A chatbot sometimes invents policy clause numbers.
Answers should show the source and uncertainty.
Which first measure is most appropriate?
Retrieve trusted documents for the model context and display sources and uncertainty so users can verify the answer.
Detailed explanation
More randomness is not a factuality control.
Short prompts do not eliminate missing knowledge or unsupported generation.
Unverified output should not update authoritative records automatically.
Grounding the answer in retrieved evidence limits unsupported generation and enables verification.
Check official documentation
Compare the following points with the official documentation.
Amazon Bedrock Knowledge Bases公式ドキュメントとResponsible AIの説明を確認する。
Official references
What to confirm
検索拡張、出典、検証をハルシネーション対策として説明できる。
Key points
- Hallucination
- Retrieval grounding
- Source verification
Notes
- Environment: AWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
- Compare the definition with the AIF-C01 objective and the service documentation before applying it.
- Keep the concept separate from a particular answer choice or implementation step.
Foundation review
Evidence boundary
Retrieved context can improve factuality but does not remove the need to check relevance, access, and freshness.
Abstention
A model or application may decline to answer when evidence is missing or confidence is too low.