In the classical Reinforcement Learning from Human Feedback (RLHF) framework, Proximal
Policy Optimization (PPO) is employed to learn from sparse, sentence-level rewards--a …

Human feedback plays a central role in the alignment of Large Language Models (LLMs).
However, open questions remain about the methods (how), domains (where), people (who) …

Reinforcement Learning from Human Feedback (RLHF) has been crucial to the recent
success of Large Language Models (LLMs), however, it is often a complex and brittle …

The complexity of the alignment problem stems from the fact that existing methods are
unstable. Researchers continuously invent various tricks to address this shortcoming. For …

Self-correction is a highly desirable capability of large language models (LLMs), yet it has
consistently been found to be largely ineffective in modern LLMs. Existing approaches for …

Preference tuning is a crucial process for aligning deep generative models with human
preferences. This survey offers a thorough overview of recent advancements in preference …

Safety and trustworthiness are indispensable requirements for applying AI systems based
on large language models (LLMs) in real-world applications. This paper formulates a human …

Recent advancements in generative models have sparked significant interest within the
machine learning community. Particularly, diffusion models have demonstrated remarkable …

Several variance-reduced versions of REINFORCE based on importance sampling achieve
an improved O (ϵ-3) sample complexity to find an ϵ-stationary point, under an unrealistic …

The recent surge of versatile large language models (LLMs) largely depends on aligning
increasingly capable foundation models with human intentions by preference learning …