# What RAG Does Not Fix — Retrieval-Augmented Generation (RAG)

Source: https://www.geekswithgeeks.com/en/rag/b-limits

> Recognise the limits so you do not over-promise.

## Better, not perfect

RAG reduces hallucination but does not remove it. Common failures: the right passage is **never retrieved** (the most common cause of bad answers); the passage is retrieved but **ignored or misread**; retrieved text is **outdated or wrong** (garbage in, garbage out); the answer needs **combining many documents** (multi-hop questions) or **calculating across a table**; the question is **ambiguous**; and **conflicting sources** disagree. Good RAG engineering is mostly about measuring which of these is happening and fixing that stage.

## Always allow "I don't know"

Instruct the model to say it does not know when the context lacks the answer, and measure how often it does so correctly.

**Quiz:** What is the most common cause of bad RAG answers?

- [ ] The font was too small
- [x] The relevant passage was not retrieved
- [ ] The GPU was cold
- [ ] The answer was too short

*Answer:* The relevant passage was not retrieved. If retrieval misses the evidence, the model cannot answer faithfully.