Although ChatGPT, particularly GPT 4.0, can generate abstracts that meet structural requirements and reproduce surface-level elements of academic style, significant limitations remain in content accuracy, originality, and ethical considerations. Key messages What is already known on this topic: With the expanding application of artificial intelligence (AI) techniques, the development of large language models (LLMs) has enabled the generation of natural language with enhanced performance, driven by improved context handling, broader multimodal capabilities, and optimized architectures. However, their specific capacity to generate structurally compliant and ethically acceptable abstracts in the field of orthopedic surgery remains unclear. What this study adds: This study demonstrates that while GPT-4.0 achieves superior adherence to formatting and word counts compared to GPT-3.5, both models frequently generate inaccurate conclusions and exhibit high plagiarism rates, despite being difficult for human reviewers to distinguish from human-written text. How this study might affect research, practice, or policy: Although ChatGPT shows potential as a supportive tool for generating orthopedic research abstracts, our overall findings emphasize that its unregulated or exclusive use introduces significant ethical and practical concerns. To ensure the integrity of academic publishing, it is imperative to establish clear, field-specific guidelines that govern the responsible application of LLMs in scientific writing.
Kim et al. (Tue,) studied this question.