Related papers: Learning a Pessimistic Reward Model in RLHF
Reinforcement Learning from Human Feedback (RLHF) allows us to train models, such as language models (LMs), to follow complex human preferences. In RLHF for LMs, we first train an LM using supervised fine-tuning, sample pairs of responses,…
In this work, we study the issue of reward hacking on the response length, a challenge emerging in Reinforcement Learning from Human Feedback (RLHF) on LLMs. A well-formatted, verbose but less helpful response from the LLMs can often…
Reinforcement Learning from Human Feedback relies on reward models to align large language models with human preferences. However, RLHF often suffers from reward hacking, wherein policy learning exploits flaws in the trained reward model to…
Reinforcement learning from human feedback (RLHF) has emerged as a key technique for aligning the output of large language models (LLMs) with human preferences. To learn the reward function, most existing RLHF algorithms use the…
Reinforcement Learning from Human Feedback (RLHF) has become a cornerstone technique for post-training large language models. While most existing approaches rely on the reverse KL-regularization, recent empirical studies have begun…
Reinforcement Learning from Human Feedback (RLHF) has emerged as a key technique for post-training large language models. Despite its empirical success, the theoretical understanding of RLHF is still limited, as learning the KL-regularized…
In reinforcement learning, specifying reward functions that capture the intended task can be very challenging. Reward learning aims to address this issue by learning the reward function. However, a learned reward model may have a low error…
Reinforcement learning (RL) systems typically optimize scalar reward functions that assume precise and reliable evaluation of outcomes. However, real-world objectives--especially those derived from human preferences--are often uncertain,…
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 this problem in a…
In this paper, we study the offline and online settings of reinforcement learning from human feedback (RLHF) with KL-regularization -- a widely used objective function in large language model alignment -- under the $\epsilon$ local…
Reinforcement Learning from Human Feedback (RLHF) has become a crucial technology for aligning language models with human values and intentions, enabling models to produce more helpful and harmless responses. Reward models are trained as…
We provide a theoretical framework for Reinforcement Learning with Human Feedback (RLHF). Our analysis shows that when the true reward function is linear, the widely used maximum likelihood estimator (MLE) converges under both the…
Reinforcement learning from human feedback (RLHF) has become a core post-training step for aligning large language models, yet the reward signal used in RLHF is only a learned proxy for true human utility. From an operations research…
Reinforcement Learning from Human Feedback (\textbf{RLHF}) has emerged as a dominant approach for aligning LLM outputs with human preferences. Inspired by the success of RLHF, we study the performance of multiple algorithms that learn from…
Reward models (RMs) used in reinforcement learning from human feedback (RLHF) are vulnerable to reward hacking: as the policy maximizes a learned proxy reward, true quality plateaus or degrades. We make the assumption that reward hacking is…
Sample efficiency is critical for online Reinforcement Learning from Human Feedback (RLHF). While existing works investigate sample-efficient online exploration strategies, the potential of utilizing misspecified yet relevant reward models…
Reinforcement learning (RL) has become a standard approach for post-training large language models and, more recently, for improving image generation models, which uses reward functions to enhance generation quality and human preference…
Reinforcement learning from human feedback (RLHF) has been widely adopted to align language models (LMs) with human preference. Prior RLHF works typically take a bandit formulation, which, though intuitive, ignores the sequential nature of…
In reinforcement learning from human feedback, preference-based reward models play a central role in aligning large language models to human-aligned behavior. However, recent studies show that these models are prone to reward hacking and…
Reinforcement learning (RL) has achieved phenomenal success in various domains. However, its data-driven nature also introduces new vulnerabilities that can be exploited by malicious opponents. Recent work shows that a well-trained RL agent…