Paper 'Principled Personas: Defining and Measuring the Intended Effects of Persona Prompting on Task Performance' accepted to EMNLP 2025; Paper 'Influences on LLM Calibration: A Study of Response Agreement, Loss Functions, and Prompt Styles' awarded a SAC Highlight at ACL 2025; Part of the organizing committee as Student Volunteer Co-Chair for ACL 2025; Paper 'Helpful assistant or fruitful facilitator? Investigating how personas affect language model behavior' published in PLOS ONE.
Research Experience
PhD candidate in the NLP Group at the University of Vienna, conducting research on large language models.
Education
PhD student at the University of Vienna, supervised by Prof. Benjamin Roth; Master’s degree from the University of Brasília, supervised by Prof. Teo de Campos, focusing on building and evaluating language resources for Brazilian legal texts.
Background
Research interests include how large language models behave under different specifications, from fine-tuning models on data encoding specific functionalities to persona prompting.
Miscellany
Pronouns: he/they; Based in Vienna, Austria; Social media: GitHub, Google Scholar, Bluesky.