Policy Filtration for RLHF to Mitigate Noise in Reward Models

Documenti analoghi

• Reward-Driven Interaction: Enhancing Proactive Dialogue Agents through User Satisfaction Prediction
  di: Shen, Wei, et al.
  Pubblicazione: (2025)
• Bias Fitting to Mitigate Length Bias of Reward Model in RLHF
  di: Zhao, Kangwen, et al.
  Pubblicazione: (2025)
• FedLPS: Heterogeneous Federated Learning for Multiple Tasks with Local Parameter Sharing
  di: Jia, Yongzhe, et al.
  Pubblicazione: (2024)
• DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices
  di: Jia, Yongzhe, et al.
  Pubblicazione: (2024)
• InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling
  di: Miao, Yuchun, et al.
  Pubblicazione: (2024)