A Markov Chain Approach to Preference Alignment
Takuya Koriyama, Tengyuan Liang
cs.LG, stat.ML
Submitted: 2026-06-21
Comments: 48 pages, 7 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- No-Regret Generative Modeling via Parabolic Monge-Amp\`ere PDE
- Statistical Impossibility and Possibility of Aligning LLMs with Human Preferences: From Condorcet Paradox to Nash Equilibrium
- Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences
- Proximal Policy Optimization Algorithms
- Fundamental Limits of Game-Theoretic LLM Alignment: Smith Consistency and Preference Matching
- Proximal Point Nash Learning from Human Feedback
- Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review
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