Portrait de Abdelrahman Zayed

Abdelrahman Zayed

Doctorat - Polytechnique
Superviseur⋅e principal⋅e
Sarath Chandar
Sujets de recherche
Équité
IA responsable
Traitement du langage naturel
Site web
Google Scholar

Publications

Should We Attend More or Less? Modulating Attention for Fairness
Abdelrahman Zayed
Goncalo Mordido
Samira Shabanian
A. Chandar
2024-07-09
colmweb.org/COLM/2024/Conference (accepté)
doi.org
openreview.net
Why Don't Prompt-Based Fairness Metrics Correlate?
Abdelrahman Zayed
Goncalo Mordido
Ioana Baldini
A. Chandar
The widespread use of large language models has brought up essential questions about the potential biases these models might learn. This led… (voir plus) to the development of several metrics aimed at evaluating and mitigating these biases. In this paper, we first demonstrate that prompt-based fairness metrics exhibit poor agreement, as measured by correlation, raising important questions about the reliability of fairness assessment using prompts. Then, we outline six relevant reasons why such a low correlation is observed across existing metrics. Based on these insights, we propose a method called Correlated Fairness Output (CAIRO) to enhance the correlation between fairness metrics. CAIRO augments the original prompts of a given fairness metric by using several pre-trained language models and then selects the combination of the augmented prompts that achieves the highest correlation across metrics. We show a significant improvement in Pearson correlation from 0.3 and 0.18 to 0.90 and 0.98 across metrics for gender and religion biases, respectively. Our code is available at https://github.com/chandar-lab/CAIRO.
2024-06-08
ArXiv (prépublication)
doi.org
arxiv.org
Fairness-Aware Structured Pruning in Transformers
Abdelrahman Zayed
Goncalo Mordido
Samira Shabanian
Ioana Baldini
A. Chandar
2023-12-23
ArXiv (prépublication)
doi.org
arxiv.org
Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness
Abdelrahman Zayed
Prasanna Parthasarathi
Goncalo Mordido
Hamid Palangi
Samira Shabanian
Sarath Chandar
Data-driven predictive solutions predominant in commercial applications tend to suffer from biases and stereotypes, which raises equity conc… (voir plus)erns. Prediction models may discover, use, or amplify spurious correlations based on gender or other protected personal characteristics, thus discriminating against marginalized groups. Mitigating gender bias has become an important research focus in natural language processing (NLP) and is an area where annotated corpora are available. Data augmentation reduces gender bias by adding counterfactual examples to the training dataset. In this work, we show that some of the examples in the augmented dataset can be not important or even harmful for fairness. We hence propose a general method for pruning both the factual and counterfactual examples to maximize the model's fairness as measured by the demographic parity, equality of opportunity, and equality of odds. The fairness achieved by our method surpasses that of data augmentation on three text classification datasets, using no more than half of the examples in the augmented dataset. Our experiments are conducted using models of varying sizes and pre-training settings.
2022-11-19
ArXiv (prépublication)
doi.org
arxiv.org