3 papers
cs.CL2025
Investigating Bias: A Multilingual Pipeline for Generating, Solving, and Evaluating Math Problems with LLMs
Mariam Mahran, Katharina Simbeck
Large Language Models (LLMs) are increasingly used for educational support, yet their response quality varies depending on the language of interaction. This paper presents an autom…
cs.CL2025
GPT and Prejudice: A Sparse Approach to Understanding Learned Representations in Large Language Models
Mariam Mahran, Katharina Simbeck
Large Language Models (LLMs) are trained on massive, unstructured corpora, making it unclear which social patterns and biases they absorb and later reproduce. Existing evaluations…
cs.LG2025
Mechanistic Interpretability with SAEs: Probing Religion, Violence, and Geography in Large Language Models
Katharina Simbeck, Mariam Mahran
Despite growing research on bias in large language models (LLMs), most work has focused on gender and race, with little attention to religious identity. This paper explores how rel…