Many real-world problems, such as those with fairness constraints, involve complex expectation constraints and large datasets, necessitating the design of efficient stochastic methods to solve them. Most existing research focuses on cases with no {constraint} or easy-to-project constraints or deterministic constraints. In this paper, we consider nonconvex nonsmooth stochastic optimization problems with expectation constraints, for which we build a novel exact penalty model. We first show the relationship between the penalty model and the original problem. Then on solving the penalty problem, we present a single-loop SPIDER-type stochastic subgradient method, which utilizes the subgradients of both the objective and constraint functions, as well as the constraint function value at each iteration. Under certain regularity conditions (weaker than Slater-type constraint qualification or strong feasibility assumed in existing works), we establish an iteration complexity result of $O(\epsilon^{-4})$ to reach a near-$\epsilon$ stationary point of the penalized problem in expectation, matching the lower bound for such tasks. Building on the exact penalization, an $(\epsilon,\epsilon)$-KKT point of the original problem is obtained. For a few scenarios, our complexity of either the {objective} sample subgradient or the constraint sample function values can be lower than the state-of-the-art results by a factor of $\epsilon^{-2}$. Moreover, on solving two fairness-constrained problems and a multi-class Neyman-Pearson classification problem, our method is significantly (up to 466 times) faster than the state-of-the-art algorithms, including switching subgradient method and inexact proximal point methods.
Artificial Intelligence (AI) can undermine and strengthen democratic governance. This paper introduces the AIRD/AIPD framework, a dual taxonomy and operational framework for analyzing AI's democratic risks and conditional contributions. The AI Risks to Democracy (AIRD) taxonomy identifies threats to autonomy, fairness, public discourse, democratic institutions, and trust, while the AI's Positive Contributions to Democracy (AIPD) taxonomy captures AI's potential to enhance efficiency, accessibility, security, informed citizenry, transparency and accountability, inclusive democratic dialogue, and evidence-based policymaking. Grounded in five democratic principles and the seven Trustworthy AI requirements proposed by the European Commission's High-Level Expert Group on AI, the framework connects democratic goals with governance and design mechanisms. It provides an operational process for identifying affected contexts and actors, classifying primary and secondary AIRD/AIPD effects, mapping them to relevant Trustworthy AI requirements, and defining proportionate governance responses and responsible actors. An operational mapping and two worked examples illustrate its application to electoral misinformation and AI-assisted public service allocation. The analysis highlights the transversal relevance of transparency, accountability, fairness, and societal wellbeing, while recognizing trade-offs, implementation costs, differential impacts, institutional capacity, and contextual variation across democratic settings. The framework is conceptual and has not been empirically validated, but it offers a traceable and adaptable basis for research, policy analysis, institutional oversight, and responsible AI design. By connecting democratic diagnosis with governance action, it bridges the gap between normative principles and the operational requirements of trustworthy and democratically legitimate AI.
Large Language Models (LLMs) are increasingly being employed for downstream tasks such as tabular classification, where predictions can directly influence individuals in high-stakes domain such as hiring, education and criminal justice. As the adoption of LLMs for such decision making tasks continues to grow, ensuring fairness in their predictions becomes increasingly important. Existing approaches to ensure fairness in tabular data, typically process test instances independently, limiting the models awareness of the demographic composition and predictions of other instances, which is particularly important for reasoning about group-level fairness. To address this limitation, we propose FABLE (FAir Batch-based LLM framEwork) for tabular classification, a batch-based framework that jointly processes multiple test instances, enabling LLMs to reason over demographic information and prediction outcomes within a batch. To mitigate positional bias introduced by batch processing, the framework generates multiple shuffled versions of each batch and aggregates the resulting predictions through voting. We evaluate FABLE on three tabular classification datasets using three popular LLMs and four prompting configurations spanning zero-shot, few-shot, direct, and self-reflective prompting. Experimental results demonstrate that incorporating demographic information and explicit fairness constraints enable LLMs to achieve substantial fairness improvements across diverse datasets and fairness notions, highlighting their potential as fairness reasoners for tabular classification and promoting more equitable and accountable decision-making.
Recommender systems are known to exhibit fairness issues, particularly on the product side, where products and their associated suppliers receive unequal exposure in recommended results. While this problem has been widely studied in traditional recommendation settings, its implications for bundle recommendation (BR) remain largely unexplored. This emerging task introduces additional complexity: recommendations are generated at the bundle level, yet user satisfaction and product (or supplier) exposure depend on both the bundle and the individual items it contains. Existing fairness frameworks and metrics designed for traditional recommender systems may not directly translate to this multi-layered setting. In this paper, we conduct a comprehensive reproducibility study of product-side fairness in BR across three real-world datasets using four state-of-the-art BR methods. We analyze exposure disparities at both the bundle and item levels using multiple fairness metrics, uncovering important patterns. Our results show that exposure patterns differ notably between bundles and items, revealing the need for fairness interventions that go beyond bundle-level assumptions. We also find that fairness assessments vary considerably depending on the metric used, reinforcing the need for multi-faceted evaluation. Furthermore, user behavior plays a critical role: when users interact more frequently with bundles than with individual items, BR systems tend to yield fairer exposure distributions across both levels. Overall, our findings offer actionable insights for building fairer bundle recommender systems and establish a vital foundation for future research in this emerging domain.
Diffusion models have demonstrated remarkable image generation capabilities, but also pose risks in privacy and fairness by memorizing sensitive concepts or perpetuating biases. We propose a novel \textbf{concept erasure} method for text-to-image diffusion models, designed to remove specified concepts (e.g., a private individual or a harmful stereotype) from the model's generative repertoire. Our method, termed \textbf{FADE} (Fair Adversarial Diffusion Erasure), combines a trajectory-aware fine-tuning strategy with an adversarial objective to ensure the concept is reliably removed while preserving overall model fidelity. Theoretically, we prove a formal guarantee that our approach minimizes the mutual information between the erased concept and the model's outputs, ensuring privacy and fairness. Empirically, we evaluate FADE on Stable Diffusion and FLUX, using benchmarks from prior work (e.g., object, celebrity, explicit content, and style erasure tasks from MACE). FADE achieves state-of-the-art concept removal performance, surpassing recent baselines like ESD, UCE, MACE, and ANT in terms of removal efficacy and image quality. Notably, FADE improves the harmonic mean of concept removal and fidelity by 5--10\% over the best prior method. We also conduct an ablation study to validate each component of FADE, confirming that our adversarial and trajectory-preserving objectives each contribute to its superior performance. Our work sets a new standard for safe and fair generative modeling by unlearning specified concepts without retraining from scratch.
Fairness has emerged as one of the key challenges in federated learning. In horizontal federated settings, data heterogeneity often leads to substantial performance disparities across clients, raising concerns about equitable model behavior. To address this issue, we propose FedGA, a fairness-aware federated learning algorithm. We first employ the Gini coefficient to measure the performance disparity among clients. Based on this, we establish a relationship between the Gini coefficient $G$ and the update scale of the global model ${U_s}$, and use this relationship to adaptively determine the timing of fairness intervention. Subsequently, we dynamically adjust the aggregation weights according to the system's real-time fairness status, enabling the global model to better incorporate information from clients with relatively poor performance.We conduct extensive experiments on the Office-Caltech-10, CIFAR-10, and Synthetic datasets. The results show that FedGA effectively improves fairness metrics such as variance and the Gini coefficient, while maintaining strong overall performance, demonstrating the effectiveness of our approach.
Recommender systems can be found everywhere today, shaping our everyday experience whenever we're consuming content, ordering food, buying groceries online, or even just reading the news. Let's imagine we're in the process of building a recommender system to make content suggestions to users on social media. When thinking about fairness, it becomes clear there are several perspectives to consider: the users asking for tailored suggestions, the content creators hoping for some limelight, and society at large, navigating the repercussions of algorithmic recommendations. A shared fairness concern across all three is the emergence of filter bubbles, a side-effect that takes place when recommender systems are almost "too good", making recommendations so tailored that users become inadvertently confined to a narrow set of opinions/themes and isolated from alternative ideas. From the user's perspective, this is akin to manipulation. From the small content creator's perspective, this is an obstacle preventing them access to a whole range of potential fans. From society's perspective, the potential consequences are far-reaching, influencing collective opinions, social behavior and political decisions. How can our recommender system be fine-tuned to avoid the creation of filter bubbles, and ensure a more inclusive and diverse content landscape? Approaching this problem involves defining one (or more) performance metric to represent diversity, and tweaking our recommender system's performance through the lens of fairness. By incorporating this metric into our evaluation framework, we aim to strike a balance between personalized recommendations and the broader societal goal of fostering rich and varied cultures and points of view.
We propose a novel secure integrated sensing and communications (ISAC) system designed to serve multiple communication users (CUs) and targets. To that end, we formulate an optimization problem that maximizes the secrecy rate under constraints balancing both communication and sensing requirements. To enhance fairness among users, an entropy-regularized fairness metric is introduced within the problem framework. We then propose a solution employing an accelerated quadratic transform (QT) with a non-homogeneous bound to iteratively solve two subproblems, thereby effectively optimizing the overall objective. This approach ensures robust security and fairness in resource allocation for ISAC systems. Finally, simulation results verify the performance gains in terms of average secrecy rate, average data rate, and beam gain.
The dynamic allocation of spectrum in 5G / 6G networks is critical to efficient resource utilization. However, applying traditional deep reinforcement learning (DRL) is often infeasible due to its immense sample complexity and the safety risks associated with unguided exploration, which can cause severe network interference. To address these challenges, we propose a meta-learning framework that enables agents to learn a robust initial policy and rapidly adapt to new wireless scenarios with minimal data. We implement three meta-learning architectures, model-agnostic meta-learning (MAML), recurrent neural network (RNN), and an attention-enhanced RNN, and evaluate them against a non-meta-learning DRL algorithm, proximal policy optimization (PPO) baseline, in a simulated dynamic integrated access/backhaul (IAB) environment. Our results show a clear performance gap. The attention-based meta-learning agent reaches a peak mean network throughput of 48 Mbps, while the PPO baseline decreased drastically to 10 Mbps. Furthermore, our method reduces SINR and latency violations by more than 50% compared to PPO. It also shows quick adaptation, with a fairness index 0.7, showing better resource allocation. This work proves that meta-learning is a very effective and safer option for intelligent control in complex wireless systems.
Collaborative fairness is a crucial challenge in federated learning. However, existing approaches often overlook a practical yet complex form of heterogeneity: imbalanced covariate shift. We provide a theoretical analysis of this setting, which motivates the design of FedAKD (Federated Asynchronous Knowledge Distillation)- simple yet effective approach that balances accurate prediction with collaborative fairness. FedAKD consists of client and server updates. In the client update, we introduce a novel asynchronous knowledge distillation strategy based on our preliminary analysis, which reveals that while correctly predicted samples exhibit similar feature distributions across clients, incorrectly predicted samples show significant variability. This suggests that imbalanced covariate shift primarily arises from misclassified samples. Leveraging this insight, our approach first applies traditional knowledge distillation to update client models while keeping the global model fixed. Next, we select correctly predicted high-confidence samples and update the global model using these samples while keeping client models fixed. The server update simply aggregates all client models. We further provide a theoretical proof of FedAKD's convergence. Experimental results on public datasets (FashionMNIST and CIFAR10) and a real-world Electronic Health Records (EHR) dataset demonstrate that FedAKD significantly improves collaborative fairness, enhances predictive accuracy, and fosters client participation even under highly heterogeneous data distributions.
Large language models are increasingly used to support high-stakes decisions, potentially influencing who is granted bail or receives a loan. Naive chain-of-thought sampling can improve average decision accuracy, but has also been shown to amplify unfair bias. To address this challenge and enable the trustworthy use of reasoning models in high-stakes decision-making, we propose a framework for training a generalizable Fairness Reward Model (FRM). Our model assigns a fairness score to LLM reasoning, enabling the system to down-weight biased trajectories and favor equitable ones when aggregating decisions across reasoning chains. We show that a single Fairness Reward Model, trained on weakly supervised, LLM-annotated examples of biased versus unbiased reasoning, transfers across tasks, domains, and model families without additional fine-tuning. Applied to real-world decision-making tasks including recidivism prediction and social media moderation, we show that our approach consistently improves fairness while matching, or even surpassing, baseline accuracy.
Within a legal framework, fairness in datasets and models is typically assessed by dividing observations into predefined groups and then computing fairness measures (e.g., Disparate Impact or Equality of Odds with respect to gender). However, when sensitive attributes such as skin color are continuous, dividing into default groups may overlook or obscure the discrimination experienced by certain minority subpopulations. To address this limitation, we propose a fairness-based grouping approach for continuous (possibly multidimensional) sensitive attributes. By grouping data according to observed levels of discrimination, our method identifies the partition that maximizes a novel criterion based on inter-group variance in discrimination, thereby isolating the most critical subgroups. We validate the proposed approach using multiple synthetic datasets and demonstrate its robustness under changing population distributions - revealing how discrimination is manifested within the space of sensitive attributes. Furthermore, we examine a specialized setting of monotonic fairness for the case of skin color. Our empirical results on both CelebA and FFHQ, leveraging the skin tone as predicted by an industrial proprietary algorithm, show that the proposed segmentation uncovers more nuanced patterns of discrimination than previously reported, and that these findings remain stable across datasets for a given model. Finally, we leverage our grouping model for debiasing purpose, aiming at predicting fair scores with group-by-group post-processing. The results demonstrate that our approach improves fairness while having minimal impact on accuracy, thus confirming our partition method and opening the door for industrial deployment.
Conversational recommender systems (CRSs) often suffer from an extreme long-tail distribution of dialogue data, causing a strong bias toward head-frequency blockbusters that sacrifices diversity and exacerbates the cold-start problem. An empirical analysis of DCRS and statistics on the REDIAL corpus show that only 10% of head movies account for nearly half of all mentions, whereas about 70% of tail movies receive merely 26% of the attention. This imbalance gives rise to three critical challenges: head over-fitting, body representation drift, and tail sparsity. To address these issues, we propose LumiCRS, an end-to-end framework that mitigates long-tail imbalance through three mutually reinforcing layers: (i) an Adaptive Comprehensive Focal Loss (ACFL) that dynamically adjusts class weights and focusing factors to curb head over-fitting and reduce popularity bias; (ii) Prototype Learning for Long-Tail Recommendation, which selects semantic, affective, and contextual prototypes to guide clustering and stabilize body and tail representations; and (iii) a GPT-4o-driven prototype-guided dialogue augmentation module that automatically generates diverse long-tail conversational snippets to alleviate tail sparsity and distribution shift. Together, these strategies enable LumiCRS to markedly improve recommendation accuracy, diversity, and fairness: on the REDIAL and INSPIRED benchmarks, LumiCRS boosts Recall@10 and Tail-Recall@10 by 7-15% over fifteen strong baselines, while human evaluations confirm superior fluency, informativeness, and long-tail relevance. These results demonstrate the effectiveness of multi-layer collaboration in building an efficient and fair long-tail conversational recommender.
The increasing use of generative AI for resume screening is predicated on the assumption that it offers an unbiased alternative to biased human decision-making. However, this belief fails to address a critical question: are these AI systems fundamentally competent at the evaluative tasks they are meant to perform? This study investigates the question of competence through a two-part audit of eight major AI platforms. Experiment 1 confirmed complex, contextual racial and gender biases, with some models penalizing candidates merely for the presence of demographic signals. Experiment 2, which evaluated core competence, provided a critical insight: some models that appeared unbiased were, in fact, incapable of performing a substantive evaluation, relying instead on superficial keyword matching. This paper introduces the "Illusion of Neutrality" to describe this phenomenon, where an apparent lack of bias is merely a symptom of a model's inability to make meaningful judgments. This study recommends that organizations and regulators adopt a dual-validation framework, auditing AI hiring tools for both demographic bias and demonstrable competence to ensure they are both equitable and effective.
Multi-agent systems, which consist of multiple AI models interacting within a shared environment, are increasingly used for persona-based interactions. However, if not carefully designed, these systems can reinforce implicit biases in large language models (LLMs), raising concerns about fairness and equitable representation. We present MALIBU, a novel benchmark developed to assess the degree to which LLM-based multi-agent systems implicitly reinforce social biases and stereotypes. MALIBU evaluates bias in LLM-based multi-agent systems through scenario-based assessments. AI models complete tasks within predefined contexts, and their responses undergo evaluation by an LLM-based multi-agent judging system in two phases. In the first phase, judges score responses labeled with specific demographic personas (e.g., gender, race, religion) across four metrics. In the second phase, judges compare paired responses assigned to different personas, scoring them and selecting the superior response. Our study quantifies biases in LLM-generated outputs, revealing that bias mitigation may favor marginalized personas over true neutrality, emphasizing the need for nuanced detection, balanced fairness strategies, and transparent evaluation benchmarks in multi-agent systems.
The rapid advancement of Large Language Models (LLMs) has transformed various domains, particularly computer science (CS) education. These models exhibit remarkable capabilities in code-related tasks and problem-solving, raising questions about their potential and limitations in advanced CS contexts. This study presents a novel bilingual (English-Romanian) multimodal (text and image) dataset of multiple-choice questions derived from a high-level computer science competition. A particularity of our dataset is that the problems are conceived such that some of them are easier solved using reasoning on paper, while for others writing code is more efficient. We systematically evaluate State of The Art LLMs on this dataset, analyzing their performance on theoretical programming tasks. Our findings reveal the strengths and limitations of current LLMs, including the influence of language choice (English vs. Romanian), providing insights into their applicability in CS education and competition settings. We also address critical ethical considerations surrounding educational integrity and the fairness of assessments in the context of LLM usage. These discussions aim to inform future educational practices and policies. To support further research, our dataset will be made publicly available in both English and Romanian. Additionally, we release an educational application tailored for Romanian students, enabling them to self-assess using the dataset in an interactive and practice-oriented environment.
Graph learning has rapidly evolved into a critical subfield of machine learning and artificial intelligence (AI). Its development began with early graph-theoretic methods, gaining significant momentum with the advent of graph neural networks (GNNs). Over the past decade, progress in scalable architectures, dynamic graph modeling, multimodal learning, generative AI, explainable AI (XAI), and responsible AI has broadened the applicability of graph learning to various challenging environments. Graph learning is significant due to its ability to model complex, non-Euclidean relationships that traditional machine learning struggles to capture, thus better supporting real-world applications ranging from drug discovery and fraud detection to recommender systems and scientific reasoning. However, challenges like scalability, generalization, heterogeneity, interpretability, and trustworthiness must be addressed to unlock its full potential. This survey provides a comprehensive introduction to graph learning, focusing on key dimensions including scalable, temporal, multimodal, generative, explainable, and responsible graph learning. We review state-of-the-art techniques for efficiently handling large-scale graphs, capturing dynamic temporal dependencies, integrating heterogeneous data modalities, generating novel graph samples, and enhancing interpretability to foster trust and transparency. We also explore ethical considerations, such as privacy and fairness, to ensure responsible deployment of graph learning models. Additionally, we identify and discuss emerging topics, highlighting recent integration of graph learning and other AI paradigms and offering insights into future directions. This survey serves as a valuable resource for researchers and practitioners seeking to navigate the rapidly evolving landscape of graph learning.
The use of large language models (LLMs) in hiring promises to streamline candidate screening, but it also raises serious concerns regarding accuracy and algorithmic bias where sufficient safeguards are not in place. In this work, we benchmark several state-of-the-art foundational LLMs - including models from OpenAI, Anthropic, Google, Meta, and Deepseek, and compare them with our proprietary domain-specific hiring model (Match Score) for job candidate matching. We evaluate each model's predictive accuracy (ROC AUC, Precision-Recall AUC, F1-score) and fairness (impact ratio of cut-off analysis across declared gender, race, and intersectional subgroups). Our experiments on a dataset of roughly 10,000 real-world recent candidate-job pairs show that Match Score outperforms the general-purpose LLMs on accuracy (ROC AUC 0.85 vs 0.77) and achieves significantly more equitable outcomes across demographic groups. Notably, Match Score attains a minimum race-wise impact ratio of 0.957 (near-parity), versus 0.809 or lower for the best LLMs, (0.906 vs 0.773 for the intersectionals, respectively). We discuss why pretraining biases may cause LLMs with insufficient safeguards to propagate societal biases in hiring scenarios, whereas a bespoke supervised model can more effectively mitigate these biases. Our findings highlight the importance of domain-specific modeling and bias auditing when deploying AI in high-stakes domains such as hiring, and caution against relying on off-the-shelf LLMs for such tasks without extensive fairness safeguards. Furthermore, we show with empirical evidence that there shouldn't be a dichotomy between choosing accuracy and fairness in hiring: a well-designed algorithm can achieve both accuracy in hiring and fairness in outcomes.
Reasoning Language Models (RLMs) have gained traction for their ability to perform complex, multi-step reasoning tasks through mechanisms such as Chain-of-Thought (CoT) prompting or fine-tuned reasoning traces. While these capabilities promise improved reliability, their impact on robustness to social biases remains unclear. In this work, we leverage the CLEAR-Bias benchmark, originally designed for Large Language Models (LLMs), to investigate the adversarial robustness of RLMs to bias elicitation. We systematically evaluate state-of-the-art RLMs across diverse sociocultural dimensions, using an LLM-as-a-judge approach for automated safety scoring and leveraging jailbreak techniques to assess the strength of built-in safety mechanisms. Our evaluation addresses three key questions: (i) how the introduction of reasoning capabilities affects model fairness and robustness; (ii) whether models fine-tuned for reasoning exhibit greater safety than those relying on CoT prompting at inference time; and (iii) how the success rate of jailbreak attacks targeting bias elicitation varies with the reasoning mechanisms employed. Our findings reveal a nuanced relationship between reasoning capabilities and bias safety. Surprisingly, models with explicit reasoning, whether via CoT prompting or fine-tuned reasoning traces, are generally more vulnerable to bias elicitation than base models without such mechanisms, suggesting reasoning may unintentionally open new pathways for stereotype reinforcement. Reasoning-enabled models appear somewhat safer than those relying on CoT prompting, which are particularly prone to contextual reframing attacks through storytelling prompts, fictional personas, or reward-shaped instructions. These results challenge the assumption that reasoning inherently improves robustness and underscore the need for more bias-aware approaches to reasoning design.
Large Language Model-enhanced Recommender Systems (LLM-enhanced RSs) have emerged as a powerful approach to improving recommendation quality by leveraging LLMs to generate item representations. Despite these advancements, the integration of LLMs raises severe fairness concerns. Existing studies reveal that LLM-based RSs exhibit greater unfairness than traditional RSs, yet fairness issues in LLM-enhanced RSs remain largely unexplored. In this paper, our empirical study reveals that while LLM-enhanced RSs improve fairness across item groups, a significant fairness gap persists. Further enhancement remains challenging due to the architectural differences and varying sources of unfairness inherent in LLM-enhanced RSs. To bridge this gap, we first decompose unfairness into i) \textit{prior unfairness} in LLM-generated representations and ii) \textit{training unfairness} in recommendation models. Then, we propose BiFair, a bi-level optimization-based fairness-aware training framework designed to mitigate both prior and training unfairness simultaneously. BiFair optimizes two sets of learnable parameters: LLM-generated representations and a trainable projector in the recommendation model, using a two-level nested optimization process. Additionally, we introduce an adaptive inter-group balancing mechanism, leveraging multi-objective optimization principles to dynamically balance fairness across item groups. Extensive experiments on three real-world datasets demonstrate that BiFair significantly mitigates unfairness and outperforms previous state-of-the-art methods.