相关论文: CausalRM: Causal-Theoretic Reward Modeling for RLH…

Current RLHF methods such as PPO and DPO typically reduce human preferences to binary labels, which are costly to obtain and too coarse to reflect individual variation. We observe that expressions of satisfaction and dissatisfaction follow…

Reinforcement learning from human feedback (RLHF) is a variant of reinforcement learning (RL) that learns from human feedback instead of relying on an engineered reward function. Building on prior work on the related setting of…

Reward modeling in large language models is susceptible to reward hacking, causing models to latch onto superficial features such as the tendency to generate lists or unnecessarily long responses. In reinforcement learning from human…

Large Language Models (LLMs) have revolutionized natural language processing, yet aligning these models with human values and preferences using RLHF remains a significant challenge. This challenge is characterized by various instabilities,…

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,…

Techniques that learn improved representations via offline data or self-supervised objectives have shown impressive results in traditional reinforcement learning (RL). Nevertheless, it is unclear how improved representation learning can…

Reward models (RMs) play a crucial role in Reinforcement Learning from Human Feedback by serving as proxies for human preferences in aligning large language models. However, they suffer from various biases which could lead to reward…

Reward models (RMs) are crucial for the training and inference-time scaling up of large language models (LLMs). However, existing reward models primarily focus on human preferences, neglecting verifiable correctness signals which have shown…

Reinforcement Learning from Human Feedback (RLHF) typically relies on static reward models to align Large Language Models with human preferences. However, human values are inherently diverse and heterogeneous, and a single reward model…

Pluralistic alignment has emerged as a critical frontier in the development of Large Language Models (LLMs), with reward models (RMs) serving as a central mechanism for capturing diverse human values. While benchmarks for general response…

Designing effective reward functions is crucial to training reinforcement learning (RL) algorithms. However, this design is non-trivial, even for domain experts, due to the subjective nature of certain tasks that are hard to quantify…

Reinforcement Learning from Human Feedback (RLHF) aligns language models with human preferences but is computationally expensive. We explore two approaches that leverage human gaze modeling to enhance RLHF: (1) gaze-aware reward models and…

Reinforcement learning with verifiable rewards (RLVR) has been shown to enhance the reasoning capabilities of large language models (LLMs), enabling the development of large reasoning models (LRMs). However, LRMs such as DeepSeek-R1 and…

Current audio captioning relies on supervised learning with paired audio-caption data, which is costly to curate and may not reflect human preferences in real-world scenarios. To address this, we propose a preference-aligned audio…

In reinforcement learning with human feedback (RLHF), reward models can efficiently learn and amplify latent biases within multimodal datasets, which can lead to imperfect policy optimization through flawed reward signals and decreased…

Generative reward models (GRMs) have emerged as a promising approach for aligning Large Language Models (LLMs) with human preferences by offering greater representational capacity and flexibility than traditional scalar reward models.…

Current reinforcement learning from human feedback (RLHF) pipelines for large language model (LLM) alignment typically assign scalar rewards to sequences, using the final token as a surrogate indicator for the quality of the entire…

Causal effect estimation from observational data is fundamental across various applications. However, selecting an appropriate estimator from dozens of specialized methods demands substantial manual effort and domain expertise. We present…

Reinforcement learning with human feedback for aligning large language models (LLMs) trains a reward model typically using ranking loss with comparison pairs.However, the training procedure suffers from an inherent problem: the uncontrolled…

Recent advances in speech language models, such as GPT-4o Voice Mode and Gemini Live, have demonstrated promising speech generation capabilities. Nevertheless, the aesthetic naturalness of the synthesized audio still lags behind that of…