The paper 'Localizing Lying in Llama: Understanding Instructed Dishonesty on True-False Questions Through Prompting, Probing, and Patching' by Campbell et al. (2023) investigates instructed dishonesty in Llama models.

Authors

• Person: Not available Organization: GitHub
  Awesome-Hallucination-Detection-and-Mitigation - GitHub

Sources

• Awesome-Hallucination-Detection-and-Mitigation - GitHub github.com GitHub via serper

Referenced by nodes (1)

• LLaMA concept