evaluation

A list of content tagged evaluation

Responses

• Why We Are Excited About Confessions
• How confessions can keep language models honest
• Introducing Metrax: performant, efficient, and robust model evaluation metrics in JAX
• Measuring AI Ability to Complete Long Tasks
• Evaluating Context Compression for AI Agents
• Predictive Human Preference: From Model Ranking to Model Routing

Bookmarks

• Evaluating LLMs is a minefield
• Best Practices for LLM Evaluation of RAG Applications
• MLflow 2.8 with LLM-as-a-judge metrics and Best Practices for LLM Evaluation of RAG Applications