Fairness Evaluation

Fairness evaluation in artificial intelligence aims to identify and mitigate biases in algorithms, ensuring equitable outcomes across different demographic groups. Current research focuses on developing and applying fairness metrics to various model architectures, including graph neural networks, large language models, and computer vision systems, often employing techniques like score normalization and multitask learning to improve fairness without sacrificing accuracy. This field is crucial for building responsible AI systems, impacting not only scientific understanding of algorithmic bias but also the ethical deployment of AI in high-stakes applications like healthcare, law enforcement, and loan applications. A key challenge lies in the lack of standardized evaluation frameworks and the need for methods robust to noisy or incomplete data on protected attributes.

Papers

July 6, 2023

When Fair Classification Meets Noisy Protected Attributes
Avijit Ghosh, Pablo Kvitca, Christo Wilson
Algorithmic Fairness Fairness Evaluation Fair Classification FAir Classifier Protected Attribute Blind Algorithm

May 29, 2023

Counterpart Fairness -- Addressing Systematic between-group Differences in Fairness Evaluation
Yifei Wang, Zhengyang Zhou, Liqin Wang, John Laurentiev, Peter Hou, Li Zhou, Pengyu Hong
Fairness Evaluation Fairness Performance Group Difference

May 22, 2023

Fairness of ChatGPT
Yunqi Li, Lanjing Zhang, Yongfeng Zhang
ChatGPT Generated Conversation Procedural Fairness Bias Mitigation Group Fairness Fairness Evaluation Fairness Performance

March 1, 2023

Fairness Evaluation in Text Classification: Machine Learning Practitioner Perspectives of Individual and Group Fairness
Zahra Ashktorab, Benjamin Hoover, Mayank Agarwal, Casey Dugan, Werner Geyer, Hao Bang Yang, Mikhail Yurochkin
Text Classification Group Fairness Model Fairness Algorithmic Bias Individual Fairness Fairness Evaluation Individual Perspective Fairness Assessment

October 9, 2022

Quantifying Social Biases Using Templates is Unreliable
Preethi Seshadri, Pouya Pezeshkpour, Sameer Singh
Social Bias Deep Template Fairness Evaluation Bias Measurement Template Based Value Bias

October 7, 2022

An Analysis of the Effects of Decoding Algorithms on Fairness in Open-Ended Language Generation
Jwala Dhamala, Varun Kumar, Rahul Gupta, Kai-Wei Chang, Aram Galstyan
Language Model General Analysis Practical Algorithm Procedural Fairness Mixed Effect Fairness Evaluation Open Ended Text Generation

September 27, 2022

Fairness in Medical Image Analysis and Healthcare: A Literature Survey
Zikang Xu, Jun Li, Qingsong Yao, Han Li, S. Kevin Zhou
Procedural Fairness Medical Image Analysis Healthcare System Fairness Evaluation Fairness Research Literature Survey

September 25, 2022

Re-contextualizing Fairness in NLP: The Case of India
Shaily Bhatt, Sunipa Dev, Partha Talukdar, Shachi Dave, Vinodkumar Prabhakaran
Natural Language NLP Field Case Relevance Fairness Evaluation NLP Fairness

July 11, 2022

How Robust is your Fair Model? Exploring the Robustness of Diverse Fairness Strategies
Edward Small, Wei Shao, Zeliang Zhang, Peihan Liu, Jeffrey Chan, Kacper Sokol, Flora Salim
Native Robustness Fairness Evaluation Fair Model Fairness Method Robustness Measurement Fairness Benchmark Datasets

July 8, 2022

On the Need and Applicability of Causality for Fair Machine Learning
Rūta Binkytė, Ljupcho Grozdanovski, Sami Zhioua
Procedural Fairness Causal Pattern Community Need Fair Machine Learning Fairness Evaluation Applicability Study Causal Prediction Causal View

June 6, 2022

A Justice-Based Framework for the Analysis of Algorithmic Fairness-Utility Trade-Offs
Corinna Hertweck, Joachim Baumann, Michele Loi, Eleonora Viganò, Christoph Heitz
General Analysis Pareto Optimal Value Laden Choice Fairness Evaluation Decision Making System Prediction Based Decision Making Fairness Utility Trade

May 4, 2022

fairlib: A Unified Framework for Assessing and Improving Classification Fairness
Xudong Han, Aili Shen, Yitong Li, Lea Frermann, Timothy Baldwin, Trevor Cohn
Unified Framework Debiasing Method Fairness Evaluation Fairness Criterion

March 14, 2022

Fairness Evaluation in Deepfake Detection Models using Metamorphic Testing
Muxin Pu, Meng Yi Kuan, Nyee Thoang Lim, Chun Yong Chong, Mei Kuan Lim
Deep Learning Deepfake Detector Fairness Evaluation Deepfake Detection Model Metamorphic Testing

February 15, 2022

Fairness Indicators for Systematic Assessments of Visual Feature Extractors
Priya Goyal, Adriana Romero Soriano, Caner Hazirbas, Levent Sagun, Nicolas Usunier
Computer Vision Computer Vision Model Fairness Evaluation Fairness Assessment

December 14, 2021

Measuring Fairness with Biased Rulers: A Survey on Quantifying Biases in Pretrained Language Models
Pieter Delobelle, Ewoenam Kwaku Tokpo, Toon Calders, Bettina Berendt
Language Model Timely Survey Pretrained Language Model Fairness Metric Bias Evaluation Fairness Evaluation Quantifying Bias Embedding Based Metric