Protocol
Test AI-suggested terms before changing a search
Treat an AI term list as a proposal. A term can sound professional yet describe the wrong concept, and a cleaner query can still miss evidence.
Before you use it
- Use when
- You suspect your terminology is narrow and want AI help generating alternate terms.
Keep this limit in mind
- AI-generated terms can be hallucinated, obsolete or from another domain; verification is mandatory for consequential searches.
Current editorial reading
Check candidates against the field
Give the AI the question, field and target database. Ask for possible alternative terms, keeping suggestions separate from the final query. Verify promising terms in real papers or the database vocabulary, and check which concept each one belongs to. If a suggested subject heading does not exist, do not silently treat it as a valid heading. It might still be a useful text word, but that needs a separate test.
Compare the searches, not the wording
Save the original query. Run the original and proposed version in the same database, then inspect newly retrieved records and any known relevant records that disappear. Record the model, date, terms changed and reasons for keeping or rejecting them. In query-generation studies, results varied by model and prompt; some cleaner result sets missed more relevant studies. They do not establish that this particular vocabulary exercise will improve your search.
Take it with you
Accept a change because its meaning and retrieval behavior fit the task. Keep the original query and an explanation of the trade-off, even when the AI version reads better.
Sources and evidence (3)
What we checked
The cited 2025 review concerns AI reliability across literature-review tasks.
Selected publisher full-text passages read on 2026-10-04. It is broad background, not direct validation of synonym generation or this workflow; DOI 10.1007/s00146-025-02406-7.
Can generative AI reliably synthesise literature? exploring hallucination issues in ChatGPT · Sections 3.1-3.4 and 4
A single-question analysis found omitted terms and incorrect grouping in generated search strategies.
Selected publisher full text read on 2026-10-04; Journal of Translational Medicine 22, 1 (2024), DOI 10.1186/s12967-023-04371-5. A case analysis does not estimate performance across fields or current models.
Development of search strategies for systematic reviews in health using ChatGPT: a critical analysis · Letter, comparative search-strategy analysis following the description of MEDLINE, LILACS and Embase prompts
In the reported benchmarks, query refinement raised precision while reducing recall; performance varied by model and prompt.
Selected full-text passages of arXiv v2 dated 2025-06-02 read on 2026-10-04. These are benchmark-specific results. The authors also flag possible training-data overlap; this is not a test of the exact card routine.
Reassessing Large Language Model Boolean Query Generation for Systematic Reviews · arXiv:2505.07155v2, sections 4.3, 4.5 and 6
Editorial sources (3)
- Can generative AI reliably synthesise literature? exploring hallucination issues in ChatGPT — Amr Adel, Noor Alani
- Development of search strategies for systematic reviews in health using ChatGPT: a critical analysis
- Reassessing Large Language Model Boolean Query Generation for Systematic Reviews — Shuai Wang, Harrisen Scells, Bevan Koopman, Guido Zuccon
Save and practise this idea
My learning
Read. Recall. Repeat.
Save this idea and return to it on any device.
Keep exploring
Connected ideas
You are readingTest AI-suggested terms before changing a search
Original edition evidence and sources
These records belong to the original released edition. The current editorial reading has its own evidence above; neither set silently replaces the other.
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
Original edition, downloads and provenance
The reading above is editorial version 1.0.0, bound to this exact source edition. The original data and saved downloads retain that edition and the separate editorial layer. They may contain earlier wording; use the current reading above when interpreting it.
Version 0.1.0
No review details are supplied for this edition.
Read the original edition and overlay as JSON · Release details