Zara Siddique

(she/her)

Overview

I am a PhD candidate in the School of Computer Science and Informatics, funded by the UKRI’s AIMLAC CDT. My thesis explores how we can conceptualise and quantify harms caused by large language models (LLMs) and how debiasing methods affect intersecting forms of discrimination, e.g. race and gender.

My main research interests lie in the fields of bias in LLMs and AI ethics, as well as political and media bias. I am also a member of the Cardiff NLP research group.