Model Hubs and Beyond: Analyzing Model Popularity, Performance, and Documentation
This addresses the problem of model selection for users on platforms like Hugging Face, highlighting issues with popularity metrics and documentation, but it is incremental as it focuses on a specific domain (sentiment analysis).
The study analyzed 500 sentiment analysis models on Hugging Face to assess if popularity correlates with performance and how documentation quality relates to both, finding that popularity does not align with performance, 80% of models lack detailed documentation, and 88% overstate performance.
With the massive surge in ML models on platforms like Hugging Face, users often lose track and struggle to choose the best model for their downstream tasks, frequently relying on model popularity indicated by download counts, likes, or recency. We investigate whether this popularity aligns with actual model performance and how the comprehensiveness of model documentation correlates with both popularity and performance. In our study, we evaluated a comprehensive set of 500 Sentiment Analysis models on Hugging Face. This evaluation involved massive annotation efforts, with human annotators completing nearly 80,000 annotations, alongside extensive model training and evaluation. Our findings reveal that model popularity does not necessarily correlate with performance. Additionally, we identify critical inconsistencies in model card reporting: approximately 80% of the models analyzed lack detailed information about the model, training, and evaluation processes. Furthermore, about 88% of model authors overstate their models' performance in the model cards. Based on our findings, we provide a checklist of guidelines for users to choose good models for downstream tasks.