Back to Basics: Revisiting REINFORCE-Style Optimization for Learning from Human Feedback in LLMs ACL

Arash Ahmadian | Chris Cremer | Matthias Gallé | Marzieh Fadaee | Julia Kreutzer | Olivier Pietquin | Ahmet Üstün | Sara Hooker |

RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs EMNLP

John Dang | Arash Ahmadian | Kelly Marchisio | Julia Kreutzer | Ahmet Üstün | Sara Hooker |

Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion EMNLP

Yannis Flet-Berliac | Nathan Grinsztajn | Florian Strub | Eugene Choi | Bill Wu | Chris Cremer | Arash Ahmadian | Yash Chandak | Mohammad Gheshlaghi Azar | Olivier Pietquin | Matthieu Geist |

The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm EMNLP

Aakanksha | Arash Ahmadian | Beyza Ermis | Seraphina Goldfarb-Tarrant | Julia Kreutzer | Marzieh Fadaee | Sara Hooker |