FILTER MODE ACTIVE

#reinforcement learning from human feedback

Records found: 2

#reinforcement learning from human feedback07/07/2025

SynPref-40M and Skywork-Reward-V2: Revolutionizing Human-AI Alignment with Scalable Reward Models

SynPref-40M introduces a huge new preference dataset, enabling the Skywork-Reward-V2 family of models to achieve state-of-the-art results in human-AI alignment across multiple benchmarks.

READ →

#reinforcement learning from human feedback04/07/2025

Crome: Google DeepMind's Causal Framework Enhances Reward Modeling for Safer LLM Alignment

Google DeepMind and collaborators introduce Crome, a causal framework that improves reward modeling robustness in LLM alignment by using counterfactual data augmentation to tackle reward hacking issues.

READ →