Tag: Safety Alignment

All the papers with the tag "Safety Alignment".

• Fight Fire with Fire: Defending Against Malicious RL Fine-Tuning via Reward Neutralization

  grok-3-latest

  Score: 0.66

  Published:2025年5月7日 at  at 17:18

  #LLM, #Reinforcement Learning, #Safety Alignment, #Reward Design, #Fine-Tuning

  本文提出Reward Neutralization框架，通过训练模型生成最小信息拒绝来中和恶意RL微调的奖励信号，显著提升开源模型在攻击下的安全性。