Garak Refusal Detector Description: Garak Refusal Detector is a binary sequence classifier model that detects refusal responses in LLM outputs. The model is built as a semantic replacement for string based keyword detectors (e.g., Garak's MitigationBypass detector), enabling refusal detection based on meaning rather than surface patterns. This model is ready for commercial use. Key Features: Semantic refusal detection based on transformer classification Trained on 20K synthetic samples generated via NeMo Data Designer covering: 5 compliance degrees: complete refusal, partial refusal, refusal with redirection, full fulfillment, fulfillment with disclaimer 7 refusal communication styles: direct ethical, policy based, brief decline, educational, censorship, misinformation, disclaimer technical License/Terms of Use: Governing Terms: Use of this model is governed by the NVIDIA Open Model License. Deployment Geography: Global Use Case: Developers integrating the Garak framework can use this model to detect refusal responses in LLM outputs. It serves as an alternative to keyword‑based detectors, using a transformer‑based classifier that returns a binary signal indicating refusal or non‑re…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy