Latest Articles for Preferences

A look into the complexities of pairing people based on preferences.

A new approach helps language models better understand human choices.

Learn how AHP can streamline your decision-making process.

SEE-DPO improves image generation by aligning models with human preferences.

Finding common ground for AI decision-making among diverse human values.

This article explores how self-knowledge affects social preferences and decision-making.

A look at how agents collaborate and adapt in decision-making scenarios.

A guide on fair resource distribution in diverse groups.

A new method called AVA enhances alignment in language models for safer outputs.

This paper examines the complexities of pairing hospitals with residents fairly.

Explore how seating arrangements affect conversation and social interactions.

A new method for selecting fair representatives in multi-winner elections.

Explore how online recommendations influence what we watch and enjoy.

A look at how student preferences impact school matching.

Using images to shape personalized recommendations for food and entertainment.

CIDER improves recommendations by connecting preferences across different areas like books and movies.

Effective communication is key to improving interactions with AI agents.

This research looks at how agents adapt their choices in a changing world.

PlanCritic simplifies complex planning tasks with user-friendly feedback.

Navigating fairness in recommendation systems while keeping user satisfaction intact.

Learn how bundle choice models explain consumer decisions at snack time!

A clear look at a new voting method that respects voter preferences.

Users often choose confident falsehoods over accurate information, raising ethical concerns.

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

New methods improve evaluation of language models using human-written responses.

A look into how the Bayesian Mallows model analyzes rankings and preferences.

Discover how Direct Preference Alignment enhances AI understanding of human needs.

Learn how to effectively choose facility locations for better service and customer satisfaction.

Machines now generate images and videos based on human preferences.