Protocol
Use AI to expand search language, then verify the vocabulary
AI is useful for widening the vocabulary; it is not the authority on which terms the field actually uses.
When it fits
- You suspect your terminology is narrow and want AI help generating alternate terms.
When to avoid it
- AI-generated terms can be hallucinated, obsolete or from another domain; verification is mandatory for consequential searches.
Why it matters
Ask AI for synonyms, acronyms, neighboring terms and likely controlled-vocabulary candidates. Verify each promising term in authoritative papers, indexes or standards before putting it into the final strategy. Keep terms that improve retrieval and discard plausible-sounding inventions that do not occur in the field.
Steps
- Provide the research concept and target field to AI.
- Generate alternate terms and abbreviations.
- Check candidate terms against real sources or database vocabularies.
- Test whether each term retrieves relevant material.
- Keep only terms with observed retrieval value.
An example
AI may suggest 'automation trust' for a reliance search, but the final strategy keeps 'advice taking' only after real papers show that usage.
Check your result
AI contributes vocabulary candidates without becoming the source of terminology truth.
Keep this limit in mind
- AI-generated terms can be hallucinated, obsolete or from another domain; verification is mandatory for consequential searches.
Connected ideas
Useful withKeep task stewardship when AI does the middle
Evidence and sources
Generative-AI literature synthesis can contain hallucinated or misattributed evidence, so generated summaries should not substitute for inspecting the underlying source.
AI tools vary and can still be useful for discovery, query expansion and triage with verification.
Can generative AI reliably synthesise literature? exploring hallucination issues in ChatGPT · Hallucination and attribution findings