In 2023, a lawyer filed a brief citing six court rulings — all of which had been fabricated by ChatGPT. The case made headlines worldwide and became the prime example of AI hallucinations. Even in 2026, hallucinations are not fully solved, but the tools for containment have become significantly better. Understanding them allows you to deploy AI safely nonetheless.
📖 Definition: An AI hallucination is a model-generated statement that sounds plausible but is factually wrong — fabricated facts, non-existent sources, or logically incorrect conclusions.
LLMs are statistical text generators. They calculate the most probable next token (word or word fragment) based on the preceding context. This means:
💡 Tip: Hallucinations are not a bug but a feature of the architecture. Every LLM hallucinates — the question is how frequently and how you handle it.
| Type | Description | Example | Risk |
|---|---|---|---|
| 📚 Factual hallucination | Fabricated facts or events | "Company X's revenue in 2025 was exactly 4.7 billion euros" (entirely made up) | 🔴 High |
| 📄 Source fabrication | Citing non-existent sources | "According to a 2025 Harvard study…" (study does not exist) | 🔴 Very high |
| 🔢 Numeric hallucination | Wrong numbers, calculations | "23% of 450 is 115" (would actually be 103.5) | 🟡 Medium |
| 🔗 Logical hallucination | Correct facts, wrong conclusion | "A leads to B, B leads to C, therefore A directly leads to D" | 🟡 Medium |
⚠️ Caution: Source fabrication is particularly dangerous because it suggests trustworthiness. When an LLM cites a "study," always verify whether it actually exists — no matter how convincing the reference sounds.
Grounding refers to methods that anchor AI responses in verified facts:
| Technique | How It Works | Hallucination Reduction | Effort |
|---|---|---|---|
| 🔍 RAG (Retrieval-Augmented Generation) | Model first searches own knowledge base | ⬇️ 60–80% | Medium to high |
| 📎 Citations | Model must back each claim with a source | ⬇️ 40–60% | Low |
| 🌐 Web Search | Model accesses current web content | ⬇️ 50–70% | Low |
| 🔗 Combination RAG + Citations | Knowledge base plus source references | ⬇️ 80–95% | High |
🏢 Real-world example: A consulting firm implemented RAG with their internal knowledge base (15,000 documents). Before RAG, 23% of AI-generated reports contained factual errors. After RAG, the rate dropped below 3%. The investment paid for itself in 4 months.
Not all models hallucinate equally:
💡 Tip: For applications where accuracy is critical (law, finance, medicine), choose models with demonstrably low hallucination rates and combine them with RAG.
A proven four-stage process for safely handling AI output:
Stage 1: 🤖 AI generates response (with citation prompt)
Stage 2: 🔍 AI checks its own response for internal consistency
Stage 3: 📊 Automatic comparison with verified data sources
Stage 4: 👤 Human verifies critical facts and approves
Additional safeguards:
🔑 Remember: Trust AI output like a brilliant intern — impressively fast and often correct, but always worth checking. The more critical the application, the more verification needed.
🎯 Exercise: Ask the same LLM the same specialized question from your domain three times. Compare the answers — discrepancies are an indicator of hallucination risk. Document where the model responds consistently and where it is uncertain.
Next lesson: Data governance for AI projects — how to ensure compliance and data protection.
Warum halluzinieren LLMs?