Papers by Apostolos Modas

1 papers
Resampled Datasets Are Not Enough: Mitigating Societal Bias Beyond Single Attributes (2024.emnlp-main)

Copied to clipboard

Challenge: Traditional approaches only target labeled attributes, ignoring biases from unlabeled ones.
Approach: They propose a method that ensures protected group independence from all attributes and mitigates inpainting biases through data filtering.
Outcome: The proposed approach achieves an average reduction of 46.1% in leakage-based bias metrics for multi-label classification and 74.8% for image captioning.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations