EAMET: Robust Massive Model Editing via Embedding Alignment Optimization

Documenti analoghi

• Disabling Self-Correction in Retrieval-Augmented Generation via Stealthy Retriever Poisoning
  di: Dai, Yanbo, et al.
  Pubblicazione: (2025)
• SEAL: Subspace-Anchored Watermarks for LLM Ownership
  di: Dai, Yanbo, et al.
  Pubblicazione: (2025)
• STShield: Single-Token Sentinel for Real-Time Jailbreak Detection in Large Language Models
  di: Wang, Xunguang, et al.
  Pubblicazione: (2025)
• Testing and Understanding Erroneous Planning in LLM Agents through Synthesized User Inputs
  di: Ji, Zhenlan, et al.
  Pubblicazione: (2024)
• InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models
  di: Wang, Xunguang, et al.
  Pubblicazione: (2023)