Glossary › LLM

Hallucination

When a model generates plausible-sounding but factually incorrect content. Caused by: training data patterns, no real-world grounding, high temperature. Mitigated by: RAG, citations, lower temperature.

Where this is taught

• Hallucination Detection & Mitigation — Phase 2b: LLM-Specific Responsible AI
• Measuring Hallucination, Bias & Safety — Phase 5: Evaluation & Quality for AI Products
• The Slopsquatting Attack Vector — Phase 6: Supply Chain Security & Slopsquatting
• Model Capabilities & Limitations — Phase 1: AI & ML Literacy for PMs
• Designing for Failure — Phase 4: Writing AI Product Requirements
• When AI Leads You Astray — Phase 8: Security, Privacy, and Judgment Traps

Related terms

RAG

More in LLM

Temperature · Token · Context Window · Top-p (Nucleus Sampling) · In-Context Learning · System Prompt · Function Calling

Learn this by building

DeVenture Academy teaches AI engineering through projects, with hands-on labs you run on your own machine using real tools.

Create a free account — the opening phases of 29 of 35 courses are free, no credit card. Or see Pro pricing.

All courses · Pricing · About · FAQ · Glossary