Glossary · Phase 6 · Modern LLM engineering
Position bias
Preferring whichever answer is shown first (or second) regardless of quality. Swapping the order and asking again exposes it.
Learn it properly
Instruction and preference data · The datasets that shape assistant behavior. About 30 minutes.
Other terms from the same lesson
- Bradley-Terry model: A way to turn many "A beat B" judgments into one strength score per item, so you can predict how often any item beats any other.
- Cohen's kappa: How much two judges agree beyond what chance alone would give: 0 is no better than chance, 1 is perfect agreement.
- JSON Lines: A file format with one JSON record per line, the usual way to store training examples.
- preference data: Pairs of answers to the same prompt where people (or a model) marked which one is better.
- sycophancy: A model telling people what they want to hear, such as agreeing with a wrong claim, because agreeable answers got rated higher in training.