3 papers
cs.CL2025
Advancing Jailbreak Strategies: A Hybrid Approach to Exploiting LLM Vulnerabilities and Bypassing Modern Defenses
Mohamed Ahmed, Mohamed Abdelmouty, Mingyu Kim +3
The advancement of Pre-Trained Language Models (PTLMs) and Large Language Models (LLMs) has led to their widespread adoption across diverse applications. Despite their success, the…
cs.HC2024
SummAct: Uncovering User Intentions Through Interactive Behaviour Summarisation
Guanhua Zhang, Mohamed Ahmed, Zhiming Hu +1
Recent work has highlighted the potential of modelling interactive behaviour analogously to natural language. We propose interactive behaviour summarisation as a novel computationa…
cs.CL2024
Exploring Retrieval Augmented Generation in Arabic
Samhaa R. El-Beltagy, Mohamed A. Abdallah
Recently, Retrieval Augmented Generation (RAG) has emerged as a powerful technique in natural language processing, combining the strengths of retrieval-based and generation-based m…