Addressing Bias

Addressing bias in artificial intelligence and data analysis is a crucial area of research aiming to create fairer, more accurate, and reliable models and interpretations. Current efforts focus on mitigating biases through techniques like ensemble learning, regularized fine-tuning, and data augmentation strategies, often employing deep neural networks and large language models. These methods are applied across diverse fields, including medical image analysis, geological interpretation, and social media analysis, with the ultimate goal of improving the trustworthiness and societal impact of AI systems and scientific findings. The significance lies in ensuring equitable outcomes and preventing the perpetuation of harmful stereotypes or inaccuracies in various applications.

Papers

July 19, 2024

Refining Tuberculosis Detection in CXR Imaging: Addressing Bias in Deep Neural Networks via Interpretability
Özgür Acar Güler, Manuel Günther, André Anjos
Deep Neural Network Deep Learning Model Inherent Interpretability Classification Performance Unseen Data Automatic Classification Tuberculosis Treatment Addressing Bias Tuberculosis Detection CXR Imaging

May 17, 2024

Mitigating Interpretation Bias in Rock Records with Large Language Models: Insights from Paleoenvironmental Analysis
Luoqi Wang, Haipeng Li, Linshu Hu, Jiarui Cai, Zhenhong Du
DCU Insight AQ Addressing Bias

February 18, 2024

A Note on Bias to Complete
Jia Xu, Mona Diab
Absolute Stance Bias Social Bias Short Note Addressing Bias Multiple Bias

February 1, 2024

Addressing Bias Through Ensemble Learning and Regularized Fine-Tuning
Ahmed Radwan, Layan Zaafarani, Jetana Abudawood, Faisal AlZahrani, Fares Fourati
Ensemble Learning Length Bias Reliable Prediction Addressing Bias

May 30, 2023

Fighting Bias with Bias: Promoting Model Robustness by Amplifying Dataset Biases
Yuval Reif, Roy Schwartz
Absolute Stance Bias NLP Model Model Robustness Dataset Bias Common Bias Space Bias Addressing Bias

March 13, 2023

Addressing Biases in the Texts using an End-to-End Pipeline Approach
Shaina Raza, Syed Raza Bashir, Sneha, Urooj Qamar
Procedural Fairness Text Based Fair Machine Learning Social Medium Data Model Fairness Medium Bias Addressing Bias End to End Pipeline

October 28, 2022

Addressing Bias in Face Detectors using Decentralised Data collection with incentives
M. R. Ahan, Robin Lehmann, Richard Blythman
Machine Learning Decentralized Data Institutional Incentive Face Embeddings Face Detector Addressing Bias

March 9, 2022

Addressing Bias in Visualization Recommenders by Identifying Trends in Training Data: Improving VizML Through a Statistical Analysis of the Plotly Community Feed
Allen Tu, Priyanka Mehta, Alexander Wu, Nandhini Krishnan, Amar Mujumdar
Machine Learning Training Data Machine Learning Model Addressing Bias RIN Visualization Visualization Recommendation

January 26, 2022

Handling Bias in Toxic Speech Detection: A Survey
Tanmay Garg, Sarah Masud, Tharun Suresh, Tanmoy Chakraborty
Timely Survey Bias Mitigation Toxicity Detection Addressing Bias Toxic Speech Detection

December 16, 2021

Analyzing the Limits of Self-Supervision in Handling Bias in Language
Lisa Bauer, Karthik Gopalakrishnan, Spandana Gella, Yang Liu, Mohit Bansal, Dilek Hakkani-Tur
Language Model Human Language Continuum Limit Self Supervision Natural Language Task Description Addressing Bias Specific Supervision

December 13, 2021

Addressing Bias in Active Learning with Depth Uncertainty Networks... or Not
Chelsea Murray, James U. Allingham, Javier Antorán, José Miguel Hernández-Lobato
Active Learning Generalization Error Depth Network Bias Correction Bias Variance Decomposition Addressing Bias