Towards Resilient and Efficient LLMs: A Comparative Study of Efficiency, Performance, and Adversarial Robustness

Documenti analoghi

• Harnessing LLMs for API Interactions: A Framework for Classification and Synthetic Data Generation
  di: Tao, Chunliang, et al.
  Pubblicazione: (2024)
• LoRA-LiteE: A Computationally Efficient Framework for Chatbot Preference-Tuning
  di: Yang, Yahe, et al.
  Pubblicazione: (2024)
• On the Robustness of Verbal Confidence of LLMs in Adversarial Attacks
  di: Obadinma, Stephen, et al.
  Pubblicazione: (2025)
• PEARL: Towards Permutation-Resilient LLMs
  di: Chen, Liang, et al.
  Pubblicazione: (2025)
• Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs
  di: Cha, Sungmin, et al.
  Pubblicazione: (2024)