From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning

Documenti analoghi

• Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs
  di: Xu, Xiaoyu, et al.
  Pubblicazione: (2025)
• OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models
  di: Xu, Xiaoyu, et al.
  Pubblicazione: (2025)
• FIT to Forget: Robust Continual Unlearning for Large Language Models
  di: Xu, Xiaoyu, et al.
  Pubblicazione: (2026)
• How Much Do Large Language Model Cheat on Evaluation? Benchmarking Overestimation under the One-Time-Pad-Based Framework
  di: Liang, Zi, et al.
  Pubblicazione: (2025)
• When Routine Chats Turn Toxic: Unintended Long-Term State Poisoning in Personalized Agents
  di: Xu, Xiaoyu, et al.
  Pubblicazione: (2026)