Preference as Reward, Maximum Preference Optimization with Importance Sampling
Preference learning is a key technology for aligning language models with human values. Reinforcement Learning from Human Feedback (RLHF) is a model-based algorithm to optimize preference learning, which first fits a reward model for preference scores and then optimizes the generating policy with an on-policy PPO algorithm to maximize the reward. The processing of RLHF is complex, time-consuming, and unstable. The Direct Preference Optimization (DPO) algorithm uses an off-policy algorithm to directly optimize the generating policy and eliminates the need for a reward model. DPO is more data-efficient and stable. However, DPO has a drawback of overfitting to the preference data and ignoring the KL-regularization term when the preference is deterministic. Identity mapping Preference Optimization(IPO) uses a root-finding MSE loss to incorporate KL-regularization. However, both DPO and IPO fail to properly address the KL-regularization term because the support of the preference distribution is not equal to the reference distribution. In this paper, we propose a simple and intuitive off-policy preference optimization algorithm from an importance sampling view, which we call Maximum Preference Optimization (MPO). MPO incorporates the off-policy KL-regularization term, making regularization truly effective. MPO achieves the best of both worlds by combining the objectives of RLHF and IPO while being an off-policy algorithm. Furthermore, MPO eliminates the need for a reward model and reference policy, simplifying the learning process and reducing memory usage.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge
As the era of large language models (LLMs) unfolds, Preference Optimization (PO) methods have become a central approach to aligning LLMs with human preferences and improving performance. We propose Maximum a Posteriori P…
Computational EfficiencyBinary ClassificationOffline Preference Optimization via Maximum Marginal Likelihood Estimation
Aligning Large Language Models (LLMs) with human preferences is crucial, but standard methods like Reinforcement Learning from Human Feedback (RLHF) are often complex and unstable. In this work, we propose a new, simpler…
Reinforcement LearningRobust Reinforcement Learning from Corrupted Human Feedback
Reinforcement learning from human feedback (RLHF) provides a principled framework for aligning AI systems with human preference data. For various reasons, e.g., personal bias, context ambiguity, lack of training, etc, hu…
reinforcement-learningReinforcement LearningText GenerationProvably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer
Aligning generative models with human preference via RLHF typically suffers from overoptimization, where an imperfectly learned reward model can misguide the generative model to output undesired responses. We investigate…
Failure Modes of Maximum Entropy RLHF
In this paper, we show that Simple Preference Optimization (SimPO) can be derived as Maximum Entropy Reinforcement Learning, providing a theoretical foundation for this reference-free method. Motivated by SimPO's strong …
Reinforcement Learning