Algorithmic Fairness

Ask about this topic

Overview

The field asks whether automated systems treat people and groups fairly, using criteria such as demographic parity, equalized odds, individual similarity, and causal or counterfactual fairness. Researchers audit disparities in credit, hiring, healthcare, recommendation, and language or vision models, using benchmarks such as COMPAS, Adult, and MIMIC alongside subgroup and intersectional tests. Mitigation ranges from data reweighting and representation learning to constrained or robust optimization, causal interventions, and post-hoc thresholding; work also studies fairness in rankings, sequential allocation, federated learning, and LLM agents. A central challenge is that fairness criteria can conflict with one another and with utility, while estimates and interventions may be unstable under small samples, distribution shift, strategic behavior, or uncertain causal assumptions.

Latest papers

CardsList

424 papers28 papers in the last four weeks, down 20% on the four weeks before. 0.2% of all new papers.

Mar 4, 2026

Fairness Begins with State: Purifying Latent Preferences for Hierarchical Reinforcement Learning in Interactive Recommendation

Interactive recommender systems (IRS) are increasingly optimized with Reinforcement Learning (RL) to capture the sequential nature of user-system dynamics. However, existing fairness-aware methods often suffer from a fundamental oversight: they assume the observed user state is a faithful representation of true preferences. In reality, implicit feedback is contaminated by popularity-driven noise and exposure bias, creating a distorted state that misleads the RL agent. We argue that the persistent conflict between accuracy and fairness is not merely a reward-shaping issue, but a state estimation failure. In this work, we propose DSRM-HRL, a framework that reformulates fairness-aware recommendation as a latent state purification problem followed by decoupled hierarchical decision-making. We introduce a Denoising State Representation Module (DSRM) based on diffusion models to recover the low-entropy latent preference manifold from high-entropy, noisy interaction histories. Built upon this purified state, a Hierarchical Reinforcement Learning (HRL) agent is employed to decouple conflicting objectives: a high-level policy regulates long-term fairness trajectories, while a low-level policy optimizes short-term engagement under these dynamic constraints. Extensive experiments on high-fidelity simulators (KuaiRec, KuaiRand) demonstrate that DSRM-HRL effectively breaks the "rich-get-richer" feedback loop, achieving a superior Pareto frontier between recommendation utility and exposure equity.

Yun Lu, Xiaoyu Shi, Hong Xie +2

Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences Chongqing School, University of Chinese Academy of Sciences Chongqing, China · The First Affiliated Hospital, University of Science and Technology of China Hefei, China · City University of Hong Kong Hong Kong, Hong Kong

Fairness in Recommender SystemsRecommender SystemsAlgorithmic FairnessUser Preference Modeling
AskPDF
Mar 3, 2026

[Re] FairDICE: A Fair Tradeoff in Multi-objective Offline RL

Offline Reinforcement Learning (RL) is an emerging field of RL in which policies are learned solely from demonstrations. Within offline RL, some environments involve balancing multiple objectives, but existing multi-objective offline RL algorithms do not provide an efficient way to find a fair compromise. FairDICE (see arXiv:2506.08062v2) seeks to fill this gap by adapting OptiDICE (an offline RL algorithm) to automatically learn weights for multiple objectives to e.g. incentivise fairness among objectives. As this would be a valuable contribution, this replication study examines the replicability of claims made regarding FairDICE. We find that many theoretical claims hold, but an error in the code reduces FairDICE to standard behaviour cloning in continuous environments, and many important hyperparameters were originally underspecified. After rectifying this, we show in experiments extending the original paper that FairDICE can scale to complex environments and high-dimensional rewards, though it can be reliant on (online) hyperparameter tuning. We conclude that FairDICE is a theoretically interesting method, but the experimental justification requires significant revision.

Peter Adema, Karim Galliamov, Aleksey Evstratovskiy +1

Informatics Institute, University of Amsterdam

Offline RLMulti-Objective Reinforcement LearningAlgorithmic Fairness
AskPDF
Mar 3, 2026

Proactive Guiding Strategy for Item-side Fairness in Interactive Recommendation

Item-side fairness is crucial for ensuring the fair exposure of long-tail items in interactive recommender systems. Existing approaches promote the exposure of long-tail items by directly incorporating them into recommended results. This causes misalignment between user preferences and the recommended long-tail items, which hinders long-term user engagement and reduces the effectiveness of recommendations. We aim for a proactive fairness-guiding strategy, which actively guides user preferences toward long-tail items while preserving user satisfaction during the interactive recommendation process. To this end, we propose HRL4PFG, an interactive recommendation framework that leverages hierarchical reinforcement learning to guide user preferences toward long-tail items progressively. HRL4PFG operates through a macro-level process that generates fairness-guided targets based on multi-step feedback, and a micro-level process that fine-tunes recommendations in real time according to both these targets and evolving user preferences. Extensive experiments show that HRL4PFG improves cumulative interaction rewards and maximum user interaction length by a larger margin when compared with state-of-the-art methods in interactive recommendation environments.

Chongjun Xia, Xiaoyu Shi, Hong Xie +3

Chinese Academy of Sciences · University of Technology Sydney · University of Science and Technology of China

Long-Tail RecommendationFairness in Recommender SystemsRecommender SystemsAlgorithmic Fairness
AskPDF
Mar 2, 2026

Skin Tone in the Wild: A Dataset and Benchmark for 10-tone MST Classification

Skin tone classification is a fundamental task in computer vision, with applications in quantifying medical features, assessing demographic representativeness, and mitigating algorithmic bias. However, existing datasets either rely on a restrictive 6-tone Fitzpatrick scale, prohibit training through restrictive licenses, or lack representation of extreme skin tones, while current methods often fail to disentangle true skin tone from in-the-wild imaging conditions, degrading to random-classifier performance. We introduce skin tone in the wild (STW), the first open-access dataset annotated with the 10-tone Monk Skin Tone (MST) scale, containing over 42K images and specifically curated to include underrepresented tones. Alongside a rigorous evaluation protocol, we propose SkinToneNet, a ViT-based model that leverages global image context for robust in-the-wild generalization. Experiments show that SkinToneNet achieves 90% weighted off-by-one accuracy, substantially outperforming prior baselines. We further use SkinToneNet to audit widely used face datasets, including CelebA and VGGFace2, revealing substantial representation imbalances across MST tones.

Vitor Matias, Márcus Vinícius Lobo Costa, Tiago Novello +1

Instituto de Ciências Matemáticas e de Computação (ICMC), Universidade de São Paulo (USP), São Carlos, São Paulo, Brazil · Instituto de Matemática Pura e Aplica, Rio de Janeiro, Brazil

ClassificationAlgorithmic FairnessImage ClassificationFine-Grained Image Classification
AskPDF
Mar 1, 2026

The MAMA-MIA Challenge: Advancing Generalizability and Fairness in Breast MRI Tumor Segmentation and Treatment Response Prediction

Breast cancer is the most frequently diagnosed malignancy among women worldwide and a leading cause of cancer-related mortality. Dynamic contrast-enhanced magnetic resonance imaging plays a central role in tumor characterization and treatment monitoring, particularly in patients receiving neoadjuvant chemotherapy. However, existing artificial intelligence models for breast magnetic resonance imaging are typically developed and evaluated using heterogeneous datasets, study populations, and assessment protocols, making direct comparison difficult and limiting understanding of model robustness across institutions and clinically relevant patient subgroups. The MAMA-MIA Challenge was designed to address these challenges by providing a standardized benchmark for the joint evaluation of primary tumor segmentation and prediction of pathologic complete response using pre-treatment magnetic resonance imaging only. The training cohort comprised 1,506 patients from multiple institutions in the United States, while evaluation was conducted on an external test set of 574 patients from three independent European centers to assess cross-continental and cross-institutional generalization. A unified scoring framework combined predictive performance with subgroup consistency across age, menopausal status, and breast density. Twenty-six international teams participated in the final evaluation phase. Results demonstrate substantial performance variability under a common external evaluation framework and reveal trade-offs between overall accuracy and subgroup fairness. The challenge provides standardized datasets, evaluation protocols, and public resources to promote the development of robust and equitable artificial intelligence systems for breast cancer imaging.

Lidia Garrucho, Smriti Joshi, Kaisar Kushibar +43

Medical Image SegmentationMedical Image BenchmarksClinical Outcome PredictionAlgorithmic Fairness
AskPDF
Feb 28, 2026

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

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.

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 FairnessAlgorithmic BiasAI Agent AuditingTool-Using AgentsMedical VQA
AskPDF
Feb 28, 2026

Fair in Mind, Fair in Action? A Synchronous Benchmark for Understanding and Generation in UMLLMs

As artificial intelligence (AI) is increasingly deployed across domains, ensuring fairness has become a core challenge. However, the field faces a "Tower of Babel'' dilemma: fairness metrics abound, yet their underlying philosophical assumptions often conflict, hindering unified paradigms-particularly in unified Multimodal Large Language Models (UMLLMs), where biases propagate systemically across tasks. To address this, we introduce the IRIS Benchmark, to our knowledge the first benchmark designed to synchronously evaluate the fairness of both understanding and generation tasks in UMLLMs. Enabled by our demographic classifier, ARES, and four supporting large-scale datasets, the benchmark is designed to normalize and aggregate arbitrary metrics into a high-dimensional "fairness space'', integrating 60 granular metrics across three dimensions-Ideal Fairness, Real-world Fidelity, and Bias Inertia & Steerability (IRIS). Through this benchmark, our evaluation of leading UMLLMs uncovers systemic phenomena such as the "generation gap'', individual inconsistencies like "personality splits'', and the "counter-stereotype reward'', while offering diagnostics to guide the optimization of their fairness capabilities. With its novel and extensible framework, the IRIS benchmark is capable of integrating evolving fairness metrics, ultimately helping to resolve the "Tower of Babel'' impasse. Project Page: https://iris-benchmark-web.vercel.app/

Yiran Zhao, Lu Zhou, Xiaogang Xu +3

Nanjing University of Aeronautics and Astronautics · Collaborative Innovation Center of Novel Software Technology and Industrialization · The Chinese University of Hong Kong +2

Algorithmic FairnessDemographic Bias in Language ModelsMultimodal Model Evaluation
AskPDF
Feb 27, 2026

When Does Multimodal Learning Help in Healthcare? A Benchmark on EHR and Chest X-Ray Fusion

Machine learning holds promise for advancing clinical decision support, yet it remains unclear when multimodal learning truly helps in practice, particularly under modality missingness and fairness constraints. In this work, we conduct a systematic benchmark of multimodal fusion between Electronic Health Records (EHR) and chest X-rays (CXR) on standardized cohorts from MIMIC-IV and MIMIC-CXR, aiming to answer four fundamental questions: when multimodal fusion improves clinical prediction, how different fusion strategies compare, how robust existing methods are to missing modalities, and whether multimodal models achieve algorithmic fairness. Our study reveals several key insights. Multimodal fusion improves performance when modalities are complete, with gains concentrating in diseases that require complementary information from both EHR and CXR. While cross-modal learning mechanisms capture clinically meaningful dependencies beyond simple concatenation, the rich temporal structure of EHR introduces strong modality imbalance that architectural complexity alone cannot overcome. Under realistic missingness, multimodal benefits rapidly degrade unless models are explicitly designed to handle incomplete inputs. Moreover, multimodal fusion does not inherently improve fairness, with subgroup disparities mainly arising from unequal sensitivity across demographic groups. To support reproducible and extensible evaluation, we further release a flexible benchmarking toolkit that enables plug-and-play integration of new models and datasets. Together, this work provides actionable guidance on when multimodal learning helps, when it fails, and why, laying the foundation for developing clinically deployable multimodal systems that are both effective and reliable. The open-source toolkit can be found at https://github.com/jakeykj/CareBench.

Kejing Yin, Haizhou Xu, Wenfang Yao +5

Department of Computer Science, Hong Kong Baptist University · Division of Artificial Intelligence, Lingnan University · School of Nursing, The Hong Kong Polytechnic University

Multimodal FusionMultimodal Model EvaluationMissing-Modality LearningElectronic Health RecordsAlgorithmic Fairness
AskPDF
Feb 27, 2026

Fairness under Graph Uncertainty: Achieving Interventional Fairness with Partially Known Causal Graphs over Clusters of Variables

Algorithmic decisions about individuals require predictions that are not only accurate but also fair with respect to sensitive attributes such as gender and race. Causal notions of fairness align with legal requirements, yet many methods assume access to detailed knowledge of the underlying causal graph, which is a demanding assumption in practice. We propose a learning framework that achieves interventional fairness by leveraging a causal graph over clusters of variables, which is substantially easier to estimate than a variable-level graph. With possible adjustment cluster sets identified from such a cluster causal graph, our framework trains a prediction model by reducing the worst-case discrepancy between interventional distributions across these sets. To this end, we develop a computationally efficient barycenter kernel maximum mean discrepancy (MMD) that scales favorably with the number of sensitive attribute values. Extensive experiments show that our framework strikes a better balance between fairness and accuracy than existing approaches, highlighting its effectiveness under limited causal graph knowledge.

Yoichi Chikahara

NTT Communication Science Laboratories, Kyoto, Japan

Algorithmic FairnessCausal Inference
AskPDF
Feb 26, 2026

FairQuant: Fairness-Aware Mixed-Precision Quantization for Medical Image Classification

Compressing neural networks by quantizing model parameters offers useful trade-off between performance and efficiency. Methods like quantization-aware training and post-training quantization strive to maintain the downstream performance of compressed models compared to the full precision models. However, these techniques do not explicitly consider the impact on algorithmic fairness. In this work, we study fairness-aware mixed-precision quantization schemes for medical image classification under explicit bit budgets. We introduce FairQuant, a framework that combines group-aware importance analysis, budgeted mixed-precision allocation, and a learnable Bit-Aware Quantization (BAQ) mode that jointly optimizes weights and per-unit bit allocations under bitrate and fairness regularization. We evaluate the method on Fitzpatrick17k and ISIC2019 across ResNet18/50, DeiT-Tiny, and TinyViT. Results show that FairQuant configurations with average precision near 4-6 bits recover much of the Uniform 8-bit accuracy while improving worst-group performance relative to Uniform 4- and 8-bit baselines, with comparable fairness metrics under shared budgets.

Thomas Woergaard, Raghavendra Selvan

Department of Computer Science, University of Copenhagen, Denmark

Mixed-Precision QuantizationAlgorithmic FairnessMedical Image ClassificationQuantization-Aware Training
AskPDF
Feb 26, 2026

Operationalizing Fairness: Post-Hoc Threshold Optimization Under Hard Resource Limits

The deployment of machine learning in high-stakes domains requires a balance between predictive safety and algorithmic fairness. However, existing fairness interventions often as- sume unconstrained resources and employ group-specific decision thresholds that violate anti- discrimination regulations. We introduce a post-hoc, model-agnostic threshold optimization framework that jointly balances safety, efficiency, and equity under strict and hard capacity constraints. To ensure legal compliance, the framework enforces a single, global decision thresh- old. We formulated a parameterized ethical loss function coupled with a bounded decision rule that mathematically prevents intervention volumes from exceeding the available resources. An- alytically, we prove the key properties of the deployed threshold, including local monotonicity with respect to ethical weighting and the formal identification of critical capacity regimes. We conducted extensive experimental evaluations on diverse high-stakes datasets. The principal re- sults demonstrate that capacity constraints dominate ethical priorities; the strict resource limit determines the final deployed threshold in over 80% of the tested configurations. Furthermore, under a restrictive 25% capacity limit, the proposed framework successfully maintains high risk identification (recall ranging from 0.409 to 0.702), whereas standard unconstrained fairness heuristics collapse to a near-zero utility. We conclude that theoretical fairness objectives must be explicitly subordinated to operational capacity limits to remain in deployment. By decou- pling predictive scoring from policy evaluation and strictly bounding intervention rates, this framework provides a practical and legally compliant mechanism for stakeholders to navigate unavoidable ethical trade-offs in resource-constrained environments.

Moirangthem Tiken Singh, Amit Kalita, Sapam Jitu Singh

Department of Computer Science and Engineering, DUIET, Dibrugarh University, Assam, India · Department of Computer Science and Engineering, MIT, Manipur University, 795003, India

Algorithmic FairnessFair Resource AllocationConstrained OptimizationPost-Hoc Calibration
AskPDF
Feb 25, 2026

From Bias to Balance: Fairness-Aware Paper Recommendation for Equitable Peer Review

Despite frequent double-blind review, systemic biases related to author demographics still disadvantage underrepresented groups. We start from a simple hypothesis: if a post-review recommender is trained with an explicit fairness regularizer, it should increase inclusion without degrading quality. To test this, we introduce Fair-PaperRec, a Multi-Layer Perceptron (MLP) with a differentiable fairness loss over intersectional attributes (e.g., race, country) that re-ranks papers after double-blind review. We first probe the hypothesis on synthetic datasets spanning high, moderate, and near-fair biases. Across multiple randomized runs, these controlled studies map where increasing the fairness weight strengthens macro/micro diversity while keeping utility approximately stable, demonstrating robustness and adaptability under varying disparity levels. We then carry the hypothesis into the original setting, conference data from ACM Special Interest Group on Computer-Human Interaction (SIGCHI), Designing Interactive Systems (DIS), and Intelligent User Interfaces (IUI). In this real-world scenario, an appropriately tuned configuration of Fair-PaperRec achieves up to a 42.03% increase in underrepresented-group participation with at most a 3.16% change in overall utility relative to the historical selection. Taken together, the synthetic-to-original progression shows that fairness regularization can act as both an equity mechanism and a mild quality regularizer, especially in highly biased regimes. By first analyzing the behavior of the fairness parameters under controlled conditions and then validating them on real submissions, Fair-PaperRec offers a practical, equity-focused framework for post-review paper selection that preserves, and in some settings can even enhance, measured scholarly quality.

Uttamasha Anjally Oyshi, Susan Gauch

Department of Electrical Engineering & Computer Science University of Arkansas Fayetteville, USA

Fairness in Recommender SystemsRecommender SystemsAlgorithmic FairnessIntersectional FairnessLearning to RankAutomated Peer Review
AskPDF
Feb 25, 2026

Private and Robust Contribution Evaluation in Federated Learning

Cross-silo federated learning allows multiple organizations to collaboratively train machine learning models without sharing raw data, but client updates can still leak sensitive information through inference attacks. Secure aggregation protects privacy by hiding individual updates, yet it complicates contribution evaluation, which is critical for fair rewards and detecting low-quality or malicious participants. Existing marginal-contribution methods, such as the Shapley value, are incompatible with secure aggregation, and practical alternatives, such as Leave-One-Out, are crude and rely on self-evaluation. We introduce two marginal-difference contribution scores compatible with secure aggregation. Fair-Private satisfies standard fairness axioms, while Everybody-Else eliminates self-evaluation and provides resistance to manipulation, addressing a largely overlooked vulnerability. We provide theoretical guarantees for fairness, privacy, robustness, and computational efficiency, and evaluate our methods on multiple medical image datasets and CIFAR10 in cross-silo settings. Our scores consistently outperform existing baselines, better approximate Shapley-induced client rankings, and improve downstream model performance as well as misbehavior detection. These results demonstrate that fairness, privacy, robustness, and practical utility can be achieved jointly in federated contribution evaluation, offering a principled solution for real-world cross-silo deployments.

Delio Jaramillo Velez, Gergely Biczok, Alexandre Graell i Amat +2

University of La Laguna Tenerife, Spain · HUN-REN Hungarian Research Network Budapest, Hungary · Chalmers University Gotheburg, Sweden +2

Federated LearningPrivacy-Preserving MLPrivacy-Preserving Federated LearningAlgorithmic Fairness
AskPDF
Feb 24, 2026

Equitable Evaluation via Elicitation

Individuals with similar qualifications and skills may vary in their demeanor, or outward manner: some tend toward self-promotion while others are modest to the point of omitting crucial information. Comparing the self-descriptions of equally qualified job-seekers with different self-presentation styles is therefore problematic. We build an interactive AI for skill elicitation that provides accurate determination of skills while simultaneously allowing individuals to speak in their own voice. Such a system can be deployed, for example, when a new user joins a professional networking platform, or when matching employees to needs during a company reorganization. To obtain sufficient training data, we train an LLM to act as synthetic humans. Elicitation mitigates endogenous bias arising from individuals' own self-reports. To address systematic model bias we enforce a mathematically rigorous notion of equitability ensuring that the covariance between self-presentation manner and skill evaluation error is small.

Elbert Du, Cynthia Dwork, Lunjia Hu +3

Harvard University · Northeastern University · University of Maryland +1

Algorithmic FairnessHuman-in-the-Loop AI
AskPDF
Feb 24, 2026

A Counterfactual Approach for Addressing Individual User Unfairness in Collaborative Recommender System

Recommender Systems (RSs) are exploited by various business enterprises to suggest their products (items) to consumers (users). Collaborative filtering (CF) is a widely used variant of RSs which learns hidden patterns from user-item interactions for recommending items to users. Recommendations provided by the traditional CF models are often biased. Generally, such models learn and update embeddings for all the users, thereby overlooking the biases toward each under-served users individually. This leads to certain users receiving poorer recommendations than the rest. Such unfair treatment toward users incur loss to the business houses. There is limited research which addressed individual user unfairness problem (IUUP). Existing literature employed explicit exploration-based multi-armed bandits, individual user unfairness metric, and explanation score to address this issue. Although, these works elucidate and identify the underlying individual user unfairness, however, they do not provide solutions for it. In this paper, we propose a dual-step approach which identifies and mitigates IUUP in recommendations. In the proposed work, we counterfactually introduce new interactions to the candidate users (one at a time) and subsequently analyze the benefit from this perturbation. This improves the user engagement with other users and items. Thus, the model can learn effective embeddings across the users. To showcase the effectiveness of the proposed counterfactual methodology, we conducted experiments on MovieLens-100K, Amazon Beauty and MovieLens-1M datasets. The experimental results validate the superiority of the proposed approach over the existing techniques.

Nikita Baidya, Bidyut Kr. Patra, Ratnakar Dash

Pattern Recognition Laboratory, Department of Computer Science and Engineering, National Institute of Technology Rourkela, Odisha, India. · Department of Computer Science and Engineering, Indian Institute of Technology (BHU) Varanasi, Uttar Pradesh, India.

Fairness in Recommender SystemsRecommender SystemsAlgorithmic FairnessCollaborative Filtering
AskPDF
Feb 24, 2026

Physics-based phenomenological characterization of cross-modal bias in multimodal models

The term 'algorithmic fairness' is used to evaluate whether AI models operate fairly in both comparative (where fairness is understood as formal equality, such as "treat like cases as like") and non-comparative (where unfairness arises from the model's inaccuracy, arbitrariness, or inscrutability) contexts. Recent advances in multimodal large language models (MLLMs) are breaking new ground in multimodal understanding, reasoning, and generation; however, we argue that inconspicuous distortions arising from complex multimodal interaction dynamics can lead to systematic bias. The purpose of this position paper is twofold: first, it is intended to acquaint AI researchers with phenomenological explainable approaches that rely on the physical entities that the machine experiences during training/inference, as opposed to the traditional cognitivist symbolic account or metaphysical approaches; second, it is to state that this phenomenological doctrine will be practically useful for tackling algorithmic fairness issues in MLLMs. We develop a surrogate physics-based model that describes transformer dynamics (i.e., semantic network structure and self-/cross-attention) to analyze the dynamics of cross-modal bias in MLLM, which are not fully captured by conventional embedding- or representation-level analyses. We support this position through multi-input diagnostic experiments: 1) perturbation-based analyses of emotion classification using Qwen2.5-Omni and Gemma 3n, and 2) dynamical analysis of Lorenz chaotic time-series prediction through the physical surrogate. Across two architecturally distinct MLLMs, we show that multimodal inputs can reinforce modality dominance rather than mitigate it, as revealed by structured error-attractor patterns under systematic label perturbation, complemented by dynamical analysis.

Hyeongmo Kim, Sohyun Kang, Yerin Choi +5

Brain Science Institute, Korea Institute of Science and Technology, Seoul, Republic of Korea · Department of Physics and Astronomy, Seoul National University, Seoul, Republic of Korea · Department of Computer Science and Engineering, Korea University, Seoul, Republic of Korea +2

Multimodal Large Language ModelsAlgorithmic FairnessMultimodal Model Interpretability
AskPDF
Feb 20, 2026

SOMtime the World Ain′'t Fair: Violating Fairness Using Self-Organizing Maps

Unsupervised representations are widely assumed to be neutral with respect to sensitive attributes when those attributes are withheld from training. We show that this assumption is false. Using SOMtime, a topology-preserving representation method based on high-capacity Self-Organizing Maps, we demonstrate that sensitive attributes such as age and income emerge as dominant latent axes in purely unsupervised embeddings, even when explicitly excluded from the input. On two large-scale real-world datasets (the World Values Survey across five countries and the Census-Income dataset), SOMtime recovers monotonic orderings aligned with withheld sensitive attributes, achieving Spearman correlations of up to 0.85, whereas PCA and UMAP typically remain below 0.23 (with a single exception reaching 0.31), and against t-SNE and autoencoders which achieve at most 0.34. Furthermore, unsupervised segmentation of SOMtime embeddings produces demographically skewed clusters, demonstrating downstream fairness risks without any supervised task. These findings establish that fairness through unawareness fails at the representation level for ordinal sensitive attributes and that fairness auditing must extend to unsupervised components of machine learning pipelines. We have made the code available at~ https://github.com/JosephBingham/SOMtime

Joseph Bingham, Netanel Arussy, Dvir Aran

Faculty of Biology, Technion University · Taub Faculty of Computer Science, Technion University

Unsupervised LearningAlgorithmic FairnessUnsupervised ClusteringUnsupervised Representation LearningSelf-Organizing Maps
AskPDF
Feb 20, 2026

Fairness-Aware Partial-label Domain Adaptation for Voice Classification of Parkinson's and ALS

Voice-based digital biomarkers can enable scalable, non-invasive screening and monitoring of Parkinson's disease (PD) and Amyotrophic Lateral Sclerosis (ALS). However, models trained on one cohort or device often fail on new acquisition settings due to cross-device and cross-cohort domain shift. This challenge is amplified in real-world scenarios with partial-label mismatch, where datasets may contain different disease labels and only partially overlap in class space. In addition, voice-based models may exploit demographic cues, raising concerns about gender-related unfairness, particularly when deployed across heterogeneous cohorts. To tackle these challenges, we propose a hybrid framework for unified three-class (healthy/PD/ALS) cross-domain voice classification from partially overlapping cohorts. The method combines style-based domain generalization with conditional adversarial alignment tailored to partial-label settings, reducing negative transfer. An additional adversarial gender branch promotes gender-invariant representations. We conduct a comprehensive evaluation across four heterogeneous sustained-vowel datasets, spanning distinct acquisition settings and devices, under both domain generalization and unsupervised domain adaptation protocols. The proposed approach is compared against twelve state-of-the-art machine learning and deep learning methods, and further evaluated through three targeted ablations, providing the first cross-cohort benchmark and end-to-end domain-adaptive framework for unified healthy/PD/ALS voice classification under partial-label mismatch and fairness constraints. Across all experimental settings, our method consistently achieves the best external generalization over the considered evaluation metrics, while maintaining reduced gender disparities. Notably, no competing method shows statistically significant gains in external performance.

Arianna Francesconi, Zhixiang Dai, Arthur Stefano Moscheni +7

School of Computer and Communication Sciences, EPFL (École polytechnique fédérale de Lausanne), Lausanne, Switzerland · Unit of Artificial Intelligence and Computer Systems, Università Campus Bio-Medico di Roma, Rome, Italy · Eustema S.p.A., Research and Development Centre, Naples, Italy +2

Parkinson's Disease Detection from SpeechDomain AdaptationAudio ClassificationClinical Speech ProcessingDomain GeneralizationAlgorithmic Fairness
AskPDF
Feb 18, 2026

Beyond Procedure: Substantive Fairness in Conformal Prediction

Conformal prediction (CP) offers distribution-free uncertainty quantification for machine learning models, yet its interplay with fairness in downstream decision-making remains underexplored. Moving beyond CP as a standalone operation (procedural fairness), we analyze the holistic decision-making pipeline to evaluate substantive fairness-the equity of downstream outcomes. Theoretically, we derive an upper bound that decomposes prediction-set size disparity into interpretable components, clarifying how label-clustered CP helps control method-driven contributions to unfairness. To facilitate scalable empirical analysis, we introduce an LLM-in-the-loop evaluator that approximates human assessment of substantive fairness across diverse modalities. Our experiments show that label-clustered CP often provides a favorable balance between utility and substantive fairness, while reducing set-size disparities in line with our theory. Finally, we empirically show that equalized set sizes, rather than coverage, strongly correlate with improved substantive fairness, enabling practitioners to design more fair CP systems. Our code is available at https://github.com/layer6ai-labs/llm-in-the-loop-conformal-fairness.

Pengqi Liu, Zijun Yu, Mouloud Belbahri +3

McGill University, Montreal, Canada · TD Insurance, Montreal, Canada · UQAM, Montreal, Canada +1

Algorithmic FairnessConformal PredictionGroup-Conditional Conformal Prediction
AskPDF
Feb 18, 2026

Fairness Dynamics in Digital Economy Platforms with Biased Ratings

The digital services economy consists of online platforms that facilitate interactions between service providers and consumers. This ecosystem is characterized by short-term, often one-off, transactions between parties that have no prior familiarity. To establish trust among users, platforms employ rating systems which allow users to report on the quality of their previous interactions. However, while arguably crucial for these platforms to function, rating systems can perpetuate negative biases against marginalised groups. This paper investigates how to design platforms around biased reputation systems, reducing discrimination while maintaining incentives for all service providers to offer high quality service for users. We introduce an evolutionary game theoretical model to study how digital platforms can perpetuate or counteract rating-based discrimination. We focus on the platforms' decisions to promote service providers who have high reputations or who belong to a specific protected group. Our results demonstrate a fundamental trade-off between user experience and fairness: promoting highly-rated providers benefits users, but lowers the demand for marginalised providers against which the ratings are biased. Our results also provide evidence that intervening by tuning the demographics of the search results is a highly effective way of reducing unfairness while minimally impacting users. Furthermore, we show that even when precise measurements on the level of rating bias affecting marginalised service providers is unavailable, there is still potential to improve upon a recommender system which ignores protected characteristics. Altogether, our model highlights the benefits of proactive anti-discrimination design in systems where ratings are used to promote cooperative behaviour.

J. Martin Smit, Fernando P. Santos

University of Amsterdam, Amsterdam, Netherlands

Fairness in Recommender SystemsAlgorithmic FairnessGroup FairnessRecommender Systems
AskPDF
Feb 18, 2026

Temporal Panel Selection in Ongoing Citizens' Assemblies

Permanent citizens' assemblies are ongoing deliberative bodies composed of randomly selected citizens, organized into panels that rotate over time. Unlike one-off panels, which represent the population in a single snapshot, permanent assemblies enable shifting participation across multiple rounds. This structure offers a powerful framework for ensuring that different groups of individuals are represented over time across successive panels. In particular, it allows smaller groups of individuals that may not warrant representation in every individual panel to be represented across a sequence of them. We formalize this temporal sortition framework by requiring proportional representation both within each individual panel and across the sequence of panels. Building on the work of Ebadian and Micha (2025), we consider a setting in which the population lies in a metric space, and the goal is to achieve both proportional representation, ensuring that every group of citizens receives adequate representation, and individual fairness, ensuring that each individual has an equal probability of being selected. We extend the notion of representation to a temporal setting by requiring that every initial segment of the panel sequence, viewed as a cumulative whole, proportionally reflects the structure of the population. We present algorithms that provide varying guarantees of proportional representation, both within individual panels and across any sequence of panels, while also maintaining individual fairness over time.

Yusuf Hakan Kalayci, Evi Micha

University of Southern California

Social Choice TheoryAlgorithmic FairnessDeliberative Democracy
AskPDF
Feb 17, 2026

Fairness over Equality: Correcting Social Incentives in Asymmetric Sequential Social Dilemmas

Sequential Social Dilemmas (SSDs) provide a key framework for studying how cooperation emerges when individual incentives conflict with collective welfare. In Multi-Agent Reinforcement Learning, these problems are often addressed by incorporating intrinsic drives that encourage prosocial or fair behavior. However, most existing methods assume that agents face identical incentives in the dilemma and require continuous access to global information about other agents to assess fairness. In this work, we introduce asymmetric variants of well-known SSD environments and examine how natural differences between agents influence cooperation dynamics. Our findings reveal that existing fairness-based methods struggle to adapt under asymmetric conditions by enforcing raw equality that wrongfully incentivize defection. To address this, we propose three modifications: (i) redefining fairness by accounting for agents' reward ranges, (ii) introducing an agent-based weighting mechanism to better handle inherent asymmetries, and (iii) localizing social feedback to make the methods effective under partial observability without requiring global information sharing. Experimental results show that in asymmetric scenarios, our method fosters faster emergence of cooperative policies compared to existing approaches, without sacrificing scalability or practicality.

Alper Demir, Hüseyin Aydın, Kale-ab Abebe Tessera +2

Izmir University of Economics & University of Edinburgh, Izmir, Turkey · Middle East Technical University & Utrecht University, Ankara, Turkey · University of Edinburgh, Edinburgh, United Kingdom +1

Cooperative MARLMulti-Agent Reinforcement LearningReward Design for RLAlgorithmic Fairness
AskPDF
Feb 9, 2026

FairRARI: A Plug and Play Framework for Fairness-Aware PageRank

PageRank (PR) is a fundamental algorithm in graph machine learning tasks. Owing to the increasing importance of algorithmic fairness, we consider the problem of computing PR vectors subject to various group-fairness criteria based on sensitive attributes of the vertices. At present, principled algorithms for this problem are lacking - some cannot guarantee that a target fairness level is achieved, while others do not feature optimality guarantees. In order to overcome these shortcomings, we put forth a unified in-processing convex optimization framework, termed FairRARI, for tackling different group-fairness criteria in a ``plug and play'' fashion. Leveraging a variational formulation of PR, the framework computes fair PR vectors by solving a strongly convex optimization problem with fairness constraints, thereby ensuring that a target fairness level is achieved. We further introduce three different fairness criteria which can be efficiently tackled using FairRARI to compute fair PR vectors with the same asymptotic time-complexity as the original PR algorithm. Extensive experiments on real-world datasets showcase that FairRARI outperforms existing methods in terms of utility, while achieving the desired fairness levels across multiple vertex groups; thereby highlighting its effectiveness.

Emmanouil Kariotakis, Aritra Konar

Department of Electrical Engineering (ESAT-STADIUS), KU Leuven, Kasteelpark Arenberg 10, 3001 Leuven, Belgium.

Algorithmic FairnessGroup Fairness
AskPDF
Feb 4, 2026

Separation-Utility Pareto Frontier: An Information-Theoretic Characterization

We study the Pareto frontier (optimal trade-off) between utility and separation, a fairness criterion requiring predictive independence from sensitive attributes conditional on the true outcome. Through an information-theoretic lens, we prove a characterization of the utility-separation Pareto frontier, establish its concavity, and thereby prove the increasing marginal cost of separation in terms of utility. In addition, we characterize the conditions under which this trade-off becomes strict, providing a guide for trade-off selection in practice. Based on the theoretical characterization, we develop an empirical regularizer based on conditional mutual information (CMI) between predictions and sensitive attributes given the true outcome. The CMI regularizer is compatible with any deep model trained via gradient-based optimization and serves as a scalar monitor of residual separation violations, offering tractable guarantees during training. Finally, numerical experiments support our theoretical findings: across COMPAS, UCI Adult, UCI Bank, and CelebA, the proposed method substantially reduces separation violations while matching or exceeding the utility of established baseline methods. This study thus offers a provable, stable, and flexible approach to enforcing separation in deep learning.

Shizhou Xu

Department of Mathematics University of California Davis Davis, CA 95616, USA

Algorithmic Fairness
AskPDF
Feb 3, 2026

Fair and Efficient Investment in Public Transportation

We study a stylized model of infrastructure investment in public transportation. In our model, each agent travels between a pair of terminals in a network captured by a weighted graph, where edge weights represent distances. The central planner can reduce the travel time along a fixed number of edges, with the goal of maximizing the utilitarian or egalitarian welfare. When there is only one agent, we provide a polynomial-time algorithm that combines Dijkstra's algorithm with a dynamic program. We then demonstrate how to use this algorithm as a subroutine to solve the problem for two agents. Generalizing this idea, we present an XP algorithm parameterized by the number of agents nn; however, our problem turns out to be W[1]-hard with respect to nn. Nevertheless, we establish a fixed-parameter tractability result for the special case where all agents travel to a common hub. If the number of agents is variable, we obtain NP-completeness and inapproximability results. We discuss implications of our results for a related model of railway network design.

Martin Bullinger, Edith Elkind, Kassian Köck

School of Engineering Mathematics and Technology, University of Bristol, Bristol, UK · School of Engineering, Northwestern University, Evanston, USA · School of Computation, Information and Technology, Technical University of Munich, Munich, Germany

Algorithmic FairnessCombinatorial OptimizationParameterized Complexity
AskPDF
Jan 30, 2026

Improved Algorithms for Nash Welfare in Linear Bandits

Nash regret has recently emerged as a principled fairness-aware performance metric for stochastic multi-armed bandits, motivated by the Nash Social Welfare objective. Although this notion has been extended to linear bandits, existing results suffer from suboptimality in ambient dimension dd, stemming from proof techniques that rely on restrictive concentration inequalities. In this work, we resolve this open problem by introducing new analytical tools that yield an order-optimal Nash regret bound in linear bandits. Beyond Nash regret, we initiate the study of pp-means regret in linear bandits, a unifying framework that interpolates between fairness and utility objectives and strictly generalizes Nash regret. We propose a generic algorithmic framework, FairLinBandit, that works as a meta-algorithm on top of any linear bandit strategy. We instantiate this framework using two bandit algorithms: Phased Elimination and Upper Confidence Bound, and prove that both achieve sublinear pp-means regret for the entire range of pp. Extensive experiments on linear bandit instances generated from real-world datasets demonstrate that our methods consistently outperform the existing state-of-the-art baseline.

Dhruv Sarkar, Nishant Pandey, Sayak Ray Chowdhury

Indian Institute of Technology Kharagpur · Indian Institute of Technology Kanpur

Multi-Armed BanditsAlgorithmic Fairness
AskPDF
Jan 30, 2026

Fairness-Aware Performance Evaluation for Multi-Party Multi-Objective Optimization

In multiparty multiobjective optimization problems, solution sets are usually evaluated using classical performance metrics, aggregated across DMs. However, such mean-based evaluations may be unfair by favoring certain parties, as they assume identical geometric approximation quality to each party's PF carries comparable evaluative significance. Moreover, prevailing notions of MPMOP optimal solutions are restricted to strictly common Pareto optimal solutions, representing a narrow form of cooperation in multiparty decision making scenarios. These limitations obscure whether a solution set reflects balanced relative gains or meaningful consensus among heterogeneous DMs. To address these issues, this paper develops a fairness-aware performance evaluation framework grounded in a generalized notion of consensus solutions. From a cooperative game-theoretic perspective, we formalize four axioms that a fairness-aware evaluation function for MPMOPs should satisfy. By introducing a concession rate vector to quantify acceptable compromises by individual DMs, we generalize the classical definition of MPMOP optimal solutions and embed classical performance metrics into a Nash-product-based evaluation framework, which is theoretically shown to satisfy all axioms. To support empirical validation, we further construct benchmark problems that extend existing MPMOP suites by incorporating consensus-deficient negotiation structures. Experimental results demonstrate that the proposed evaluation framework is able to distinguish algorithmic performance in a manner consistent with consensus-aware fairness considerations. Specifically, algorithms converging toward strictly common solutions are assigned higher evaluation scores when such solutions exist, whereas in the absence of strictly common solutions, algorithms that effectively cover the commonly acceptable region are more favorably evaluated.

Zifan Zhao, Peilan Xu, Wenjian Luo

School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing 210044, China · Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies, Institute of Cyberspace Security, School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen 518055, China

Multi-Party Multi-Objective OptimizationCooperative Game TheoryAlgorithmic FairnessMulti-Objective Optimization
AskPDF
Jan 27, 2026

Intersectional Fairness via Mixed-Integer Optimization

The deployment of Artificial Intelligence in high-risk domains, such as finance and healthcare, necessitates models that are both fair and transparent. While regulatory frameworks, including the EU's AI Act, mandate bias mitigation, they are deliberately vague about the definition of bias. In line with existing research, we argue that true fairness requires addressing bias at the intersections of protected groups. We propose a unified framework that leverages Mixed-Integer Optimization (MIO) to train intersectionally fair and intrinsically interpretable classifiers. We prove the equivalence of two measures of intersectional fairness (MSD and SPSF) in detecting the most unfair subgroup and empirically demonstrate that our MIO-based algorithm improves performance in finding bias. We train high-performing, interpretable classifiers that bound intersectional bias below an acceptable threshold, offering a robust solution for regulated industries and beyond.

Jiří Němeček, Mark Kozdoba, Illia Kryvoviaz +2

Czech Technical University in Prague · Technion

Algorithmic FairnessIntersectional Fairness
AskPDF
Jan 6, 2026

Audit Me If You Can: Query-Efficient Active Fairness Auditing of Black-Box LLMs

Large Language Models (LLMs) exhibit systematic biases across demographic groups. Auditing is proposed as an accountability tool for black-box LLM applications, but suffers from resource-intensive query access. We conceptualise auditing as uncertainty estimation over a target fairness metric and introduce BAFA, the Bounded Active Fairness Auditor for query-efficient auditing of black-box LLMs. BAFA maintains a version space of surrogate models consistent with queried scores and computes uncertainty intervals for fairness metrics (e.g., ΔΔ AUC) via constrained empirical risk minimisation. Active query selection narrows these intervals to reduce estimation error. We evaluate BAFA on two standard fairness dataset case studies: CivilComments and Bias-in-Bios, comparing against stratified sampling, power sampling, and ablations. BAFA achieves target error thresholds with up to 40×\times fewer queries than stratified sampling (e.g., 144 vs 5,956 queries at ε=0.02\varepsilon=0.02 for CivilComments) for tight thresholds, demonstrates substantially better performance over time, and shows lower variance across runs. These results suggest that active sampling can reduce resources needed for independent fairness auditing with LLMs, supporting continuous model evaluations.

David Hartmann, Lena Pohlmann, Lelia Hanslik +3

Weizenbaum Institut Berlin · Technische Universität Berlin · FIZ Karlsruhe +2

LLM AuditingAlgorithmic FairnessAdaptive SamplingDemographic Bias in Language ModelsBlack-Box Model Auditing
AskPDF
Dec 19, 2025

Penalized Fair Regression for Multiple Groups in Chronic Kidney Disease

Fair regression methods have the potential to mitigate societal bias concerns in health care, but there has been little work on penalized fair regression when multiple groups experience such bias. We propose a general regression framework that addresses this gap with unfairness penalties for multiple groups. Our approach is demonstrated for binary outcomes with true positive rate disparity penalties. It can be efficiently implemented through reduction to a cost-sensitive classification problem. We additionally introduce novel score functions for automatically selecting penalty weights. Our penalized fair regression methods are empirically studied in simulations, where they achieve a fairness-accuracy frontier beyond that of existing comparison methods. Finally, we apply these methods to a national multi-site primary care study of chronic kidney disease to develop a fair classifier for end-stage renal disease. There we find substantial improvements in fairness for multiple race and ethnicity groups who experience societal bias in the health care system without any appreciable loss in overall fit.

Carter H. Nakamoto, Lucia Lushi Chen, Agata Foryciarz +1

Department of Health Policy, Stanford University, 615 Crothers Way Encina Commons MC6019 Stanford, CA 94305, USA · Psyfy Inc. · Department of Epidemiology and Population Health, Stanford University +1

Group FairnessAlgorithmic Fairness
AskPDF