Ethical documentation of open-source AI models: a multivocal literature review and large-scale analysis of model cards

This study investigates ethical documentation for open-source AI models through a combination of a Multivocal Literature Review (MLR) with a large-scale empirical analysis of real-world Model Cards. We aim to address the gap in how ethical considerations are documented and implemented in both research and practice. Publications from major scholarly databases and arXiv (N = 36) were systematically retrieved, screened, and analysed. In parallel, metadata and documentation from the most-downloaded models on Hugging Face Hub were processed, yielding over 60,000 valid Model Cards after filtering. The literature review shows that Model Cards are the predominant artifact in open publication settings, but ethical coverage is uneven: transparency is most frequently addressed, while societal and environmental aspects are rarely discussed. Notably, bias is often referenced generically, with little methodological consideration. Finally, the Model Card analysis reveals three issues that indicate an implementation gap: (i) only 16.8% include explicit references to ethics (e.g., bias, limitations, risks), (ii) these sections are typically brief, and (iii) their relative prevalence declines over time despite absolute growth in model releases. These findings underscore the importance of standardized documentation, clearer guidelines, and machine-readable, verifiable ethical properties to support responsible model development and reuse.