Skip to content

R0040/2026-04-01/Q001/S04/R01

Research R0040 — RLHF Alternatives
Run 2026-04-01
Query Q001
Search S04
Result S04-R01

Original KTO paper applying prospect theory to LLM alignment.

Summary

Field Value
Title KTO: Model Alignment as Prospect Theoretic Optimization
URL https://arxiv.org/abs/2402.01306
Date accessed 2026-04-01
Publication date 2024-02-02 (ICML 2024)
Author(s) Kawin Ethayarajh, Winnie Xu, Niklas Muennighoff, Dan Jurafsky, Douwe Kiela
Publication ICML 2024

Selection Decision

Included in evidence base: Yes

Rationale: Original peer-reviewed paper introducing KTO. Primary source. Published at ICML 2024.