Why do LLMs sometimes confidently state incorrect facts (hallucination), and what does that imply for production use?

An LLM generates the statistically most plausible next token given its training data and the prompt — it has no built-in fact-checking step or notion of 'I don't know', so a plausible-sounding but false answer is generated with the same confidence as a true one. This is why production systems pair LLMs with retrieval (RAG) or tool calling for anything factual, rather than trusting the model's raw internal knowledge.