When Scores Conflict with Preferences: Pre-Alignment Diagnosis and Adaptive Correction of Constraint Drift in DPO
cs.LG
Submitted: 2026-11-05
Updated: 2026-11-05
Sources
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- Training Verifiers to Solve Math Word Problems
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Provably Convergent Primal-Dual DPO for Constrained LLM Alignment
- Qwen2.5 Technical Report
- Mistral 7B
- Qwen3 Technical Report
- GPDPO: Learning from Reward Conflicts via Group Pareto-Dominance Policy Optimization
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