3 papers
cs.SE2026
Revisiting Code Debloating with Ground Truth-based Evaluation
Muhammad Bilal, Moiz Ali, Mohit Kumar +4
Program debloating aims to remove unused code to reduce performance overhead, attack surfaces, and maintenance costs. Over time, debloating has evolved across multiple layers (cont…
cs.CL2025
Data Doping or True Intelligence? Evaluating the Transferability of Injected Knowledge in LLMs
Essa Jan, Moiz Ali, Muhammad Saram Hassan +2
As the knowledge of large language models (LLMs) becomes outdated over time, there is a growing need for efficient methods to update them, especially when injecting proprietary inf…
cs.CL2024
Multitask Mayhem: Unveiling and Mitigating Safety Gaps in LLMs Fine-tuning
Essa Jan, Nouar AlDahoul, Moiz Ali +3
Recent breakthroughs in Large Language Models (LLMs) have led to their adoption across a wide range of tasks, ranging from code generation to machine translation and sentiment anal…