相关论文: reward-lens: A Mechanistic Interpretability Librar…

Despite the general capabilities of pre-trained large language models (LLMs), they still need further adaptation to better serve practical applications. In this paper, we demonstrate the interchangeability of three popular and distinct…

Reward models are key to language model post-training and inference pipelines. Conveniently, recent work showed that every language model defines an implicit reward model (IM-RM), without requiring any architectural changes. However, such…

Rewards serve as proxies for human preferences and play a crucial role in Reinforcement Learning from Human Feedback (RLHF). However, if these rewards are inherently imperfect, exhibiting various biases, they can adversely affect the…

Reward models (RMs) are central to reinforcement learning from human feedback (RLHF), providing the critical supervision signals that align large language models (LLMs) with human preferences. Generative reward models (GRMs) provide greater…

How can we make models robust to even imperfect human feedback? In reinforcement learning from human feedback (RLHF), human preferences over model outputs are used to train a reward model that assigns scalar values to responses. Because…

Most reward models for visual generation reduce rich human judgments to a single unexplained score, discarding the reasoning that underlies preference. We show that teaching reward models to produce explicit, multi-dimensional critiques…

Understanding the emotions in a dialogue usually requires external knowledge to accurately understand the contents. As the LLMs become more and more powerful, we do not want to settle on the limited ability of the pre-trained language…

Large pretrained models are showing increasingly better performance in reasoning and planning tasks across different modalities, opening the possibility to leverage them for complex sequential decision making problems. In this paper, we…

Recent advances at the intersection of reinforcement learning (RL) and visual intelligence have enabled agents that not only perceive complex visual scenes but also reason, generate, and act within them. This survey offers a critical and…

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…

Reinforcement Learning (RL) in games has gained significant momentum in recent years, enabling the creation of different agent behaviors that can transform a player's gaming experience. However, deploying RL agents in production…

Reward Modeling is critical in evaluating and improving the generation of Large Language Models (LLMs). While numerous recent works have shown its feasibility in improving safety, helpfulness, reasoning, and instruction-following ability,…

Large language models (LLMs) trained with Reinforcement Learning from Human Feedback (RLHF) have demonstrated remarkable capabilities, but their underlying reward functions and decision-making processes remain opaque. This paper introduces…

Reward models (RMs) are central to aligning large language models (LLMs) with human values but have received less attention than pretrained and post-trained LLMs themselves. Because RMs are initialized from LLMs, they inherit…

Vision-language reward modeling faces a dilemma: generative approaches are interpretable but slow, while discriminative ones are efficient but act as opaque "black boxes." To bridge this gap, we propose VL-MDR (Vision-Language…

Reinforcement Learning from Verifiable Rewards (RLVR) has substantially enhanced the reasoning capabilities of large language models in abstract reasoning tasks. However, its application to Large Vision-Language Models (LVLMs) remains…

Designing reward functions is a longstanding challenge in reinforcement learning (RL); it requires specialized knowledge or domain data, leading to high costs for development. To address this, we introduce Text2Reward, a data-free framework…

Reward models (RMs) play a crucial role in aligning large language models (LLMs) with human preferences and enhancing reasoning quality. Traditionally, RMs are trained to rank candidate outputs based on their correctness and coherence.…

Multimodal LLMs often produce fluent yet unreliable reasoning, exhibiting weak step-to-step coherence and insufficient visual grounding, largely because existing alignment approaches supervise only the final answer while ignoring the…

Large Language Models (LLMs) have achieved remarkable success across diverse natural language tasks, yet the reward models employed for aligning LLMs often encounter challenges of reward hacking, where the approaches predominantly rely on…