Objective-Conditioned Active Preference Learning for Multi-Objective Alignment
cs.LG, cs.AI
Submitted: 2026-11-03
Updated: 2026-11-03
Terminology
Sources
- Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- Reward-free Alignment for Conflicting Objectives
- UltraFeedback: Boosting Language Models with Scaled AI Feedback
- The Llama 3 Herd of Models
- LoRA: Low-Rank Adaptation of Large Language Models
- GPT-4o System Card
- Reinforcement Learning from Human Feedback with Active Queries
- Active Learning for Direct Preference Optimization
- Sample Efficient Preference Alignment in LLMs via Active Exploration
- Gemma 3 Technical Report
- LESS: Selecting Influential Data for Targeted Instruction Tuning
- REWARD CONSISTENCY: Improving Multi-Objective Alignment from a Data-Centric Perspective
- Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis