SHEN YIFull-Stack & AI

Paris • Singapore • Shanghai

RAG Formation · Reference

Refusal, uncertainty, and hallucination control

A standalone cheat sheet for learning and testing RAG quality on this site.

$ reference --status
▸ course RAG Formation
▸ mode standalone reference
▸ status Complete
● learn → test → verify

Reference sheet

Refusal, uncertainty, and hallucination control

The guided RAG Formation course content is complete; this reference is available for self-directed practice.

One-line rule

A fluent partial answer can still hallucinate if it adds an important claim the evidence does not support.

Core terms

TermMeaning
RefusalA clear statement that the indexed evidence does not establish the requested fact.
UncertaintyA calibrated explanation of what the evidence supports and what remains unknown.
HallucinationAn important claim presented without enough support from the allowed evidence.

Evidence card

NeedRecordDon't claim
BaselineCommand, configuration, observed resultThe baseline is a target.
ChangeOne hypothesis or decisionYou can tell what caused the result when several things changed.
MetricTrack refusal accuracy and hallucination rate separately, plus one answer that crossed the boundary.One metric tells you everything about quality.
SafetyA failure and a regression caseA fluent answer proves the system is reliable.

Local command

cd demo
python3 eval.py run --mode answer --workspace meridian_demo --category unanswerable --tag lesson-12-refusal

Artifact: A refusal policy with test cases for no evidence, partial evidence, conflict, and ambiguity.

Continue learning: Open the matching standalone lesson · Course roadmap