Author

N. Al Moubayed

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Oct 2026

Evaluating the Causal Faithfulness of SHAP as a Candidate Attribution Method for SAE Features

Sparse autoencoders decompose language model representations into interpretable features, but feature interpretation in this literature remains predominantly correlational. Attribution methods offer more direct estimates of feature influence, yet their faithfulness to actual causal effects has not been systematically e...

Samuel Xie, N. Al Moubayed · 0 citations

#artificial intelligence Preprint Sep 2026

Harm Laundering in GPT Models: Evidence That Gender Discrimination Is Transformed Rather Than Reduced Across Safety-Trained Generations

Safety evaluations for large language models rely on surface-form classifiers that report declining harm scores across model generations. We provide evidence that this methodology is systematically incomplete: explicit discriminatory content is transformed rather than removed. We call this \emph{harm laundering}. Analy...

S. Wyer, Sue Black, N. Al Moubayed · 0 citations