Steering Without Side Effects: Improving Post-Deployment Control of Language Models

Documenti analoghi

• Does Unlearning Truly Unlearn? A Black Box Evaluation of LLM Unlearning Methods
  di: Doshi, Jai, et al.
  Pubblicazione: (2024)
• Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMs
  di: Price, Sara, et al.
  Pubblicazione: (2024)
• Why Do Language Model Agents Whistleblow?
  di: Agrawal, Kushal, et al.
  Pubblicazione: (2025)
• The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
  di: Berglund, Lukas, et al.
  Pubblicazione: (2023)
• Let's Think Dot by Dot: Hidden Computation in Transformer Language Models
  di: Pfau, Jacob, et al.
  Pubblicazione: (2024)