Agentic AI Reference Architecture

Safety & Security · Software component

NLI Fact Checker

Software componentSafety & SecuritySafety, Security & Governancearc:NLIFactChecker

A fact checking rail that classifies each claim as entailed by, contradicting, or neutral to source documents using a specialized natural language inference model.

Responsibility. Verifies claims by entailment against source documents.

Also known as: NLI-based verification

Variant of Fact Checking Rail abstract

When to choose. Choose for technical support and tutoring where moderate latency (100-150ms) is acceptable.

specializesis target of alternativeTois invoked byinvokesalternative toFact Checking Rail: specializesFact Checking RailAlignment-Score Fact Checker: is target of alternativeToAlignment-Score Fact Che…Cascaded Fact Checker: is invoked byCascaded Fact CheckerNLI Scoring Service: invokesNLI Scoring ServiceSelf-Check LLM Fact Checker: alternative toSelf-Check LLM Fact Chec…
Direct neighbourhood (hover for relationship types)

Relationships

invokes dependency

is invoked by dependency

alternative to variability

Quantitative guidance

As stated by the sources; verify before use.

Classification

Quality attributes
Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)Performance efficiency (ISO/IEC 25010)

Sources

  1. Ch7.1A: T. Nguyen, "Advanced Implementation with Nvidia NEMO Framework and Nvlink," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 7.1A. ISBN: 9798244538229.