
Downloads
118.9K
on HF
Likes
47
Avg score
—
Weights
Open
Released
Jun 15, 2024
About
wildguard is a open-weights model in the wildguard family from allenai.
apache-2.0text-generation
Benchmark scores · 0
No benchmark scores yet.
The research behind this model
all papers mentioning it →WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing▲ 39 on HF · May 25, 2026Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful ContentMay 28, 2026Reflect-Guard: Enhancing LLM Safeguards against Adversarial Prompts via Logical Self-ReflectionMay 24, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.