João A.
Leite

Senior Applied Scientist at Microsoft

I develop methods to evaluate and improve the safety and reliability of language models.

João A. Leite

Selected publications

LLM-Based Adversarial Persuasion Attacks on Fact-Checking Systems

João A. Leite, Olesya Razuvayevskaya, Kalina Bontcheva, Carolina Scarton

Tailored untruths: How personalisation challenges LLM safeguards

João A. Leite, João Luz, Silvia Gargova, Arnav Arora, Gustavo Sampaio, Ian Roberts, Carolina Scarton, Kalina Bontcheva

Weakly Supervised Veracity Classification with LLM-Predicted Credibility Signals

João A. Leite, Olesya Razuvayevskaya, Kalina Bontcheva, Carolina Scarton

A Cross-Domain Study of the Use of Persuasion Techniques in Online Disinformation

João A. Leite, Olesya Razuvayevskaya, Carolina Scarton, Kalina Bontcheva

EUvsDisinfo: A Dataset for Multilingual Detection of Pro-Kremlin Disinformation in News Articles

João A. Leite, Olesya Razuvayevskaya, Kalina Bontcheva, Carolina Scarton

Toxic Language Detection in Social Media for Brazilian Portuguese

João A. Leite, Diego Silva, Kalina Bontcheva, Carolina Scarton

Show all publications Show selected publications

Build it, Break it, Repeat: Benchmarking and improving LLM-manipulated disinformation detection in social media posts

Kevin Thomas, Milosz Kasprzyk, Reuel C Igbokwe Onuigbo, Elliott Pert, Cameron Tovey, João A. Leite, Olesya Razuvayevskaya, Carolina Scarton

A Survey on Automatic Credibility Assessment Using Textual Credibility Signals in the Era of Large Language Models

Ivan Srba, Olesya Razuvayevskaya, João A. Leite, Robert Moro, Ipek Baris Schlicht, Sara Tonelli, Francisco Moreno García, and others

Comparison Between Parameter-Efficient Techniques and Full Fine-Tuning

Olesya Razuvayevskaya, Ben Wu, João A. Leite, Freddy Heppell, Ivan Srba, Carolina Scarton, Kalina Bontcheva, Xingyi Song

SheffieldVeraAI at SemEval-2023 Task 3

Ben Wu, Olesya Razuvayevskaya, Freddy Heppell, João A. Leite, Carolina Scarton, Kalina Bontcheva, Xingyi Song

Noisy Self-Training with Data Augmentations for Offensive and Hate Speech Detection Tasks

João A. Leite, Carolina Scarton, Diego Silva

NELL’s subcategories from a question answering environment

Wesley W. O. Souza, Diorge Brognara, João A. Leite, Estevam R. Hruschka Jr.

Writing

Transformers

Updates

Joined Microsoft as a Senior Applied Scientist.

Graduated with a PhD in Computer Science from the University of Sheffield.

Led an in-house research hackathon with four invited researchers.

Earlier updates

Attended the Lisbon Machine Learning School, sponsored by a Google and Zendesk scholarship.

Became a Research Associate at the University of Sheffield.

Began my PhD in Computer Science at the University of Sheffield, sponsored by an EPSRC DTP Scholarship.

Joined PicPay as a Data Scientist.

My AACL paper received the Best Paper award at Universidade Federal de São Carlos.

Graduated with a bachelor's degree in Computer Science from Universidade Federal de São Carlos.

Joined Birdie.ai as a Data Scientist.