Related papers: Mitigating Reward Hacking in RLHF via Advantage Si…

With the development of large language models (LLMs), striking a balance between the performance and safety of AI systems has never been more critical. However, the inherent tension between the objectives of helpfulness and harmlessness…

Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique to make large language models (LLMs) easier to use and more effective. A core piece of the RLHF process is the training and utilization of a model of…

Large language models (LLMs) have demonstrated remarkable performance in reasoning tasks, where reinforcement learning (RL) serves as a key algorithm for enhancing their reasoning capabilities. Currently, there are two mainstream reward…

Reinforcement learning from human feedback (RLHF) is the mainstream paradigm used to align large language models (LLMs) with human preferences. Yet existing RLHF heavily relies on accurate and informative reward models, which are vulnerable…

As Large Language Models (LLMs) continue to progress toward more advanced forms of intelligence, Reinforcement Learning from Human Feedback (RLHF) is increasingly seen as a key pathway toward achieving Artificial General Intelligence (AGI).…

Numerous algorithms have been proposed to $\textit{align}$ language models to remove undesirable behaviors. However, the challenges associated with a very large state space and creating a proper reward function often result in various…

Reinforcement Learning with Human Feedback (RLHF) is a methodology designed to align Large Language Models (LLMs) with human preferences, playing an important role in LLMs alignment. Despite its advantages, RLHF relies on human annotators…

Reinforcement Learning from Human Feedback (RLHF) has been credited as the key advance that has allowed Large Language Models (LLMs) to effectively follow instructions and produce useful assistance. Classically, this involves generating…

Reinforcement Learning from Human Feedback (RLHF) assumes annotator preferences reflect stable internal states. We challenge this through three experiments spanning the preference pipeline. In a human choice blindness study, 91% of…

Reinforcement learning with human feedback (RLHF), which learns a reward model from human preference data and then optimizes a policy to favor preferred responses, has emerged as a central paradigm for aligning large language models (LLMs)…

Direct Preference Optimization (DPO) has emerged as a lightweight and effective alternative to Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning with AI Feedback (RLAIF) for aligning large language and…

The automatic synthesis of a policy through reinforcement learning (RL) from a given set of formal requirements depends on the construction of a reward signal and consists of the iterative application of many policy-improvement steps. The…

Reinforcement learning (RL) trained language model agents with tool access are increasingly deployed in coding assistants, research tools, and autonomous systems. We introduce the Reward Hacking Benchmark (RHB), a suite of multi-step tasks…

Recent breakthroughs in preference alignment have significantly improved Large Language Models' ability to generate texts that align with human preferences and values. However, current alignment metrics typically emphasize the post-hoc…

Large language model (LLM) systems increasingly power everyday AI applications such as chatbots, computer-use assistants, and autonomous robots, where performance often depends on manually well-crafted prompts. LLM-based prompt optimizers…

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective paradigm for improving the reasoning capabilities of large language models. However, RLVR training is often hindered by sparse binary rewards and weak credit…

The objectives of option hedging/trading extend beyond mere protection against downside risks, with a desire to seek gains also driving agent's strategies. In this study, we showcase the potential of robust risk-aware reinforcement learning…

When applying reinforcement learning from human feedback (RLHF), the reward is learned from data and, therefore, always has some error. It is common to mitigate this by regularizing the policy with KL divergence from a base model, with the…

While originally developed for continuous control problems, Proximal Policy Optimization (PPO) has emerged as the work-horse of a variety of reinforcement learning (RL) applications, including the fine-tuning of generative models.…

Preference-based fine-tuning has become an important component in training large language models, and the data used at this stage may contain sensitive user information. A central question is how to design a differentially private pipeline…