I obtained a Ph.D. and M.Sc. in Natural Language Processing, both earned in Computer Science and Computational Mathematics from the University of São Paulo (USP). I also hold a BS in Information Systems and a BA in Linguistics. During my Ph.D., I was a visiting researcher at the University of Southern California (USC) in the USA and an invited researcher and speaker at the Leibniz Institute for the Social Sciences (GESIS) in Germany. I was also awarded the prestigious Google Latin America Research Award (LARA) and received the Maria Carolina Monard Award for the Best Thesis in Artificial Intelligence. In addition, I was nominated by the Brazilian Computer Society for the Thesis Awards in the broader Computer Science area and in Multimedia, Hypermedia, and the Web. I have actively contributed to ACL and AAAI international conferences and workshops, serving as a program committee member and co-organizing International AAAI Conference on Web and Social Media (ICWSM), Workshop on Online Abuse and Harms (WOAH), and Explainable Deep Neural Networks for Responsible AI (DeepXplain), along with shared tasks on hate speech [i] [ii]. My research interests focus on enhancing the interpretability and robustness of Language Models (LMs), while ensuring their alignment with safety, factuality, and fairness. I have contributed to efforts addressing hate speech and misinformation in underrepresented communities, and to the development of methods and benchmark datasets that aim to promote transparency and accountability in AI systems.
Awards, Grants and Scholarships
- 2025: Best Thesis in Artificial Intelligence Award (Maria Carolina Monard)
- 2025: Nominated for the Thesis Award in Computer Science (SBC)
- 2025: Nominated for the Thesis Award in Multimedia and Web (SBC)
- 2024: Google Latin America Research Award (LARA)
- 2024: Awarded the ACL D&I Grant (EMNLP)
- 2024: Awarded the ACL D&I Grant (NAACL)
- 2020: Doctoral Research Scholarship (SINCH)
- 2015: Master’s Research Scholarship (CAPES)
- 2013: Undergraduate Research Scholarship (CNPq)
- 2013: Outstanding Academic Achievement Award in CL (UFMG)
- 2012: Outstanding Academic Achievement Award in CL (UFMG)
Research Projects
- Contextual Ranking Models for Retrieval Augmented Natural Language Inference
2025: São Paulo State University & IDIAP Research Institute - Building Evaluation Benchmarks for Hate Speech Detection with Moral Rationales
2024: University of Southern California - Explainable Fact-Checking through Fine-Grained Factual Reasoning
2024: Google - Benchmarking Hate Speech Detection in Hausa Indigenous African Language
2023: University of São Paulo & Federal University of Minas Gerais - Expanding Evaluation Data for Multilingual Protest News Detection
2022: Koç University - Socially Responsible and Explainable Hate Speech Technologies
2020: University of São Paulo & Federal University of Minas Gerais