Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

Authors:
  • KLKenneth Li
    Kenneth Li
  • OPOam Patel
    Oam Patel
  • HPHanspeter Pfister
    Hanspeter Pfister
  • FVFernanda Viégas
    Fernanda Viégas
  • MWMartin Wattenberg
    Martin Wattenberg