zjunlp/KnowledgeEditingPapers

Issues

• Add New work ”Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces“.

  #16 opened 5 months ago by yihuaihong
  2

• add new work

  #15 opened 5 months ago by kailinjiang
  2

• One more paper may be added: "SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models"

  #14 opened 6 months ago by RadiantCrystal
  1

• Corrections in Method paradigms

  #13 opened 6 months ago by santoshTYSS
  2

• 视频资源

  #12 opened 7 months ago by yuntaodu
  1

• two papers may added: Event-level Knowledge Editing & Updating Language Models with Unstructured Facts

  #11 opened 8 months ago by YuY-2001
  0

• Maybe add Rank-One Editing paper into the paper list?

  #5 opened a year ago by cx-diao
  1

• Request for code

  #3 opened 2 years ago by wutaiqiang
  4