The paper argues that fairness failures in generative models arise mainly from inadequate evaluation practices, making fairness findings hard to compare or use for deployment. It diagnoses common empirical and conceptual shortcomings in current methods and calls for a move toward standardized, generative‑specific evaluation. The authors introduce Fairness Cards, a minimal reporting artifact that explicitly documents evaluation choices—such as prompt families, counterfactual protocols, metrics, and refusal handling—to improve reproducibility, comparability, and accountability.
By Mariia Vladimirova, Jean-Yves Franceschi, Thibaut Issenhuth
Despite groundbreaking advancements in generative models during the last decade, concerns about their lack of fairness, reinforcing societal inequalities and harming marginalized groups, remain under-...
The paper investigates the tradeoff between fairness and accuracy when a single predictive model serves multiple demographic groups. It introduces the fairness-accuracy (FA) Pareto frontier, which identifies models that cannot be improved in either dimension without compromising the other. Focusing on finite-sample settings, the authors derive worst‑case‑optimal estimators, analyze how limited data asymmetrically affect each group’s welfare, and provide uniform bounds along the entire FA frontier.
By Alireza Fallah, Michael I. Jordan, Annie Ulichney
arXiv:2607. 28934v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly involved in the distribution of scarce resources, raising concerns about biased allocations based on characteristics like race and gender.
By Martin Lukk (University of Toronto)
arXiv:2606. 01719v1 Announce Type: cross Abstract: Machine learning models trained on sensitive data can inadvertently leak population-level information about their training distributions -- a threat known as distribution inference attack (DIA).
By Rakshit Naidu
The paper introduces a targeted learning approach to assess fairness in the data generating process used for training predictive models, rather than focusing solely on model performance. It derives estimators for demographic parity, equal opportunity, and conditional mutual information, and demonstrates through simulations that these estimators improve confidence‑interval coverage and reduce false detections of population unfairness compared to fixed‑model inference. The authors also apply the method to real data to illustrate its practical utility.
By Joseph H. Rudoler, Alexander Asemota, Giles Hooker
arXiv:2407. 14766v4 Announce Type: replace-cross Abstract: This paper presents a philosophical and experimental study of fairness interventions in AI classification, centered on the explainability and transparency of corrective methods, and on the opposition between two fairness criteria, namely Demographic Parity and Equalized Odds.
By Thomas Souverain, Paul \'Egr\'e
The study examines how large language models (LLMs) decide who gets access to restricted academic resources in a controlled simulation. Models consistently favor PhD candidates, but their preferences shift with the requester's region and academic status. Large proprietary LLMs tend to favor low‑income or Global South applicants, while smaller open‑weight models favor the Global North, suggesting that model scale, alignment, and training data influence gatekeeping biases.
By Nouar AlDahoul, Hezerul Abdul Karim, Myles Joshua Toledo Tan
arXiv:2608. 09899v1 Announce Type: new Abstract: In fair ranked link prediction, demographic parity ($\Delta_\mathrm{DP}$) is a common fairness metric.
By Valentijn Oldenburg, Floris de Kam, Stef de Wildt, Jarno Nilson Balk
arXiv:2507. 11548v3 Announce Type: replace-cross Abstract: The use of publicly available generative AI systems for resume evaluation is often justified by the assumption that these tools reduce bias relative to human judgment.
By Kevin T Webster
The study audits demographic bias across four deep knowledge tracing architectures—DKT, DKVMN, SAKT, and AKT—using two large public datasets (Eedi and OULAD). It finds that bias is context‑dependent: socioeconomic bias is significant on Eedi, while gender bias appears on OULAD for most models. The most accurate model, AKT, also exhibits the greatest bias, and standard mitigation techniques such as reweighting and adversarial debiasing fail to reduce bias without sacrificing accuracy.
By Dang Quang Minh, Nguyen Dung Son, Nguyen Huu Loi, Truong Viet Vu, Nguyen Thai Anh
arXiv:2605. 05882v2 Announce Type: replace-cross Abstract: Artificial-intelligence systems are becoming ubiquitous in society, yet their predictions typically inherit biases with respect to protected attributes such as race, gender, or age.
By Filip Edstr\"om, Guilherme W. F. Barros, Tetiana Gorbach, Xavier de Luna