Skip to content
Research R0040 — RLHF Alternatives
Run 2026-03-29
Query Q001 — RLHF Alternatives
Search S05
Result S05-R01

S05-R01 — KTO: Model Alignment as Prospect Theoretic Optimization

Summary

Title KTO: Model Alignment as Prospect Theoretic Optimization
URL https://arxiv.org/abs/2402.01306
Date accessed 2026-03-29
Publication date February 2024 (accepted ICML 2024)
Authors Kawin Ethayarajh, Winnie Xu, Niklas Muennighoff, Dan Jurafsky, Douwe Kiela
Publication ICML 2024

Selection Decision

Selected as the primary paper introducing KTO. Peer-reviewed at top venue, introduces fundamentally different signal type (binary vs comparative).