no code implementations • 10 Oct 2023 • Piero Esposito, Parmida Atighehchian, Anastasis Germanidis, Deepti Ghadiyaram
In this work, we propose a method to mitigate such biases and ensure that the outcomes are fair across different groups of people.
no code implementations • 23 Aug 2023 • Celio Larcher, Marcos Piau, Paulo Finardi, Pedro Gengo, Piero Esposito, Vinicius Caridá
The main solution to overcome the cost challenge is to rely on available pre-trained models, which, despite recent advancements such as the LLaMA and LLaMA-2 models, still demonstrate inefficiency for certain specific domain problems or prove ineffective in scenarios involving conversational memory resources, given the large number of tokens required to represent text.