Mariam Mahran

According to our database, Mariam Mahran authored at least 3 papers in 2025.

Collaborative distances:

• Dijkstra number of six.
• Erdős number of six.

2025

GPT and Prejudice: A Sparse Approach to Understanding Learned Representations in Large Language Models.

Mariam Mahran, Katharina Simbeck

CoRR, October, 2025

Investigating Bias: A Multilingual Pipeline for Generating, Solving, and Evaluating Math Problems with LLMs.

Mariam Mahran, Katharina Simbeck

Proceedings of the 2nd International Workshop on Education for Artificial Intelligence co-located with ECAI 2025, 2025

Mechanistic Interpretability with SAEs: Probing Religion, Violence, and Geography in Large Language Models.

Katharina Simbeck, Mariam Mahran

Proceedings of the 3rd Workshop on Fairness and Bias in AI co-located with 28th European Conference on Artificial Intelligence (ECAI 2025), 2025