
Stefano Civelli
HDR Student in AI at UQ
I am a PhD student in Computer Science at The University of Queensland, focusing on Large Language Models (LLMs).
Previously, I worked for a small startup in Milan, obtained my Master's degree in Computer Science from Politecnico di Milano (POLIMI) and then worked as a Research Assistant at The University of Queensland.
I also work as a tutor at UQ.
Recent Research
A Shared Geometry of Difficulty in Multilingual Language Models
Stefano Civelli, Pietro Bernardelle, Nicolò Brunello, Gianluca Demartini
ACL 2026. 2026
Ideology-Based LLMs for Content Moderation
Stefano Civelli, Pietro Bernardelle, Nardiena A Pratama, Gianluca Demartini
TIST - Special Issue on Risks and Unintended Harms of Generative AI Systems. 2026
Political Advertising on Facebook During the 2022 Australian Federal Election: A Social Identity Perspective
Stefano Civelli, Pietro Bernardelle, Frank Mols, Gianluca Demartini
ICWSM 2026. 2026
Resume
- PhD in Artificial Intelligence at The University of QueenslandOct. 2024Researching core aspects of Large Language Models (LLMs) like prompt complexity and bias. Developing novel methods to measure and predict query complexity for LLMs.
- Research Assistant at The University of QueenslandFeb. 2024 - Aug. 2024Conducted research on LLMs for classification of harmful content. Implemented multimodal ML models in PyTorch. Analyzed Facebook ads for political campaigns. Deployed AWS-based dashboard for campaign analysis.
- ML Engineer Intern at ML cubeApr. 2023 - Dec. 2023Developed RL solution for AGV mission time estimation. Implemented classic and distributional RL algorithms for time estimation.
- M.Sc. in Computer Science and Engineering at POLIMISep. 2021 - Dec. 2023Graduated with 110L/110. Main courses: Machine Learning, Neural Networks, Distributed Systems, Data Streaming, Recommender Systems. Received Merit-Based Scholarship for two consecutive years.
- B.Sc. in Computer Science and Engineering at POLIMISep. 2018 - Jul. 2021Graduated with 109/110. Main courses: software engineering, databases, algorithms & data structures, statistics, linear algebra. Awarded Best freshmen 2018/2019.