Latest Articles for Human Feedback

A new method integrates human input to enhance OOD learning for machine learning models.

Using weaker language models can improve AI alignment efficiently.

A fresh approach to training reward models enhances AI alignment with human preferences.

A new auction-based method enhances the efficiency of collecting preference data for AI models.

GRACE helps robots act socially while performing tasks in homes and workplaces.

A new method enhances language model training using self-generated feedback.

Learn how machine learning models can improve when facing new and unseen data.

Natural language unit tests offer a clearer method for assessing language models.

Optimize your prompts with iPrOp for better AI responses.

A method that aligns language models with human preferences through effective calibration.