Author

Kawin Ethayarajh

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Mar 2026

Mecha-nudges for Machines

These results provide the first large-scale evidence that systematic mecha-nudging is already occurring in the wild, but going unnoticed, and a common unit (bits) for quantifying how environments change across a wide range of interventions, contexts, and models.

G. Frey, Kawin Ethayarajh · arXiv.org · 1 citation

#artificial intelligence Feb 2024

KTO: Model Alignment as Prospect Theoretic Optimization

This work proposes a HALO that directly maximizes the utility of generations instead of maximizing the log-likelihood of preferences, and suggests that the best loss depends on the inductive biases most appropriate for a given setting, an oft-overlooked consideration.

Kawin Ethayarajh, Winnie Xu, Niklas Muennighoff et al. · arXiv.org · 195 citations · ⚡28