CurriculumPractise these
Module 04
Evaluation and Experimentation
Success criteria, metrics, LLM-as-judge limits, baselines, ablations, and error analysis.
- Lessons
- 5
- Topics
- 40
- Minutes
- 118
Lessons
- Lesson 1Success Criteria: Deciding What Good Means22 min · 8 topics · intermediate
- Lesson 2Scoring Against References: Exact, Lexical and Semantic24 min · 8 topics · intermediate
- Lesson 3Using a Model as a Judge24 min · 8 topics · intermediate
- Lesson 4Comparing Systems You Can Trust26 min · 8 topics · intermediate
- Lesson 5Error Analysis: Finding What Goes Wrong22 min · 8 topics · intermediate
Interview prep
40 questions on this module's topics.