Correcting Large Language Model Behavior via Influence Function

Documenti analoghi

• COPR: Continual Learning Human Preference through Optimal Policy Regularization
  di: Zhang, Han, et al.
  Pubblicazione: (2023)
• COPR: Continual Human Preference Learning via Optimal Policy Regularization
  di: Zhang, Han, et al.
  Pubblicazione: (2024)
• Online Self-Preferring Language Models
  di: Zhai, Yuanzhao, et al.
  Pubblicazione: (2024)
• Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles
  di: Zhai, Yuanzhao, et al.
  Pubblicazione: (2023)
• Mitigating Biases of Large Language Models in Stance Detection with Counterfactual Augmented Calibration
  di: Li, Ang, et al.
  Pubblicazione: (2024)