相关论文: Quark Medical Alignment: A Holistic Multi-Dimensio…

Personalized alignment from preference data has focused primarily on improving personal reward model (RM) accuracy, with the implicit assumption that better preference ranking translates to better personalized behavior. However, in…

Recent works have shown that deep neural networks can achieve super-human performance in a wide range of image classification tasks in the medical imaging domain. However, these works have primarily focused on classification accuracy,…

As large language models are increasingly deployed in sensitive domains such as healthcare, ensuring their outputs reflect the diverse values and perspectives held across populations is critical. However, existing alignment approaches,…

Reinforcement Learning from Human Feedback (RLHF) has become a cornerstone for aligning large language models (LLMs) with human values. However, existing approaches struggle to capture the multi-dimensional, distributional nuances of human…

Reinforcement Learning from Human Feedback (RLHF) aligns Large Language Models (LLMs) with human preferences, yet the underlying reward signals they internalize remain hidden, posing a critical challenge for interpretability and safety.…

Reward models are a key component of large language model alignment, serving as proxies for human preferences during training. However, existing evaluations focus primarily on broad instruction-following benchmarks, providing limited…

We study the problem of computing an optimal large language model (LLM) policy for the constrained alignment problem, where the goal is to maximize a primary reward objective while satisfying constraints on secondary utilities. Despite the…

Despite the success of Reinforcement Learning from Human Feedback (RLHF) in aligning language models with human values, reward hacking-or reward over-optimization-remains a major challenge. We identify two key obstacles to its mitigation:…

Reinforcement Learning from Human Feedback (RLHF) has enabled significant advancements within language modeling for powerful, instruction-following models. However, the alignment of these models remains a pressing challenge as the policy…

Large Language Models (LLMs) have achieved remarkable success on reasoning benchmarks through Reinforcement Learning with Verifiable Rewards (RLVR), excelling at tasks such as math, coding, logic, and puzzles. However, existing benchmarks…

As a subfield of machine learning, reinforcement learning (RL) aims at empowering one's capabilities in behavioural decision making by using interaction experience with the world and an evaluative feedback. Unlike traditional supervised…

Reward design is central to reinforcement learning from human feedback (RLHF) and alignment research. In this work, we propose a unified framework to study hard, continuous, and hybrid reward structures for fine-tuning large language models…

Reinforcement learning from human feedback (RLHF) is a prevalent approach to align AI systems with human values by learning rewards from human preference data. Due to various reasons, however, such data typically takes the form of rankings…

The automation of the medical evidence acquisition and diagnosis process has recently attracted increasing attention in order to reduce the workload of doctors and democratize access to medical care. However, most works proposed in the…

Designing reward functions for continuous-control robotics often leads to subtle misalignments or reward hacking, especially in complex tasks. Preference-based RL mitigates some of these pitfalls by learning rewards from comparative…

Misalignment between model predictions and intended usage can be detrimental for the deployment of computer vision models. The issue is exacerbated when the task involves complex structured outputs, as it becomes harder to design procedures…

Conventional reinforcement learning (RL) ap proaches often struggle to learn effective policies under sparse reward conditions, necessitating the manual design of complex, task-specific reward functions. To address this limitation, rein…

Reinforcement learning from verifiable rewards (RLVR) has recently gained attention for its ability to elicit self-evolved reasoning capabilitie from base language models without explicit reasoning supervisions, as demonstrated by…

Aligning human preference and value is an important requirement for contemporary foundation models. State-of-the-art techniques such as Reinforcement Learning from Human Feedback (RLHF) often consist of two stages: 1) supervised fine-tuning…

Aligning large visual generative models with human feedback is often performed through pairwise preference optimization. While such approaches are conceptually simple, they fundamentally rely on annotated pairs, limiting scalability in…