Projects
Funded research projects I lead (from 2023 onwards).
Current 4
Knowledge-Aware Language Models
Integrating structured and unstructured knowledge into neural language representations for more interpretable, robust and data-efficient NLP.
Knowledge-Enhanced NLP for Social Impact
Knowledge-enhanced NLP for socially relevant problems (misinformation, harmful content, health communication), with a focus on Brazilian Portuguese.
ESG Knowledge Bases for Responsible Generative AI
Structured ESG knowledge bases built from public corporate disclosures to ground and evaluate generative AI systems.
eXplainable MUltilingual Reasoning
Evaluating and explaining how LLMs reason across languages, and why they process equivalent problems differently.
Past 3
AI for Financial Document Analysis
NLP and LLM methods to extract, interpret and summarize information from financial documents, focused on the Brazilian market.
Low-Resource ML for Social Impact
Machine learning under scarce data, low compute and underrepresented languages, applied to health, safety and social inclusion.
Personalized Investment Advisory Focused on ESG Practices Using Generative AI
Investigates the integration of small and large language models (SLMs and LLMs) to support the generation of accurate, reliable, and personalized financial analyses aligned with ESG principles.