Trust and Safety with LLM¶
The Guardrails service enhances the security of LLM-based applications by offering a suite of microservices designed to ensure trustworthiness, safety, and security.
MicroService |
Description |
Contributors |
---|---|---|
Detects Biased language (framing bias, epistemological bias, and demographic bias) |
Intel |
|
Detects hallucination by checking for factual consistency between two text passages |
PredictionGuard |
|
Provides general guardrails for inputs and outputs to ensure safe interactions using Llama Guard or WildGuard |
Intel |
|
Detects hallucination given a text document, question and answer |
Intel |
|
Detects Personally Identifiable Information (PII) and Business Sensitive Information (BSI) |
Prediction Guard |
|
Detects malicious prompts causing the system running an LLM to execute the attacker’s intentions |
Intel, PredictionGuard |
|
Detects Toxic language (rude, disrespectful, or unreasonable language that is likely to make someone leave a discussion) |
Intel, Prediction Guard |
Additional safety-related microservices will be available soon.