Which Preferences to Train On? End-to-End Multi-Objective Alignment with an Adversarial Preference Distribution
cs.LG
Submitted: 2026-10-04
Updated: 2026-10-04
Code: https://github.com/Nkluge-correa/Aira
Terminology
Sources
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models
- Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignment
- Preference Orchestrator: Prompt-Aware Multi-Objective Alignment for Large Language Models
- High-Dimensional Continuous Control Using Generalized Advantage Estimation
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Bone Soups: A Seek-and-Soup Model Merging Approach for Controllable Multi-Objective Generation
- Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks