Daniel Jude·Mar 9Understanding Evaluation Metrics in AI: From F1 Score to RAG and Agentic SystemsWhen you train a machine learning model, the first thing you want to know is simple:
Srinivas Bommena·Dec 19, 2025Evaluation Is the Hardest Unsolved Problem in Large Language ModelsMost LLM systems do not fail because the model is weak. They fail because we cannot reliably evaluate LLM behavior under real operating…
InData Science + AI at Microsoftbyshima ghassempour·Mar 4, 2025Beyond thumbs up and thumbs down: A human-centered approach to evaluation design for LLM productsBy Shima GhassemPour, Anna Pershukova, Esra Gokgoz, and Irina NikulinaA response icon1A response icon1
