Parenting Journal · Volume 3 · Issue 1 · Licensed source edition
Cross-sectional comparative evaluation of five large language model–driven chatbots on an expert-curated 44-question set of parent-facing questions about pediatric vitamin D deficiency
Originally published 2026-09-09 · Frontiers in Pediatrics
Frontiers Media SA · DOI 10.3389/fped.2026.1927624 ↗
AI / system type
Generative AI / multi-model safety benchmark
Family implicationsDesign, ethics, stakeholder or technical evidence with child/family implications; household benefits are not assumed.
The AI connection
Compares five generative chatbot services on standardized caregiver-oriented pediatric information questions.
Why this reading matters
Makes unsafe outliers visible alongside favorable average ratings, a useful distinction for calibrated reliance.
Editorial reading guide · Trust
Can a model perform well on average and still give an unsafe answer to a parent?
The study evaluates safety separately from other quality dimensions, illustrating why high overall scores do not eliminate unsafe answers.
Study context
Forty-four expert-curated parent-facing questions across five LLM services
Age / stage: Pediatric vitamin-D questions; no children or parents enrolled
Read with three questions
- How were safety, accuracy and information quality rated separately?
- What did a single response per question omit about variability?
- Were parents involved in validating the question set or testing understanding?
Keep the limits in view
This was a single-run, time-specific expert benchmark with no parent content validation or clinical outcome assessment. Model routing, prompt choice and updates limit reproducibility and stable rankings.
The text below is the original article’s licensed repository edition. Its wording is not rewritten. Use the Paper Agent beside the text to locate evidence; open the source for figures, tables and complete context.
Opening the verified paper and agent…
Checking the article identity, license record, and saved source text.
Open the repository recordAttribution & reuse
Follow the original.
Original authorship, publication date, journal and DOI are preserved. This issue’s TRICK placement and reading questions are editorial additions, not claims made by the original authors.
Ping Shi; Tian Zhou; Qiao Nie; Baicheng Tao; Xiaolu Li; Mei Zhu (2026). Cross-sectional comparative evaluation of five large language model–driven chatbots on an expert-curated 44-question set of parent-facing questions about pediatric vitamin D deficiency Frontiers in Pediatrics. https://doi.org/10.3389/fped.2026.1927624
Permissions checked against the saved article notice; repository publication notices screened 2026-11-04. This is not a new peer-review decision. The source authors and publishers are not represented as endorsing this issue.