1 citations · 2 across the 9 of their papers we have counts for
4 papers · 1 filter
WAQS: Weight Absorption for Quadratic Probing and Affine Steering
Ding Zhu, Mohammad Mahdi Khalili
Activation steering provides a lightweight alternative to fine-tuning for controlling large language model behavior. Existing methods, however, often face a trade-off between effic…
When Pruning Meets Interpretability: Preserving Sparse Autoencoder Robustness in LLMs
Suchit Gupte, Xueru Zhang, Mohammad Mahdi Khalili
Sparse autoencoders (SAEs) are widely used to interpret the internal representations of large language models (LLMs), yet their reliability under post-hoc model compression remains…
tensorFM: Low-Rank Approximations of Cross-Order Feature Interactions
Alessio Mazzetto, Mohammad Mahdi Khalili, Laura Fee Nern +3
We address prediction problems on tabular categorical data, where each instance is defined by multiple categorical attributes, each taking values from a finite set. These attribute…
Individual Fairness In Strategic Classification
Zhiqun Zuo, Mohammad Mahdi Khalili
Strategic classification, where individuals modify their features to influence machine learning (ML) decisions, presents critical fairness challenges. While group fairness in this…