Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Models

Documenti analoghi

• How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study
  di: Ju, Tianjie, et al.
  Pubblicazione: (2024)
• Probing then Editing Response Personality of Large Language Models
  di: Ju, Tianjie, et al.
  Pubblicazione: (2025)
• Transferring Backdoors between Large Language Models by Knowledge Distillation
  di: Cheng, Pengzhou, et al.
  Pubblicazione: (2024)
• TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models
  di: Cheng, Pengzhou, et al.
  Pubblicazione: (2024)
• Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models
  di: Ju, Tianjie, et al.
  Pubblicazione: (2025)