Ctrl + Alt + Conceive: fertility awareness in the age of Artificial Intelligence, how do large language models compare?
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Technology continues to change how we manage our health, and recent breakthroughs in Artificial Intelligence have increased the adoption of Large Language Models (LLMs) in healthcare. Since the launch of ChatGPT, LLMs have been increasingly used for health information; this study, therefore, aimed to qualitatively assess fertility information provided by LLMs. Content generated by four LLM platforms: ChatGPT, Gemini, Copilot, Perplexity, were analysed comparatively. Thirty-seven prompts were generated, covering five topics: menstrual cycle, conception, risk factors, assisted reproductive technologies and age-related fertility decline. Prompts were analysed for concordance, comprehensibility and conciseness. Safety warnings for all platforms were recorded. LLM platforms generally provided concordant answers for menstrual cycle, conception, and risk factors. However, content on assisted reproductive technologies was the least accurate. Perplexity provided the highest number of strongly-concordant and poorly-concordant responses. Comprehensibility was similar across platforms. ChatGPT was the most concise. Not all platforms provided warning or safety messages regarding potential inaccuracies. LLMs present an opportunity to expand access to fertility and reproductive health information not only for individuals and patients, but also for clinicians, researchers, educators, charities, reproductive health organisations and policymakers. Nevertheless, attention must be paid to the quality of information generated in order to ensure that professionals have accurate guidance, and that individuals can access quality information to help achieve their desired fertility and reproductive health intentions.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it