# Hallucinated Citations

> Trusting the model to write its own citations — and shipping fabricated sources to users.

- **Category**: Agentic AI
- **Subcategory**: Anti-Patterns
- **Canonical URL**: https://designpattern.fyi/patterns/hallucinated_citations/

---

## Description
**Intent**: Letting the model format citations inline instead of binding them to actually retrieved documents.

**Context**: Research, legal, or QA agents are told to "include sources." The model writes whatever URL or paper title sounds plausible. Nothing verifies it. Users get confident-looking references to documents that don''t exist — or did exist once, under a different URL.

**Solution**: Wire citations to retrieved-source IDs from an actual retrieval pipeline. Validate URLs before display. Never trust free-text citation output from the model. See citation-streaming, naive-rag, contextual-retrieval.



## Use Cases
- Never use this; cite an example only to label the failure mode.
- Use citation-streaming, naive-rag, or contextual-retrieval to bind citations to retrieved-source IDs.
- Validate URLs and titles against retrieval results before display.






## Trade-offs




### Considerations & Drawbacks

- Trust collapses the first time a user clicks a citation and hits 404

- Legal and regulatory exposure in any domain where sourcing matters







---
**Reference**: [Original Source](https://www.agentpatternscatalog.org/patterns/hallucinated-citations/)