Strengths and Weaknesses of ChatGPT Models for Scientific Writing About Medical Vitamin B12: Mixed Methods Study
Bibliographic record
Abstract
BACKGROUND: ChatGPT is a large language model developed by OpenAI designed to generate human-like responses to prompts. OBJECTIVE: This study aims to evaluate the ability of GPT-4 to generate scientific content and assist in scientific writing using medical vitamin B12 as the topic. Furthermore, the study will compare the performance of GPT-4 to its predecessor, GPT-3.5. METHODS: The study examined responses from GPT-4 and GPT-3.5 to vitamin B12-related prompts, focusing on their quality and characteristics and comparing them to established scientific literature. RESULTS: The results indicated that GPT-4 can potentially streamline scientific writing through its ability to edit language and write abstracts, keywords, and abbreviation lists. However, significant limitations of ChatGPT were revealed, including its inability to identify and address bias, inability to include recent information, lack of transparency, and inclusion of inaccurate information. Additionally, it cannot check for plagiarism or provide proper references. The accuracy of GPT-4's answers was found to be superior to GPT-3.5. CONCLUSIONS: ChatGPT can be considered a helpful assistant in the writing process but not a replacement for a scientist's expertise. Researchers must remain aware of its limitations and use it appropriately. The improvements in consecutive ChatGPT versions suggest the possibility of overcoming some present limitations in the near future.
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.
How this classification was reachedexpand
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 | 0.011 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".