NEURIPS "ai alignment" Papers

Deep Value Benchmark: Measuring Whether Models Generalize Deep values or Shallow Preferences

Joshua Ashkinaze, Hua Shen, Saipranav Avula et al.

Efficient and Near-Optimal Algorithm for Contextual Dueling Bandits with Offline Regression Oracles

Aadirupa Saha, Robert Schapire

Impartial Selection with Predictions

Learning “Partner-Aware” Collaborators in Multi-Party Collaboration

Abhijnan Nath, Nikhil Krishnaswamy

Many LLMs Are More Utilitarian Than One

Anita Keshmirian, Razan Baltaji, Babak Hemmatian et al.