Topic Bias

Topic bias in artificial intelligence (AI) refers to the systematic errors in AI models stemming from skewed training data or algorithmic design, leading to unfair or inaccurate outputs for certain groups or topics. Current research focuses on identifying and mitigating these biases across various AI applications, including language models (LLMs), image recognition systems, and even models used in healthcare and social sciences, employing techniques like adversarial training, fairness-aware algorithms, and bias detection frameworks. Understanding and addressing topic bias is crucial for ensuring fairness, reliability, and ethical deployment of AI systems across diverse contexts, impacting both the development of more robust AI and the equitable application of AI-driven technologies in society.

Papers

November 8, 2024

Equivariant IMU Preintegration with Biases: an Inhomogeneous Galilean Group Approach
Giulio Delama, Alessandro Fornasier, Robert Mahony, Stephan Weiss
Inertial Measurement Unit Topic Bias

October 24, 2024

ConceptDrift: Uncovering Biases through the Lens of Foundational Models
Cristian Daniel Păduraru, Antonio Bărbălau, Radu Filipescu, Andrei Liviu Nicolicioiu, Elena Burceanu
Pre Trained Model Camera Lens Topic Bias Text Datasets Foundational Model Novel Concept

October 18, 2024

Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning
Yuxiang Lu, Shengcao Cao, Yu-Xiong Wang
Full Model Multi Task Learning Knowledge Based Vision Task Topic Bias Vision Foundation Model Representation Bias

October 11, 2024

Hypothesis-only Biases in Large Language Model-Elicited Natural Language Inference
Grace Proebsting, Adam Poliak
Natural Language Scientific Inference LLM Inference Large Language Topic Bias Scientific Hypothesis NLI Model

October 2, 2024

Social coordination perpetuates stereotypic expectations and behaviors across generations in deep multi-agent reinforcement learning
Rebekah A. Gelpí, Yikai Tang, Ethan C. Jackson, William A. Cunningham
Faithful Generation Stereotype Content Topic Bias Behavior Style Stereotypical Bias Coordinated Behavior Complex Coordination

September 28, 2024

FairPIVARA: Reducing and Assessing Biases in CLIP-Based Multimodal Models
Diego A. B. Moreira, Alef Iury Ferreira, Gabriel Oliveira dos Santos, Luiz Pereira, João Medrado Gondim, Gustavo Bonil, Helena Maia, Nádia da Silva, Simone Tiemi Hashiguti, Jefersson A. dos Santos, Helio Pedrini, Sandra Avila
Vision Language Model Multimodal Model Visual Language Model Image Datasets Topic Bias CLIP Model

September 7, 2024

Centralized Selection with Preferences in the Presence of Biases
L. Elisa Celis, Amit Kumar, Nisheeth K. Vishnoi, Andrew Xu
Speech Presence Preference Feedback Group Fairness Task Utility Topic Bias Distributional Assumption Utility Assessment

August 24, 2024

Uncovering Biases with Reflective Large Language Models
Edward Y. Chang
Large Language Model Supervised Learning Topic Bias Unbiased Meta Data

August 7, 2024

Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Models
Shachi H Kumar, Saurav Sahay, Sahisnu Mazumder, Eda Okur, Ramesh Manuvinakurike, Nicole Beckage, Hsuan Su, Hung-yi Lee, Lama Nachman
Language Model Adversarial Prompt Topic Bias Bias Metric LLM a a Judge

August 5, 2024

LLM economicus? Mapping the Behavioral Biases of LLMs via Utility Theory
Jillian Ross, Yoon Kim, Andrew W. Lo
Large Language Model Medical LLM Topic Bias Utility Based Behavioral Economics Behavioral Bias

July 30, 2024

On Biases in a UK Biobank-based Retinal Image Classification Model
Anissa Alloula, Rima Mustafa, Daniel R McGowan, Bartłomiej W. Papież
Bias Mitigation Fundus Image Topic Bias Disease Classification Significant Disparity

July 21, 2024

Decoding Multilingual Moral Preferences: Unveiling LLM's Biases Through the Moral Machine Experiment
Karina Vida, Fabian Damken, Anne Lauscher
Topic Bias Moral Judgment Moral Bias Moral Machine

July 9, 2024

Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equations
Nick McGreivy, Ammar Hakim
Machine Learning Strong Baseline Topic Bias PDE Solver Publication Bias Computational Physic

June 21, 2024

Disability Representations: Finding Biases in Automatic Image Generation
Yannis Tevissen
Meaningful Representation AI Generated Image Topic Bias Image Generation Model Representation Bias Inclusive Artificial Intelligence

June 20, 2024

Modeling Human Subjectivity in LLMs Using Explicit and Implicit Human Factors in Personas
Salvatore Giorgi, Tingting Liu, Ankit Aich, Kelsey Isman, Garrick Sherman, Zachary Fried, João Sedoc, Lyle H. Ungar, Brenda Curtis
Implicit Bias Topic Bias Human Bias Explicit Content Expository Text

June 3, 2024

The Life Cycle of Large Language Models: A Review of Biases in Education
Jinsook Lee, Yann Hicke, Renzhe Yu, Christopher Brooks, René F. Kizilcec
Natural Language Narrative Review Education Domain Topic Bias Algorithmic Bias LLM Integrated Application Life Cycle

May 22, 2024

Unlearning Information Bottleneck: Machine Unlearning of Systematic Patterns and Biases
Ling Han, Hao Huang, Dustin Scheinost, Mary-Anne Hartley, María Rodríguez Martínez
Machine Unlearning Information Bottleneck Complex Pattern Topic Bias Unlearned Model Information Theoretic Framework Effective Adaptation

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 Topic Bias Medical Text Underrepresented Group Racial Bias Bias Detection Medical Student

May 8, 2024

Fair Voting Outcomes with Impact and Novelty Compromises? Unraveling Biases in Electing Participatory Budgeting Winners
Sajan Maharjan, Srijoni Majumdar, Evangelos Pournaras
Topic Bias Voting Method Social Choice Election Result Novelty Reaction Participatory Budgeting Revenue Sharing

May 6, 2024

FairMonitor: A Dual-framework for Detecting Stereotypes and Biases in Large Language Models
Yanhong Bai, Jiabao Zhao, Jinxin Shi, Zhentao Xie, Xingjiao Wu, Liang He
Implicit Bias Topic Bias Subtle Bias Association Test Stereotype Detection

Topic Bias

Papers

Equivariant IMU Preintegration with Biases: an Inhomogeneous Galilean Group Approach

ConceptDrift: Uncovering Biases through the Lens of Foundational Models

Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning

Hypothesis-only Biases in Large Language Model-Elicited Natural Language Inference

Social coordination perpetuates stereotypic expectations and behaviors across generations in deep multi-agent reinforcement learning

FairPIVARA: Reducing and Assessing Biases in CLIP-Based Multimodal Models

Centralized Selection with Preferences in the Presence of Biases

Uncovering Biases with Reflective Large Language Models

Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Models

LLM economicus? Mapping the Behavioral Biases of LLMs via Utility Theory

On Biases in a UK Biobank-based Retinal Image Classification Model

Decoding Multilingual Moral Preferences: Unveiling LLM's Biases Through the Moral Machine Experiment

Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equations

Disability Representations: Finding Biases in Automatic Image Generation

Modeling Human Subjectivity in LLMs Using Explicit and Implicit Human Factors in Personas

The Life Cycle of Large Language Models: A Review of Biases in Education

Unlearning Information Bottleneck: Machine Unlearning of Systematic Patterns and Biases

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

Fair Voting Outcomes with Impact and Novelty Compromises? Unraveling Biases in Electing Participatory Budgeting Winners

FairMonitor: A Dual-framework for Detecting Stereotypes and Biases in Large Language Models