Source Themes

RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs
Preference optimization techniques have become a standard final stage for training state-of-art large language models (LLMs). However, …
John Dang, Arash Ahmadian, Kelly Marchisio, Julia Kreutzer, Ahmet Üstün, Sara Hooker
PDF
RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs
Aya 23: Open Weight Releases to Further Multilingual Progress
This technical report introduces Aya 23, a family of multilingual language models. Aya 23 builds on the recent release of the Aya model …
Viraat Aryabumi, John Dang, Dwarak Talupuru, Saurabh Dash, David Cairuz, Hangyu Lin, Bharat Venkitesh, Madeline Smith, Jon Ander Campos, Yi Chern Tan, Kelly Marchisio, Max Bartolo, Sebastian Ruder, Acyr Locatelli, Julia Kreutzer, Nick Frosst, Aidan Gomez, Phil Blunsom, Marzieh Fadaee, Ahmet Üstün, Sara Hooker
PDF
Aya 23: Open Weight Releases to Further Multilingual Progress
Group Preference Optimization: Few-Shot Alignment of Large Language Models
Many applications of large language models (LLMs), ranging from chatbots to creative writing, require nuanced subjective judgments that …
Siyan Zhao, John Dang, Aditya Grover
PDF Code
Group Preference Optimization: Few-Shot Alignment of Large Language Models
Peering Through Preferences: Unraveling Feedback Acquisition for Aligning Large Language Models
Aligning large language models (LLMs) with human values and intents critically involves the use of human or AI feedback. While dense …
Hritik Bansal, John Dang, Aditya Grover
PDF Code Dataset
Peering Through Preferences: Unraveling Feedback Acquisition for Aligning Large Language Models