Skip to main content
Vijil evaluates LLM trustworthiness along 8 dimensions. For each dimension, it assesses vulnerability to several attack vectors. Each attack vector is treated as one evaluation module. Each module contains one or more tests:

Security

Learn more about Security

Privacy

Learn more about Privacy

Hallucination / Confabulation

Learn more about Hallucination / Confabulation

Robustness

Learn more about Robustness

Toxicity

Learn more about Toxicity

Stereotype

Learn more about Stereotype

Fairness

Learn more about Fairness

Ethics

Learn more about Ethics