On the Hidden Costs of Counterfactual Knowledge Training in LLM Unlearning

Documenti analoghi

• LLM Unlearning Should Be Form-Independent
  di: Ye, Xiaotian, et al.
  Pubblicazione: (2025)
• When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?
  di: Wang, Shang, et al.
  Pubblicazione: (2024)
• Counterfactual Evaluation for Blind Attack Detection in LLM-based Evaluation Systems
  di: Liu, Lijia, et al.
  Pubblicazione: (2025)
• Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM
  di: Wu, Xiaoyu, et al.
  Pubblicazione: (2025)
• SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts
  di: Xin, Yuan, et al.
  Pubblicazione: (2026)