receipt
increasingly chose plant-based lunches over time (from 44% to 59%Abstract, resultsThe effect of AI-based linguistically tailored health messages on plant-based lunch choices of adolescents: A randomised controlled trial (Appetite; abstract via Europe PMC) · doi.org
Rewriting daily health messages in each adolescent's own style with an LLM added no extra plant-based lunch choices over plain messages in a trial of 587 UK and Irish adolescents.
receipt
we conducted a preregistered two-week randomised controlled trial with 587 adolescentsAbstractThe effect of AI-based linguistically tailored health messages on plant-based lunch choices of adolescents: A randomised controlled trial (Appetite; abstract via Europe PMC) · doi.org
Adolescents got no messages, plain health messages, or LLM style-tailored messages for two weeks, and their choice of a plant-based lunch was tracked.
Sources
Editor's notes
verify: the abstract gives no calendar dates for the two-week trial, so the achieved dates and the window grade are left empty. verify: the 44% to 59% rise is for the message arms combined; the abstract reports no separate figure for the tailored arm.
History
- Added by the backfill run.
Verification
- Drafted by
- Anthropic
claude-sonnet-5-5 - Verified by
- OpenAI
gpt-6.1-sol· pass - How sure
- Speculative
- Source 0 could be read only in part (an abstract or a summary), not the full document.
- Not dated yet (The dated test fails because no intervention calendar dates are supplied; publication date does not establish when outcomes occurred.).
- Record
- data/verifications/llm-tailored-health-messages-adolescent-plant-based-lunch-null/2026-11-19.json · The abstract supports a preregistered randomized trial of 587 adolescents showing no additional short-term behavioural benefit from LLM tailoring and supports all receipted numbers. It does not establish when the intervention occurred or disclose funding and author ties.
Two models from different vendors read the primary source independently; this entry is published because they agreed on every receipt and every grade. It is marked speculative: The source is a press release, a news report, or the organisation's own announcement, or the benefit has not yet been measured against anything or dated, or the two checking models disagreed on a grade. Every number is still quoted from the source, and both checking models support it. The models grading an AI registry have an interest in the answer. Cross-vendor checking and the receipts on this page are how the registry handles that, not a claim to have removed it. How the gate works · Dispute this entry
Cite this entry
“Rewriting daily health messages in each adolescent's own style with an LLM added no extra plant-based lunch choices over plain messages in a trial of 587 UK and Irish adolescents.” Because of AI, updated Nov 19, 2026. https://becauseofai.org/entry/llm-tailored-health-messages-adolescent-plant-based-lunch-null@misc{becauseofai_llm_tailored_health_messages_adolescent_plant_based_lunch_null,
title = {Rewriting daily health messages in each adolescent's own style with an LLM added no extra plant-based lunch choices over plain messages in a trial of 587 UK and Irish adolescents.},
howpublished = {\url{https://becauseofai.org/entry/llm-tailored-health-messages-adolescent-plant-based-lunch-null}},
note = {Because of AI registry, updated Nov 19, 2026},
year = {2026}
}