Hallucination
When AI models generate plausible-sounding but factually incorrect or fabricated information.
In-depth explanation
LLMs can confidently produce false statements, invented citations, or nonsensical content. This occurs because they learn statistical patterns rather than true understanding. Mitigation strategies include RAG (grounding in sources), fine-tuning on factual data, and retrieval verification. Detecting and reducing hallucinations is a major research focus.
Examples
More in Generative AI
GPT
Generative Pre-trained Transformer, a family of large language models trained to generate text.
Large Language Model (LLM)
AI models trained on vast text data that can generate and understand human-like text.
Prompt Engineering
The practice of crafting effective inputs to get desired outputs from AI models.
Generative Adversarial Network (GAN)
Two neural networks competing against each other to generate realistic synthetic data.
Diffusion Model
Generative models that learn to create data by reversing a gradual noising process.
RAG (Retrieval-Augmented Generation)
Combining retrieval systems with language models to generate responses grounded in external knowledge.
Master Hallucination.
Learn how to apply this concept with hands-on projects in our comprehensive AI programs.