Graph of Attacks: Improved Black-Box and Interpretable Jailbreaks for LLMs

1 code implementation • 26 Apr 2025 • Mohammad Akbar-Tajari, Mohammad Taher Pilehvar, Mohammad Mahmoody

Identifying these vulnerabilities is crucial for enhancing the robustness of LLMs against such exploits.

An Empirical Study on the Transferability of Transformer Modules in Parameter-Efficient Fine-Tuning

no code implementations • 1 Feb 2023 • Mohammad Akbar-Tajari, Sara Rajaee, Mohammad Taher Pilehvar

Parameter-efficient fine-tuning approaches have recently garnered a lot of attention.

parameter-efficient fine-tuning Transfer Learning