相关论文: Arena as Offline Reward: Efficient Fine-Grained Pr…

Reinforcement Learning from Human Feedback (RLHF) is a powerful paradigm for aligning foundation models to human values and preferences. However, current RLHF techniques cannot account for the naturally occurring differences in individual…

One of the challenges of aligning large models with human preferences lies in both the data requirements and the technical complexities of current approaches. Predominant methods, such as RLHF, involve multiple steps, each demanding…

Direct Preference Optimization (DPO) is a widely adopted offline algorithm for preference-based reinforcement learning from human feedback (RLHF), designed to improve training simplicity and stability by redefining reward functions.…

Group Relative Policy Optimization(GRPO) has become a cornerstone of modern reinforcement learning alignment, prized for its efficacy in foregoing an explicit value-critic by leveraging reward normalization across sampled trajectory…

The alignment of large language models with human values presents a critical challenge, particularly when balancing conflicting objectives like helpfulness and harmlessness. Existing approaches, such as Reinforcement Learning from Human…

Aligning text-to-video diffusion models with human preferences is crucial for generating high-quality videos. Existing Direct Preference Otimization (DPO) methods rely on multi-sample ranking and task-specific critic models, which is…

We consider the problem of offline reinforcement learning from human feedback (RLHF) with pairwise comparisons proposed by Zhu et al. (2023), where the implicit reward is a linear function of an unknown parameter. Given an offline dataset,…

Reinforcement Learning from Human Feedback (RLHF) and derivative techniques like Direct Preference Optimization (DPO) are task-alignment algorithms used to repurpose general, foundational models for specific tasks. We show that applying…

Standard human preference-based alignment methods, such as Reinforcement Learning from Human Feedback (RLHF), are a cornerstone for aligning large language models (LLMs) with human values. However, these methods typically assume that…

Reward-model training is the cost bottleneck in modern Reinforcement Learning Human Feedback (RLHF) pipelines, often requiring tens of billions of parameters and an offline preference-tuning phase. In the proposed method, a frozen,…

Reinforcement Learning from Human Feedback (RLHF) has become a dominating strategy in aligning Language Models (LMs) with human values/goals. The key to the strategy is learning a reward model ($\varphi$), which can reflect the latent…

While astonishingly capable, large Language Models (LLM) can sometimes produce outputs that deviate from human expectations. Such deviations necessitate an alignment phase to prevent disseminating untruthful, toxic, or biased information.…

Recent work shows that preference alignment objectives can be interpreted as divergence estimators between aligned (preferred) & unaligned (less-preferred) distributions, yielding a principled recipe for designing alignment losses. However,…

The dominant framework for alignment of large language models (LLM), whether through reinforcement learning from human feedback or direct preference optimisation, is to learn from preference data. This involves building datasets where each…

DPO (Direct Preference Optimization) has become a widely used offline preference optimization algorithm due to its simplicity and training stability. However, DPO is prone to overfitting and collapse. To address these challenges, we propose…

We investigate Reinforcement Learning from Human Feedback (RLHF) in the context of a general preference oracle. In particular, we do not assume the existence of a reward function and an oracle preference signal drawn from the Bradley-Terry…

Offline preference optimization methods, such as Direct Preference Optimization (DPO), offer significant advantages in aligning Large Language Models (LLMs) with human values. However, achieving optimal performance with these methods…

Recent theory suggests that reward-model-first methods can be more sample-efficient than direct policy fitting when the reward function is statistically simpler than the induced policy. We propose DDO-RM, a finite-candidate…

Proximal Policy Optimization (PPO)-based reinforcement learning from human feedback (RLHF) is a widely adopted paradigm for aligning large language models (LLMs) with human preferences. However, its training pipeline suffers from…

This paper studies tabular reinforcement learning (RL) in the hybrid setting, which assumes access to both an offline dataset and online interactions with the unknown environment. A central question boils down to how to efficiently utilize…