Responsible AI

Detecting contextual biases in language models

Melissa Robles presents her research on bias detection in supervised models and language models, with particular attention to contextual biases in Spanish, as part of her work in Responsible AI (RAI), including her involvement in the SESGO project (Spanish Evaluation of Stereotypical Generative Outputs).

Melissa Robles Carmona
Data Scientist at Sezzle (fintech sector)
A mathematician with a master's degree in Systems Engineering from Universidad de los Andes, Colombia, she works professionally as a Data Scientist in the fintech sector at Sezzle, and has experience leading data mining consultancy projects. Academically, her research has focused on Responsible AI (RAI), particularly bias detection in supervised models and language models, as well as building translation models for indigenous languages and unsupervised models for genomic data.
Melissa Robles Carmona
More information