In one sentence
AI hallucinations are when an LLM invents false but plausible information and delivers it to you confidently as if it were true. Understanding why it happens and how to detect them has become essential.
🔍 Want an AI that cites its sources?
Compare models with integrated web search: Perplexity, Claude with MCP, Gemini grounded.
Why do LLMs hallucinate?
To understand, you need to remember how it works: an LLM predicts the next word based on the billions of sentences it's read. It doesn't have a verified knowledge base, it just has statistical probabilities.
The 4 types of hallucinations
Not all hallucinations are equal. Here's the typology:
The 4 types of hallucinations
| 🌀Type | 📝Typical example | |
|---|---|---|
| Factual | False facts, dates, figures | 'Einstein was born in 1880' (false: 1879) |
| Fabricated source | Citations of non-existent works | 'According to Smith et al. 2019, Journal of AI...' (doesn't exist) |
| Logical | False but convincing reasoning | 'If A then B, therefore C' with C not following |
| Contextual | Confusion between provided information | You provide 5 docs, it invents a detail between the 2 |
How often does it happen?
It's more frequent than you think. The official figures:
Hallucination rate by model (2026 benchmarks)
Reading: even the best 2026 models hallucinate 3-4% of the time on factual questions. Out of 100 answers, 3-4 contain an error. Out of 1,000 answers: 30-40 errors. That's not negligible.
When does it happen most?
Hallucinations that caused scandals
📚3 real cases that are scary
1. The lawyer who cited 6 invented case laws (2023)
A New York lawyer used ChatGPT to prepare a case file. He submitted to the judge 6 case laws that ChatGPT had... completely invented. The judge verified, sanctions fell: fine, professional reprimand.
Lesson: NEVER submit official AI content without verification.
2. Air Canada ordered to honour its chatbot's promises (2024)
Air Canada's chatbot invented a refund policy that didn't exist. A customer relied on it to buy a ticket. Air Canada refused to honour it. The court ruled: the company must refund, the chatbot is their responsibility.
Lesson: a company chatbot is legal liability for the company.
3. Google Bard at 100 billion (2023)
During its launch demo, Bard (Google) claimed that the James Webb telescope had taken the first photo of an exoplanet. That's false (it was another telescope, in 2004). The error was spotted by astronomers in real time. Google stock -8%, or 100 billion in market cap lost.
Lesson: hallucinations cost really expensive in the real world.
How to detect a hallucination
Not easy, by design (it's plausible). But here are the red flags:
Technical solutions to reduce hallucinations
Technical solutions 2026
| 🛠️Solution | 📉Hallucination reduction | |
|---|---|---|
| RAG (Retrieval Augmented Generation) | Forces the model to cite a database | -70% to -90% |
| Chain-of-thought prompting | Force step-by-step reasoning | -30% to -50% |
| Self-consistency | Generate 5 answers, take the majority | -20% to -40% |
| Integrated web search | Real-time connection to Google/Bing | -60% to -80% |
| Reasoning models (o1, Opus thinking) | The model 'thinks' before responding | -40% to -60% |
| Fine-tuning on your data | Specialize the model on your domain | -50% on your domain |
RAG: the star solution
RAG (Retrieval Augmented Generation) has become the technique to limit hallucinations in enterprises. The principle:
How RAG works
You ask a question
The system receives your prompt.
Search in a database
The system searches your documents (PDFs, database) for relevant passages.
Context injection
The found passages are sent to the LLM along with the question.
Anchored response
The LLM responds based on the provided documents, with citations.
Result: instead of inventing, the LLM cites real passages. Hallucinations divided by 5 to 10.
📚 Want to understand RAG in detail?
We explain RAG simply, with the tools and costs to implement it.
Use cases where NOT to trust an LLM alone
The metaphor that sums it all up
Absolutely remember
- ✅ All LLMs hallucinate: 3-4% for the best, 10-25% for older ones
- ✅ Risk zones: niche, recent, citations, precise figures, obscure code
- ✅ Always verify critical facts, especially for professional use
- ✅ To reduce: RAG, chain-of-thought, reasoning models, web search
- ❌ Never a final decision on medical, legal, financial based on AI alone
Understanding hallucinations means avoiding disasters. AI is a great assistant, not an oracle.
Why does an LLM hallucinate?
To go further
- 📚 RAG explained simply, the star solution
- ⚙️ How ChatGPT works in 5 minutes
- 🔒 AI and confidentiality