CleanRM is a reward‑modeling approach that mitigates the bias caused by noisy preference data in RLHF. It calibrates sample‑wise noise ratios using a small set of clean feedback via optimal transport, aligning the joint distribution of noisy and clean preferences. The method then trains a reward model with a noise‑corrected surrogate loss, proven to be unbiased with respect to the clean risk, and outperforms existing denoising baselines in experiments.
arXiv:2606. 18066v1 Announce Type: new Abstract: We introduce the Noise-Tilted Reverse Kernel (NTRK), a reward-guided diffusion sampler that injects reward gradients through the noise term, leaving the pretrained reverse kernel unchanged and requiring only a single sample per step.
arXiv:2609.33803v2 Announce Type: replace-cross Abstract: Reward models underpin the alignment of large language models, yet the dominant designs reduce each prompt--response pair to a point estimate...
arXiv:2608. 03929v1 Announce Type: new Abstract: Aligning diffusion models with human preferences usually relies on a sparse terminal reward evaluated on the final generated samples, presenting a severe temporal credit-assignment challenge across the multi-step denoising process.
arXiv:2506. 12529v2 Announce Type: replace-cross Abstract: Preference-based Reinforcement Learning (PbRL) entails a variety of approaches for aligning models with human intent to alleviate the burden of reward engineering.
arXiv:2607. 07693v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) has emerged as a powerful paradigm for aligning generative models with human preferences.
The paper introduces Collaborative Reward Modeling (CRM), an online framework that uses cross-model peer review and curriculum learning to identify reliable preference pairs for training reward models (RMs). By having two RMs evaluate each other's sample selections and synchronizing their learning progress, CRM reduces the impact of noisy feedback, improving RM generalization by up to 9.94 points on RewardBench under 40% preference noise. The approach also extends to implicit-reward alignment, demonstrating robustness and broad applicability for learning from imperfect feedback.
Diffusion models have strong generative capabilities. However, their maximum likelihood training objective only focuses on reconstructing the data distribution, making it difficult to align with specific preferences.
arXiv:2509. 22851v4 Announce Type: replace-cross Abstract: Margin-based optimization is fundamental to improving generalization and robustness in classification tasks.
arXiv:2607. 03248v1 Announce Type: cross Abstract: The alignment of large language models with human preferences is commonly achieved through Reinforcement Learning from Human Feedback or Direct Preference Optimization.
arXiv:2609.38329v1 Announce Type: new Abstract: Group-relative RL methods such as Flow-GRPO post-train image generators by exploring with isotropic Gaussian noise added at every denoising step. This...
arXiv:2606. 01123v1 Announce Type: new Abstract: Preference-based reinforcement learning (PbRL) avoids explicit reward engineering by learning from pairwise human preference feedback.
arXiv:2602. 10623v2 Announce Type: replace-cross Abstract: Reward models learned from human preferences are central to aligning large language models (LLMs) via reinforcement learning from human feedback, yet they are often vulnerable to reward hacking due to noisy annotations and systematic biases such as response length or style.