collaborators

5 papers

cs.AI2026

Multi-Granular Node Pruning for Causal Circuit Discovery

Muhammad Umair Haider, Hammad Rizwan, Hassan Sajjad +1

Circuit discovery aims to identify minimal subnetworks that are responsible for specific behaviors in large language models (LLMs). Existing approaches primarily rely on iterative…

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.LG2026

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.CL2025

Resolving Lexical Bias in Model Editing

Hammad Rizwan, Domenic Rosati, Ga Wu +1

Model editing aims to modify the outputs of large language models after they are trained. Previous approaches have often involved direct alterations to model weights, which can res…

cs.LG2025

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…