MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge
cs.LG, cs.AI, cs.CL
Submitted: 2025-07-27
Updated: 2026-11-08
Code: https://github.com/tatsu-lab/alpaca_eval
Terminology
Sources
- Nemotron-4 340B Technical Report
- Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
- Training Verifiers to Solve Math Word Problems
- Safe RLHF: Safe Reinforcement Learning from Human Feedback
- KTO: Model Alignment as Prospect Theoretic Optimization
- The Llama 3 Herd of Models
- Reinforced Self-Training (ReST) for Language Modeling
- TODO: Enhancing LLM Alignment with Ternary Preferences
- Mistral 7B
- From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline
- Reward Learning From Preference With Ties
- Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive
- The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models
- Disentangling Length from Quality in Direct Preference Optimization
- From $r$ to $Q^*$: Your Language Model is Secretly a Q-Function
- Learning Dynamics of LLM Finetuning
- Efficient RLHF: Reducing the Memory Usage of PPO
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data
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