Bias Detection

Bias detection in artificial intelligence focuses on identifying and mitigating unfairness stemming from biases present in training data and model architectures. Current research emphasizes developing robust and explainable methods for detecting biases across diverse applications, including language models, image generation, and medical decision-making, often leveraging transformer-based models and techniques like anomaly detection or contrastive learning. This work is crucial for ensuring fairness and ethical considerations in AI systems, impacting both the development of more equitable algorithms and the responsible deployment of AI in sensitive domains like healthcare and legal systems.

Papers

October 7, 2024

Enhancing Equity in Large Language Models for Medical Applications
Yuelyu Ji, Wenhe Ma, Sonish Sivarajkumar, Hang Zhang, Eugene Mathew Sadhu, Zhuochun Li, Xizhi Wu, Shyam Visweswaran, Yanshan Wang
Large Language Model Bias Detection Medical Application Equity Context Health Equity Clinical Trial Matching

August 29, 2024

GradBias: Unveiling Word Influence on Bias in Text-to-Image Generative Models
Moreno D'Incà, Elia Peruzzo, Massimiliano Mancini, Xingqian Xu, Humphrey Shi, Nicu Sebe
Absolute Stance Bias Bias Evaluation Bias Detection Text to Image Generative Model Visual Question Answering Model Quantifying Bias Bias Detection Method

August 18, 2024

Say My Name: a Model's Bias Discovery Framework
Massimiliano Ciranni, Luca Molinaro, Carlo Alberto Barbano, Attilio Fiandrotti, Vittorio Murino, Vito Paolo Pastore, Enzo Tartaglione
Full Model Pseudo Label Deep Model Name Translation Bias Detection Potential Bias Biased Feature Pseudo Bias

July 26, 2024

The BIAS Detection Framework: Bias Detection in Word Embeddings and Language Models for European Languages
Alexandre Puttick, Leander Rankwiler, Catherine Ikae, Mascha Kurpicz-Briki
Language Model Word Embeddings Bias Detection BIAS Detection Homogeneity Bias Bias Detection Method

July 24, 2024

Looking at Model Debiasing through the Lens of Anomaly Detection
Vito Paolo Pastore, Massimiliano Ciranni, Davide Marinelli, Francesca Odone, Vittorio Murino
Anomaly Detection Camera Lens Bias Mitigation Bias Detection Model Debiasing Bias Aligned Sample

July 15, 2024

BiasScanner: Automatic Detection and Classification of News Bias to Strengthen Democracy
Tim Menzner, Jochen L. Leidner
Classification Code Automatic Detection Medium Bias Biased Behavior Bias Detection Representative Democracy

July 8, 2024

Epistemological Bias As a Means for the Automated Detection of Injustices in Text
Kenya Andrews, Lamogha Chiazor
Text Modality Automatic Detection Implicit Bias Multiple Meaning Bias Detection Discriminatory Language Stereotype Detection High Epistemic Uncertainty

June 16, 2024

DocNet: Semantic Structure in Inductive Bias Detection Models
Jessica Zhu, Iain Cruickshank, Michel Cukier
Absolute Stance Bias Inductive Bias Semantic Structure Bias Detection BIAS Detection

June 6, 2024

BEADs: Bias Evaluation Across Domains
Shaina Raza, Mizanur Rahman, Michael R. Zhang
Large Language Model Natural Language Processing Bias Evaluation Domain Name Bias Detection Bias Measurement Bias Evaluation Across Domain Benign Data

May 22, 2024

ABI Approach: Automatic Bias Identification in Decision-Making Under Risk based in an Ontology of Behavioral Economics
Eduardo da C. Ramos, Maria Luiza M. Campos, Fernanda Baião
Decision Making Top Level Ontology High Quality Risk Description Cognitive Bias Bias Detection Prospect Theory Risk Aversion Behavioral Economics Risk Preference

May 21, 2024

Reducing Biases towards Minoritized Populations in Medical Curricular Content via Artificial Intelligence for Fairer Health Outcomes
Chiman Salavati, Shannon Song, Willmar Sosa Diaz, Scott A. Hale, Roberto E. Montenegro, Fabricio Murai, Shiri Dori-Hacohen
Artificial Intelligence MAESTRO Dataset Medical Text Topic Bias Underrepresented Group Racial Bias Bias Detection Medical Student

February 6, 2024

Advancing Legal Reasoning: The Integration of AI to Navigate Complexities and Biases in Global Jurisprudence with Semi-Automated Arbitration Processes (SAAPs)
Michael De'Shazer
Artificial Intelligence Complexity Matter Legal Document Legal Reasoning Bias Detection Legal Analysis

February 1, 2024

IndiVec: An Exploration of Leveraging Large Language Models for Media Bias Detection with Fine-Grained Bias Indicators
Luyang Lin, Lingzhi Wang, Xiaoyan Zhao, Jing Li, Kam-Fai Wong
Environment Exploration Social Bias Medium Bias Bias Detection BIAS Detection Fine Grained Bias

January 27, 2024

Semantic Properties of cosine based bias scores for word embeddings
Sarah Schröder, Alexander Schulz, Fabian Hinder, Barbara Hammer
Language Model Absolute Stance Bias Word Embeddings Social Bias Bias Detection Bias Score Semantic Property

September 30, 2023

Unlocking Bias Detection: Leveraging Transformer-Based Models for Content Analysis
Shaina Raza, Oluwanifemi Bamgbose, Veronica Chatrath, Shardul Ghuge, Yan Sidyakin, Abdullah Y Muaad
Transformer Based Model Context Transformer Bias Detection Content Analysis BIAS Detection Bidirectional Transformer Bias Testing

September 3, 2023

Bias Testing and Mitigation in LLM-based Code Generation
Dong Huang, Qingwen Bu, Jie Zhang, Xiaofei Xie, Junjie Chen, Heming Cui
Code Generation Faulty Negative Mitigation Code Generation Model Bias Detection LLM Based Code Generation Bias Testing

August 18, 2023

Data augmentation and explainability for bias discovery and mitigation in deep learning
Agnieszka Mikołajczyk-Bareła
Deep Learning Data Augmentation High Explainability Faulty Negative Mitigation Bias Detection Texture Bias Bias Discovery

July 18, 2023

Automated Ableism: An Exploration of Explicit Disability Biases in Sentiment and Toxicity Analysis Models
Pranav Narayanan Venkit, Mukund Srinath, Shomir Wilson
Environment Exploration Social Bias Implicit Sentiment Toxicity Detection Bias Detection Algorithmic Unfairness Toxicity Detection Model

June 22, 2023

Auditing Predictive Models for Intersectional Biases
Kate S. Boxer, Edward McFowland, Daniel B. Neill
Contextual Biasing Bias Detection Intersectional Bias Bias Detection Method Audit Model Subgroup Fairness

May 22, 2023

Language-Agnostic Bias Detection in Language Models with Bias Probing
Abdullatif Köksal, Omer Faruk Yalcin, Ahmet Akbiyik, M. Tahir Kilavuz, Anna Korhonen, Hinrich Schütze
Language Model Pretrained Language Model Social Bias Bias Detection Language Bias Multilingual Sentiment Nationality Bias

Bias Detection

Papers

Enhancing Equity in Large Language Models for Medical Applications

GradBias: Unveiling Word Influence on Bias in Text-to-Image Generative Models

Say My Name: a Model's Bias Discovery Framework

The BIAS Detection Framework: Bias Detection in Word Embeddings and Language Models for European Languages

Looking at Model Debiasing through the Lens of Anomaly Detection

BiasScanner: Automatic Detection and Classification of News Bias to Strengthen Democracy

Epistemological Bias As a Means for the Automated Detection of Injustices in Text

DocNet: Semantic Structure in Inductive Bias Detection Models

BEADs: Bias Evaluation Across Domains

ABI Approach: Automatic Bias Identification in Decision-Making Under Risk based in an Ontology of Behavioral Economics

Reducing Biases towards Minoritized Populations in Medical Curricular Content via Artificial Intelligence for Fairer Health Outcomes

Advancing Legal Reasoning: The Integration of AI to Navigate Complexities and Biases in Global Jurisprudence with Semi-Automated Arbitration Processes (SAAPs)

IndiVec: An Exploration of Leveraging Large Language Models for Media Bias Detection with Fine-Grained Bias Indicators

Semantic Properties of cosine based bias scores for word embeddings

Unlocking Bias Detection: Leveraging Transformer-Based Models for Content Analysis

Bias Testing and Mitigation in LLM-based Code Generation

Data augmentation and explainability for bias discovery and mitigation in deep learning

Automated Ableism: An Exploration of Explicit Disability Biases in Sentiment and Toxicity Analysis Models

Auditing Predictive Models for Intersectional Biases

Language-Agnostic Bias Detection in Language Models with Bias Probing