Nagham Omar

naghamo

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactuals

upvoted a paper 1 day ago

Alignment Makes Language Models Normative, Not Descriptive

upvoted a paper 1 day ago

MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image

View all activity

Organizations

Papers 1

arxiv:2609.06806

models 0

None public yet

datasets 2

naghamo/idiom-vision-fooling

Viewer • Updated Jul 20 • 400 • 52

naghamo/prompt-variations

Viewer • Updated Jun 5 • 196k • 8 • 1