EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-Forget

Documenti analoghi

• Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning
  di: Chen, Liang, et al.
  Pubblicazione: (2025)
• Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning
  di: Chen, Liang, et al.
  Pubblicazione: (2025)
• IndiVec: An Exploration of Leveraging Large Language Models for Media Bias Detection with Fine-Grained Bias Indicators
  di: Lin, Luyang, et al.
  Pubblicazione: (2024)
• Selective Forgetting: Advancing Machine Unlearning Techniques and Evaluation in Language Models
  di: Wang, Lingzhi, et al.
  Pubblicazione: (2024)
• Enhancing Robustness of Autoregressive Language Models against Orthographic Attacks via Pixel-based Approach
  di: Yang, Han, et al.
  Pubblicazione: (2025)