2 papers
cs.LG2024
KTO: Model Alignment as Prospect Theoretic Optimization
Kawin Ethayarajh, Winnie Xu, Niklas Muennighoff +2
Kahneman & Tversky's tells us that humans perceive random variables in a biased but well-defined manner (1992); for example, humans are famously loss-ave…
cs.LG2024
Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment
Karel D'Oosterlinck, Winnie Xu, Chris Develder +5
Large Language Models (LLMs) are often aligned using contrastive alignment objectives and preference pair datasets. The interaction between model, paired data, and objective makes…