// ⚖ Alignment & Preference Optimization
KTO (Kahneman–Tversky Optimization)
Aligns from simple good/bad labels instead of pairs.
KTO 2024 Intermediate extended
IN PLAIN WORDS
Uses a prospect-theory utility to raise desirable and lower undesirable outputs, with loss aversion. Data is easier to collect.
Used in: Alignment when only thumbs-up/down data exists
01Original paper
KTO: Model Alignment as Prospect Theoretic Optimization
Kawin Ethayarajh, Winnie Xu, Niklas Muennighoff, et al. · 2024
arXiv ↗ ✓ Verified · arXiv API
02Where it sits
Learn the left column first; the right column builds on this one.
Learn first
KTO (Kahneman–Tversky Optimization)
Then you can learn
- Nothing in the atlas builds on it yet
Related:ORPO (Odds Ratio Preference Optimization)
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
Official docs
04Where the course teaches it
For AI / data
- Verification: verified, checked 2026-10-21.
- JSON: /api/learn/algorithms.json (id:
kto)