I am a PhD candidate in the NLP Group at the University of Vienna, supervised by Prof. Benjamin Roth. My research focuses on how large language models behave under different specifications — from fine-tuning models on data encoding specific functionalities to persona prompting.
I hold a Master’s degree from the University of Brasília, where I worked with Prof. Teo de Campos on building and evaluating language resources for Brazilian legal texts.
News
| August 20, 2025 | 📢 Our paper Principled Personas: Defining and Measuring the Intended Effects of Persona Prompting on Task Performance has been accepted to EMNLP 2025. Looking forward to presenting it in Suzhou! |
| July 30, 2025 | 🎖️ Our paper Influences on LLM Calibration: A Study of Response Agreement, Loss Functions, and Prompt Styles was awarded a SAC Highlight at ACL 2025! |
| July 2025 | 🌟 ACL 2025 in Vienna! Grateful to be part of the organizing committee as Student Volunteer Co-Chair. Also excited about our paper Influences on LLM Calibration: A Study of Response Agreement, Loss Functions, and Prompt Styles, led by my labmate Yuxi Xia, who will present it in a oral session. |
| June 30, 2025 | 📢 Our paper Helpful assistant or fruitful facilitator? Investigating how personas affect language model behavior is now out in PLOS ONE. |