Glossary

Hallucination

What is Hallucination?

A hallucination is output from an AI model that sounds convincing but is wrong or entirely made up – such as a non-existent court ruling, an incorrect figure or an invented source. The cause: language models produce likely wording; they do not automatically look up facts. The risk falls when answers are based on verified sources, evidence is cited and people check important results.

How KI.ordo helps

KI.ordo agents answer from the knowledge you provide, cite their sources and say openly when they do not know something; the template ‘Fact-check against your own knowledge’ helps with verification – errors still cannot be ruled out entirely.

Learn more →

Matching templates

Fact-check against your own knowledgeChecks the statements in a text against your knowledge sources and marks each one as supported, not supported or contradicted – with the source passage.View template →

Topics

Language models
Reliability
Risk

Try KI.ordo

Agents, flows and templates in one workspace – free 24-hour demo.

Start demo

← All terms

Related terms

Retrieval-augmented generation (RAG)

Retrieval-augmented generation combines search with text generation: before answering, the system searches a knowledge collection – such as manuals, policies or FAQs – for relevant passages and passes them to the language model as context. The answer is therefore based on current, company-specific content rather than only on the model's training knowledge. This reduces invented statements, makes sources traceable and allows updates without retraining.

RAG
knowledge search
+1

Knowledge Cutoff

The knowledge cutoff is the point in time up to which a language model's training data extend. The model has no inherent knowledge of events, prices, laws or products that emerged afterwards and may give outdated information unless it is supplied with current data. This can be addressed by methods that bring in your own documents or current web content at run time.

LLM
Up-to-dateness
+1

Large language model (LLM)

A large language model (LLM) is a neural network trained on very large amounts of text, enabling it to understand and generate language. It works by calculating the most likely next token, step by step. LLMs write, summarise, translate, answer questions and generate code; well-known examples include Claude, GPT, Gemini and Llama. Without access to current sources, they only know what was in their training data.

Language models
Generative AI
+1

Human-in-the-Loop

Human-in-the-loop describes workflows in which people step into an AI process at defined points: they review results, approve or correct them, or take over difficult cases. The principle reduces the risk of faulty output and keeps accountability with people, especially for decisions affecting individuals, money or legal matters. Example: an AI agent drafts replies to customer enquiries and a member of staff checks them before they are sent.

Approval
Oversight
+1