Shirin Dehghani

I'm a graduate Research Assistant and Data Scientist with a passion for advancing technology in Natural Language Processing (NLP), Large Language Models (LLMs) and Artificial Intelligence (AI).

I recently completed my Master's degree in Artificial Intelligence from Allameh Tabataba’i University. My thesis focused on leveraging LLM embeddings for Persian Stance Detection and creating a Persian benchmark, supervised by Dr. Mohammad Reza A. Oskoei.

Currently, I work as a Data Scientist at Metodata, a company specializing in computational social sciences. In my role, I fine-tune large language models (LLMs) like LLaMa and GPT-3.5 for diverse tasks, optimize advanced prompts, and develop AI-based applications, including a cryptocurrency-focused chatbot.

My professional experience includes a research collaboration with the University of Padova. There, I developed an innovative method for matrix completion to enhance recommender systems.

Email  /  CV  /  Google Scholar  /  X  /  Github  /  LinkedIn

My research interests are broad, Natural Language Processing (NLP), Large Language Models (LLMs), Generative AI, Artificial Intelligence and Applied Machine Learning.