How do you make an LLM cite its sources reliably?

medium

Answer

$(1) Format retrieved docs with explicit IDs ('[doc 1]: ...', '[doc 2]: ...').$
$(2) Instruct the LLM to add [doc N] tags to every claim.$
$(3) Post-process: parse tags, verify each cited doc actually supports the claim (LLM-judge or NLI), and reject / regenerate if unsupported.$
$\mathrm{source}_{\mathrm{ids}}[]$
$(5) Fine-tune on citation-heavy examples.$
$Anthropic / OpenAI structured outputs make this reliable.$
$Critical for legal, medical, financial RAG.$

Check yourself — multiple choice

Trust the LLM
Numbered doc IDs + tagging instruction + post-process verification + structured output + optional fine-tune
Only regex
Impossible

Reliable citations: numbered IDs + tag + verify + structured output + optional fine-tune.

#rag#reliability

214 interview questions in this topic.