Related papers: Energy-Based Reward Models for Robust Language Mod…

While recent advances have boosted LM proficiency in linguistic benchmarks, LMs consistently struggle to reason correctly on complex tasks like mathematics. We turn to Reinforcement Learning from Human Feedback (RLHF) as a method with which…

Large vision-language models (LVLMs) often fail to align with human preferences, leading to issues like generating misleading content without proper visual context (also known as hallucination). A promising solution to this problem is using…

Reward models (RMs) are a core component in the post-training of large language models (LLMs), serving as proxies for human preference evaluation and guiding model alignment. However, training reliable RMs under limited resources remains…

Personalized alignment of large language models seeks to adapt responses to individual user preferences, typically via reinforcement learning. A key challenge is obtaining accurate, user-specific reward signals in open-ended scenarios.…

Large language models (LLMs) inevitably make mistakes when performing step-by-step mathematical reasoning. Process Reward Models (PRMs) have emerged as a promising solution by evaluating each reasoning step. However, existing PRMs typically…

Reward Model (RM) has demonstrated impressive potential for enhancing Large Language Models (LLM), as RM can serve as a proxy for human preferences, providing signals to guide LLMs' behavior in various tasks. In this paper, we provide a…

The performance of the reward model (RM) is a critical factor in improving the effectiveness of the large language model (LLM) during alignment fine-tuning. There remain two challenges in RM training: 1) training the same RM using various…

Reinforcement Learning from Human Feedback aligns the outputs of Large Language Models with human values and preferences. Central to this process is the reward model (RM), which translates human feedback into training signals for optimising…

While Large Language Models (LLMs) have demonstrated strong math reasoning abilities through Reinforcement Learning with *Verifiable Rewards* (RLVR), many advanced mathematical problems are proof-based, with no guaranteed way to determine…

Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique for aligning large language models (LLMs) with human preferences, yet it is susceptible to reward overoptimization, in which policy models overfit to the reward model,…

The success of Reinforcement Learning from Human Feedback (RLHF) in language model alignment is critically dependent on the capability of the reward model (RM). However, as the training process progresses, the output distribution of the…

Reinforcement learning has become the central approach for language models (LMs) to learn from environmental reward or feedback. In practice, the environmental feedback is usually sparse and delayed. Learning from such signals is…

Reward models have been increasingly critical for improving the reasoning capability of LLMs. Existing research has shown that a well-trained reward model can substantially improve model performances at inference time via search. However,…

Reasoning large language models (LLMs) excel in complex tasks, which has drawn significant attention to reinforcement learning (RL) for LLMs. However, existing approaches allocate an equal number of rollouts to all questions during the RL…

Energy-based models (EBMs) have experienced a resurgence within machine learning in recent years, including as a promising alternative for probabilistic regression. However, energy-based regression requires a proposal distribution to be…

Reward Models, essential for guiding Large Language Model optimization, are typically trained on fixed preference datasets, resulting in rigid alignment to single, implicit preference distributions. This prevents adaptation to diverse…

Preference optimization, particularly through Reinforcement Learning from Human Feedback (RLHF), has achieved significant success in aligning Large Language Models (LLMs) to adhere to human intentions. Unlike offline alignment with a fixed…

Reward models (RMs) are central to the alignment of language models (LMs). An RM often serves as a proxy for human preferences to guide downstream LM behavior. However, our understanding of RM behavior is limited. Our work (i) formalizes a…

Energy-based language models (ELMs) parameterize an unnormalized distribution for natural sentences and are radically different from popular autoregressive language models (ALMs). As an important application, ELMs have been successfully…

Reward Machines (RMs) are an established mechanism in Reinforcement Learning (RL) to represent and learn sparse, temporally extended tasks with non-Markovian rewards. RMs rely on high-level information in the form of labels that are emitted…