ORBiS TREE · ENGLISH DOCUMENT
Research →Hallucination in AI
A generated statement that is unsupported, fabricated, or inconsistent with the available evidence or context.
한국어
English
This English page is a curated translation layer linked to the Korean source article. Community changes are currently made on the Korean source, where the full revision history and anonymous edit trail are preserved.
In generative AI, hallucination refers to output that appears plausible but is not grounded in reliable evidence, the provided context, or the intended task. The term is commonly used for fabricated facts, citations, entities, or confident unsupported claims.
How it works
Language models optimize predictive objectives rather than a built-in truth database. Hallucination risk can be affected by prompts, model behavior, missing context, retrieval errors, ambiguous questions, and sampling choices.
Why it matters
Mitigation often combines retrieval, tool use, citations, constrained generation, abstention behavior, and task-specific evaluation. No single technique eliminates the problem in every setting.
Related concepts
SOURCES
Sources
KNOWLEDGE LINKS