3 papers
cs.CL2026
On the Persistent Effects of Lexicality in Large Language Models
Hammad Rizwan, Muhammad Umair Haider, Nishant Subramani +3
Representations extracted from large language models (LLMs) play an important role in many downstream applications. However, the structure of these representations is often influen…
cs.LG2025
Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution
Muhammad Umair Haider, Hammad Rizwan, Hassan Sajjad +2
Pervasive polysemanticity in large language models (LLMs) undermines discrete neuron-concept attribution, posing a significant challenge for model interpretation and control. We sy…
cs.LG2024
Instance-Level Difficulty: A Missing Perspective in Machine Unlearning
Hammad Rizwan, Mahtab Sarvmaili, Hassan Sajjad +1
Current research on deep machine unlearning primarily focuses on improving or evaluating the overall effectiveness of unlearning methods while overlooking the varying difficulty of…