An AI application may retrieve documents and then use a model to compose a response from them. The retrieval step selects material; the generation step produces wording using the supplied context.
A retrieved source does not guarantee that every sentence accurately reflects it. Check whether the cited page supports the particular claim, and distinguish information from the source from an inference added in the answer.
Open important references and read the relevant passage in context. The combination can be useful, but each stage has its own possible gaps. Understanding the difference helps explain why an answer with links still needs a check.
A small working example.
Imagine an assistant offering a smooth explanation beside a retrieved document. Open the document to check whether it supports the particular sentence.
A note to keep beside it.
Give review a specific responsibility. Checking a source, testing an instruction, and editing a sentence are different jobs and may need different evidence.
- Distinguish retrieval from composition.
- Check support for each important claim.
- Identify inferences added beyond the source.
Follow a related question
Define the understood inputs.
Where automation should hand backDistinguish active work from saved references.
A calmer browserKeep learning
Related background to continue exploring this subject.
Google: an introduction to language models NIST: AI risk management framework