ConceptAI & ML
MT bench
An LLM-as-a-judge benchmark that uses two-turn responses and a 0-10 rating scale across multiple categories to evaluate models.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
LLM-as-a-judge1Multi-turn dialogue1
Lecturers
1Connections
1The lectures that define it or assume it, and the concepts next to it.