5.3 Tools that make AI more trustworthy

Key points

1. NeMo Guardrails lets enterprise developers set boundaries for their large language model (LLM) apps. Topical guardrails keep chatbots on specific subjects. Safety guardrails limit the language and data sources the app uses.

   What NVIDIA says (3)

   “Topical guardrails ensure that chatbots stick to specific subjects.”

   — What Is Trustworthy AI?

   “Safety guardrails set limits on the language and data sources the apps use in their responses.”

   — What Is Trustworthy AI?

   “keeps AI language models on track by allowing enterprise developers to set boundaries for their applications.”

   — What Is Trustworthy AI?

2. A model card gives developers and users a clear, concise view of a model's capabilities. NVIDIA's Model Card++ adds four subsections: Bias, Explainability, Privacy, and Safety and Security.

   What NVIDIA says (2)

   “Four subsections detailing model-specific information concerning Bias, Explainability, Privacy, and Safety and Security.”

   — Enhancing AI Transparency and Ethical Considerations with Model Card++

   “They provide both developers and downstream users and beneficiaries with a clear understanding of an AI model’s capabilities in a clear and concise format.”

   — Enhancing AI Transparency and Ethical Considerations with Model Card++

3. Confidential computing encrypts application code, models and data while in use, not just at rest or in transit, using hardware-rooted Trusted Execution Environments (TEEs).

   What NVIDIA says (2)

   “Confidential computing secures AI workloads by encrypting application code, models, and data in use—not just at rest or in transit.”

   — What Is Confidential Computing?

   “It does this by creating hardware-rooted Trusted Execution Environments (TEEs) that are enforced by cryptographic attestation.”

   — What Is Confidential Computing?

4. NVIDIA defines explainable AI (XAI) as tools and techniques that help people better understand why a model makes certain decisions and how it works.

   What NVIDIA says (1)

   “is a set of tools and techniques used by organizations to help people better understand why a model makes certain decisions and how it works.”

   — What Is Explainable AI (XAI)?

Key terms

• NeMo Guardrails: An open-source library that adds programmable safety and topic rules around an LLM app.
• Confidential computing: Protecting data and models while in use inside hardware Trusted Execution Environments.
• Explainable AI: Tools and techniques that help people understand why a model made a decision.
• Model card / Model Card++: A document describing a model's capabilities; NVIDIA's version adds Bias, Explainability, Privacy, and Safety and Security sections.

Sample question

Which NVIDIA tool lets developers keep a large language model (LLM) chatbot on approved topics and set limits on language and data sources?