Algorithmic Bias

Follow this topic Ask about this topic

Algorithmic bias research examines how data imbalances, proxy features, shortcuts, and deployment feedback can produce unequal predictions or treatment. Researchers use group metrics such as demographic parity and equalized odds, counterfactual audits, and subgroup tests on settings including hiring, medical diagnosis, face recognition, and recommendation. Mitigations include data rebalancing, adversarial or decorrelated representations, calibration, pruning, and inference-time steering for language and image-generation models. A central tension is that interventions can trade off accuracy or create new disparities, while fairness metrics and results may not transfer across populations, datasets, or real-world contexts.

Latest papers

101 papers7 papers in the last four weeks, down 30% on the four weeks before. 0.0% of all new papers.

DUCX: Decomposing Unfairness in Tool-Using Chest X-ray Agents
Feb 28, 2026Zikang Xu, Ruinan Jin, Xiaoxiao LiAlgorithmic Fairness Algorithmic Bias
Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Anhui, China · The University of British Columbia, Vancouver, BC V6Z 1Z4, Canada · Vector Institute, Toronto, ON M5G 1M1, Canada
Language Models Exhibit Inconsistent Biases Towards Algorithmic Agents and Human Experts
Feb 25, 2026Jessica Y. Bo, Lillio Mok, Ashton AndersonHuman-AI Decision Making LLM Decision-Making
Computer Science University of Toronto
The Implicit Bias of Adam and Muon on Smooth Homogeneous Neural Networks
Feb 18, 2026Eitan Gronich, Gal VardiGradient Descent Adaptive Gradient Methods
Department of Computer Science and Applied Mathematics, Weizmann Institute of Science, Rehovot, Israel
Toward Trustworthy Portrait Editing: Evaluation of Demographic Misrepresentation in I2I Models
Feb 18, 2026Huichan Seo, Minki Hong, Sieun Choi +2Algorithmic Bias Image Editing Evaluation
Carnegie Mellon University, Pittsburgh, United States · Dongguk University, Seoul, South Korea · Lavoro AI, Pittsburgh, United States
Equity Bias: An Ethical Framework for AI Design
Jan 28, 2026Mary LockwoodAI Ethics Responsible AI
Independent Researcher, United Kingdom
Happy Young Women, Grumpy Old Men? Emotion-Driven Demographic Biases in Synthetic Face Generation
Jan 18, 2026Mengting Wei, Aditya Gulati, Guoying Zhao +1Conditional Image Generation Image Generation
University of Oulu, Oulu, Finland · ELLIS Alicante, Alicante, Spain
ECHO: A Participatory Framework for Bias-Anchored AI Harm Anticipation
Nov 27, 2025Nicoleta Tantalaki, Sophia Vei, Athena VakaliAlgorithmic Bias Human-Centered AI
Aristotle University, Thessaloniki, Greece
On the Societal Impact of Machine Learning
Oct 27, 2025Joachim BaumannAlgorithmic Fairness Algorithmic Bias
Faculty of Business, Economics and Informatics of the University of Zurich
Attribution Graphs and Causal Probing for Mechanistic Discovery and Bias Repair in Multimodal Generative Learning
Oct 14, 2025Noor Islam S. Mohammad, Uluğ BayazıtGradient-Based Attribution Causal Representation Learning
1,2Istanbul Technical University
Unequal Uncertainty: Rethinking Algorithmic Interventions for Mitigating Discrimination from AI
Aug 11, 2025Holli Sargeant, Mackenzie Jorgensen, Arina Shah +3Selective Prediction Algorithmic Fairness
University of Cambridge, United Kingdom · Northumbria University, Newcastle, United Kingdom · George Washington University, Washington D.C., United States +2
When majority rules, minority loses: bias amplification of gradient descent
May 19, 2025François Bachoc, Jérôme Bolte, Ryan Boustany +1Class-Imbalanced Learning Gradient Descent
LPP · University of Lille · Institut Universitaire de France (IUF) +6

Feb 28, 2026J/K move · Enter open · S save

DUCX: Decomposing Unfairness in Tool-Using Chest X-ray Agents

Zikang Xu, Ruinan Jin, Xiaoxiao Li

Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Anhui, China · The University of British Columbia, Vancouver, BC V6Z 1Z4, Canada · Vector Institute, Toronto, ON M5G 1M1, Canada

Algorithmic Fairness Algorithmic Bias AI Agent Auditing Tool-Using Agents Medical VQA

Open paper AskPDF arXiv

Fairness in medical agents is becoming critical as tool-using clinical AI systems orchestrate specialized vision and language modules for tasks such as chest X-ray question answering. While these medical AI agents can improve flexibility, their added pipeline complexity also creates new pathways for demographic bias beyond standalone models. We present DUCK, Decomposing Unfairness in Chest X-ray agents, a systematic audit of fairness in tool-using chest X-ray agents instantiated with MedRAX. To localize where disparities arise, we introduce a stage-wise fairness decomposition that separates end-to-end bias from three agent-specific sources: tool exposure bias, or utility gaps conditioned on tool presence; tool transition bias, or subgroup differences in tool-routing patterns; and model reasoning bias, or subgroup differences in synthesis behaviors. Extensive experiments on tool-using agentic frameworks across five driver backbones reveal that demographic gaps persist in end-to-end performance, with equalized odds up to 20.79% and the lowest fairness-utility tradeoff down to 28.65%. Intermediate behaviors, including tool usage, transition patterns, and reasoning traces, exhibit distinct subgroup disparities that are not predictable from end-to-end evaluation alone. For example, conditioned on segmentation-tool availability, the subgroup utility gap reaches as high as 50%. Our findings underscore the need for process-level fairness auditing and debiasing to ensure the equitable deployment of clinical agentic systems. Code: https://github.com/Nanboy-Ronan/DUCK.