# Groundedness Checks and Refusals — Retrieval-Augmented Generation (RAG)

Source: https://www.geekswithgeeks.com/en/rag/g-ground

> Detect unsupported answers and refuse gracefully.

## Supported by the evidence?

**Groundedness** (also called faithfulness) asks whether every claim in the answer is supported by the retrieved text. Cheap checks compare the answer's content words with the context: low overlap is a warning sign. Stronger checks use an **LLM judge** or an NLI model to test each claim against the context. When groundedness is low or retrieval confidence is below the threshold, **refuse gracefully** ("I couldn't find this in the documents"), offer related sources or hand off to a human. A correct refusal is better than a confident guess.

## A word-overlap groundedness heuristic, run

I ran this plain-Python (standard library only) example. The faithful answer shares 80% of its content words with the context; the answer inventing "20 days and cash them out" shares only 25% and is flagged. This is a crude heuristic, not a substitute for a proper judge.

```python
import re

def words(t): return set(re.findall(r"[a-z0-9]+", t.lower())) - {"the","a","an","of","to","is","are","can","be","you","per","up"}

context = "Unused leave up to 5 days can be carried over to the next year."
for ans in ("You can carry over 5 days of leave.", "You can carry over 20 days and cash them out."):
    aw = words(ans); support = len(aw & words(context)) / len(aw)
    print(round(support, 2), "grounded" if support >= 0.6 else "CHECK", "|", ans)

```

Output:

```
0.8 grounded | You can carry over 5 days of leave.
0.25 CHECK | You can carry over 20 days and cash them out.
```

## Show confidence honestly

When the evidence is partial, say which part is supported and which is not, instead of presenting a complete-sounding answer.

**Quiz:** What should the system do when evidence is too weak?

- [x] Say it could not find the answer in the documents
- [ ] Invent a plausible answer
- [ ] Increase the temperature
- [ ] Delete the index

*Answer:* Say it could not find the answer in the documents. An honest "not found" protects users from confident errors.