A novel structure-aware reinforcement learning-based method is proposed to exacerbate unfairness in recommender systems by modeling structural and sequential dependencies.

The paper proposes Test-Time Collective Action (TTCA), a framework allowing groups of users to correct algorithmic biases in black-box systems by applying pooled, proxy-based perturbations at inferenc…

This paper investigates how developer attributes influence generated software using AI, finding significant differences in interface design, template content, and code structure based on age and gende…

This paper investigates how individual agent biases amplify system-wide unfairness in multi-agent systems, demonstrating that uniform exposure to bias can elevate overall bias beyond the sum of indivi…

This paper is an invited commentary on Ying Cheng's Psychometrika focus article comparing test fairness and algorithmic fairness. The commentary discusses the distinction between equality and equity a…

This paper addresses the challenge of achieving optimal fairness and accuracy simultaneously in multi-class classification by proposing novel in-processing and post-processing algorithms that converge…

The paper introduces COPF, an online framework that ensures deployment-stable counterfactual fairness in link recommendation systems operating on evolving graphs by monitoring and controlling group di…

This paper proposes a fairness-aware adaptation of graph-based diffusion methods by modifying the Laplacian operator to mitigate bias-related components.

The paper conducts a reproducibility study on FACTER, a model-agnostic framework for fairness and statistical coverage in LLM-based recommendation, and evaluates its consistency and contribution.

The paper proposes TriAlign, a novel multi-agent reinforcement learning framework that achieves universal truth consistency across social groups in personalized LLMs while maintaining high accuracy an…

BiasEdit introduces a training-free framework that automatically detects and edits unknown social biases in web-sourced image datasets to construct a debiased dataset for fair visual classification.

The paper proposes Fair Fine-tuning (FFt), a method that fine-tunes a model using an Equalized Odds constraint on a complementary distribution, and theoretically proves that this approach significantl…

The paper proposes Fair Fine-tuning (FFt), a method that fine-tunes a model using an Equalized Odds constraint on a complementary distribution, and provides a formal theoretical bound linking this fai…

The authors propose a new solution for the content cold-start problem in industry-scale search and recommender systems, reducing bias, improving model prediction, and validating long-term impact.

PS-UIE proposes a privilege-separated architecture to continuously enforce the integrity of file-backed user-space executable objects within Confidential Virtual Machines (CVMs) like AMD SEV-SNP.

The paper argues that current AI content watermarking benchmarks fail to test for bias across different languages, cultures, and demographics, proposing a new set of evaluation standards to ensure fai…

The paper introduces PersTurnBench, a novel benchmark and evaluator for assessing personalized user conversation satisfaction at specific turns, addressing the limitation of generic response quality m…

The paper introduces PAuth, a new authorization model that grants agents only the precise permissions needed for a specific natural-language task, preventing overprivileging inherent in existing opera…