Researchers introduced Budget-Sensitive Discovery Score (BSDS) and its averaged form, Discovery Quality Score (DQS), to evaluate AI systems in scientific discovery by considering budget constraints and false discoveries. The study found that large language models do not offer additional value over existing machine learning methods for drug discovery candidate selection under various conditions.
Read the full article at arXiv stat.ML
Want to create content about this topic? Use Nemati AI tools to generate articles, social posts, and more.
4
Comments
Ali NematiWritten by Ali
