Fairness Archives - Center for Responsible AI

Towards a Detailed and Unbiased Automatic Evaluation of Multilingual Large Language Models

Description Despite the broad adoption of Large Language Models (LLMs), their evaluation primarily relies on superficial numerical scores. In this thesis, the candidate will address this disparity by developing detailed and unbiased automatic evaluation metrics for multilingual language models. The proposed methods will closely align with human judgments, tackle bias, offer multi-dimensional feedback, allow for […]

Ana Oliveira

Linguistics for AI Persona Development and Evaluation

Description We are seeking a dedicated linguistic PhD candidate to join our Halo product that will focus on its linguistic perspective, mainly developing strategies to create and evaluate the AI Persona, such as gathering information about individual preferences such as style, personality traits, and dialogue strategies. The candidate will also focus on dialog annotations as […]

Ana Oliveira