Artificial Intelligence

Language Model Evaluation and Comparison Tool

2023

Master's Thesis | Computer Science and Engineering | Instituto Superior Técnico 

Internship:  INESC-ID | Unbabel

'This dissertation is particularly relevant in the current context of AI and NLP, where the quality and fairness of language models are under intense scrutiny. Bias issues are critical to ensuring that these models are fair and do not reinforce negative stereotypes, such as gender, racial, or social biases.

This work not only contributes to the technical advancement of NLP model evaluation but also addresses essential ethical issues in AI development.'

(OpenAI, 2025)

doi.org/10.13140/RG.2.2.33749.64488/1

Keywords: Natural Language Processing, Evaluation Tool, Evaluation Metrics, Bias, Aggregation Mechanisms, Linguistic Phenomena 

CIÊNCIAvitae