3 papers · 1 filter
Safety Is Not Universal: The Selective Safety Trap in LLM Alignment
Iago Alves Brito, Walcy Santos Rezende Rios, Julia Soares Dollis +2
Current safety evaluations of large language models (LLMs) create a dangerous illusion of universal protection by aggregating harms under generic categories such as "Identity Hate"…
ToxSyn-PT: A Synthetic Fine-Grained Dataset of Minority-Targeted Toxic Language in Portuguese
Iago Alves Brito, Julia Soares Dollis, Fernanda Bufon Farber +2
The development of robust hate speech detection systems remains limited by the lack of large-scale, fine-grained training data, especially for languages beyond English. Existing co…
MedPT: A Massive Medical Question Answering Dataset for Brazilian-Portuguese Speakers
Fernanda Bufon Färber, Iago Alves Brito, Julia Soares Dollis +3
While large language models (LLMs) show transformative potential in healthcare, their development remains focused on high-resource languages. This creates a critical barrier for ot…