# KTO (Kahneman-Tversky Optimization): Alignment from One-Sided (Unpaired) Feedback

> Source: https://sukruyusufkaya.com/en/learn/fine-tuning-cookbook/ftc-kto-kahneman-tversky-unpaired-feedback
> Updated: 2026-05-14T14:42:58.169Z
> Category: Fine-Tuning Cookbook (Model-by-Model)
> Module: Part XI — Alignment & Preference Optimization
**TLDR:** KTO (Ethayarajh et al. 2024) — feedback you actually get in production: 'thumbs up' / 'thumbs down'. Not pairs. Classical DPO can't use this data. KTO fills the gap: utility function from prospect theory (Kahneman-Tversky). Continuous learning loop in production.