Why it matters

Hallucinations cause real harm: legal citations to fictional cases, medical advice that's wrong, business decisions based on fabricated data. Deploying LLMs safely requires accounting for this.

Advertisement

The architecture

Training: LLMs are trained to predict next tokens. There's no explicit truthfulness objective. Coherent text is rewarded even when factually wrong.

Confidence miscalibration: LLMs don't reliably indicate uncertainty. Fabricated content is generated with the same confidence as accurate content.

Why hallucinations happenCoherence goalnot truth goalMiscalibrated confidenceno reliable uncertaintyMissing knowledgefill with plausible fictionRAG + citations reduce risk; not perfect but usually sufficient for many use cases
Root causes of hallucination.
Advertisement

How it works end to end

Mitigations: RAG (retrieval-augmented generation) grounds responses in retrieved documents. Model answers 'according to source X...' and can be checked.

Citations: require model to cite sources for factual claims. Check citations for existence and relevance.

Multi-model verification: ask multiple models; disagreement indicates uncertainty.

Domain-specific fine-tuning + guardrails: constrain output to verified sources for high-stakes domains.