Fairness Metrics papers, 2023–2026

Key findings

• Fairness Metrics went from 78 papers in 2023 to 78 in 2026, roughly 1.0x in three years.
• NeurIPS publishes the most Fairness Metrics work: 137 papers from 2023 to 2026, 37% of the four-venue total.
• The fastest-growing overlap is with Alignment and Safety: papers tagged with both rose from 3 in 2023 to 18 in 2026.
• Among the 5 topics under Causal and Fairness, it ranks #3 by 2026 paper count; the fastest grower in the group, Causal Discovery, is up 2.4x versus 1.0x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026Adversarial Group Fairness in Contextual Bandits: When Robust is Not Fair
• ICML 2026Capacitated Fair-Range Clustering: Hardness and Approximation Algorithms
• ICLR 2026Fairness-Aware Multi-view Evidential Learning with Adaptive Prior
• CVPR 2026EMMA Concept Erasure Benchmark with Comprehensive Semantic Metrics and Diverse
• NeurIPS 2025Analyzing Similarity Metrics for Data Selection for Language Model Pretraining
• ICML 2025Kernel Quantile Embeddings and Associated Probability Metrics
• ICLR 2025Expected Sliced Transport Plans
• CVPR 2025Flexible Group Count Enables Hassle-Free Structured Pruning
• NeurIPS 2024ABCFair: an Adaptable Benchmark approach for Comparing Fairness Methods
• ICML 2024Centralized Selection with Preferences in the Presence of Biases
• ICLR 2024Causal Fairness under Unobserved Confounding: A Neural Sensitivity Framework
• CVPR 2024GARField: Group Anything with Radiance Fields
• NeurIPS 2023[Re] Fairness Guarantees under Demographic Shift
• ICML 2023A Toy Model of Universality: Reverse Engineering how Networks Learn Group Operations
• ICLR 2023Confidential-PROFITT: Confidential PROof of FaIr Training of Trees
• CVPR 2023Improving Fairness in Facial Albedo Estimation via Visual-Textual Cues
• NeurIPS 2026Auditing Cross-Lingual Fairness in Language Model Watermarking
• ICML 2026Fine-to-Coarse Fairness-Informed Multi-View Clustering
• ICLR 2026Fast and Stable Riemannian Metrics on SPD Manifolds via Cholesky Product Geometry
• CVPR 2026Decoupling Bias Aligning Distributions Synergistic Fairness Optimization for Deepfake Detection

All Fairness Metrics papers

109 papers, page 2 of 3

51. ICLR 2025Regretful Decisions under Label Noise
52. ICLR 2025Relax and Merge: A Simple Yet Effective Framework for Solving Fair $k$-Means and $k$-sparse Wasserstein Barycenter Problems
53. ICLR 2025SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP
54. ICLR 2025Severing Spurious Correlations with Data Pruning
55. ICLR 2025Towards counterfactual fairness through auxiliary variables
56. ICLR 2025Towards Marginal Fairness Sliced Wasserstein Barycenter
57. ICLR 2025UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation
58. ICLR 2024Adversarial Attacks on Fairness of Graph Neural Networks
59. ICLR 2024Aligning Relational Learning with Lipschitz Fairness
60. ICLR 2024Assessing Uncertainty in Similarity Scoring: Performance & Fairness in Face Recognition
61. ICLR 2024Balancing Act: Constraining Disparate Impact in Sparse Models
62. ICLR 2024Causal Fairness under Unobserved Confounding: A Neural Sensitivity Framework
63. ICLR 2024Consistent algorithms for multi-label classification with macro-at-$k$ metrics
64. ICLR 2024Debiasing Attention Mechanism in Transformer without Demographics
65. ICLR 2024Deceptive Fairness Attacks on Graphs via Meta Learning
66. ICLR 2024Demystifying Local & Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition
67. ICLR 2024Enhancing Group Fairness in Online Settings Using Oblique Decision Forests
68. ICLR 2024Estimating Shape Distances on Neural Representations with Limited Samples
69. ICLR 2024Fair and Efficient Contribution Valuation for Vertical Federated Learning
70. ICLR 2024Fair Classifiers that Abstain without Harm
71. ICLR 2024fairret: a Framework for Differentiable Fairness Regularization Terms
72. ICLR 2024FairSeg: A Large-Scale Medical Image Segmentation Dataset for Fairness Learning Using Segment Anything Model with Fair Error-Bound Scaling
73. ICLR 2024FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis
74. ICLR 2024FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods
75. ICLR 2024Language Model Detectors Are Easily Optimized Against
76. ICLR 2024LCOT: Linear Circular Optimal Transport
77. ICLR 2024Learning to Reject Meets Long-tail Learning
78. ICLR 2024Like Oil and Water: Group Robustness Methods and Poisoning Defenses May Be at Odds
79. ICLR 2024Near-Optimal Solutions of Constrained Learning Problems
80. ICLR 2024On the Fairness ROAD: Robust Optimization for Adversarial Debiasing
81. ICLR 2024Perceptual Scales Predicted by Fisher Information Metrics
82. ICLR 2024Post-hoc bias scoring is optimal for fair classification
83. ICLR 2024Procedural Fairness Through Decoupling Objectionable Data Generating Components
84. ICLR 2024Structural Fairness-aware Active Learning for Graph Neural Networks
85. ICLR 2024Time Fairness in Online Knapsack Problems
86. ICLR 2024Towards Best Practices of Activation Patching in Language Models: Metrics and Methods
87. ICLR 2024Towards Poisoning Fair Representations
88. ICLR 2023Bias Propagation in Federated Learning
89. ICLR 2023Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts
90. ICLR 2023Confidential-PROFITT: Confidential PROof of FaIr Training of Trees
91. ICLR 2023Equal Improvability: A New Fairness Notion Considering the Long-term Impact
92. ICLR 2023FaiREE: fair classification with finite-sample and distribution-free guarantee
93. ICLR 2023FairGBM: Gradient Boosting with Fairness Constraints
94. ICLR 2023Fairness and Accuracy under Domain Generalization
95. ICLR 2023Fairness-aware Contrastive Learning with Partially Annotated Sensitive Attributes
96. ICLR 2023FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Data
97. ICLR 2023Function-space regularized Rényi divergences
98. ICLR 2023Interpretable Debiasing of Vectorized Language Representations with Iterative Orthogonalization
99. ICLR 2023Learning Sparse Group Models Through Boolean Relaxation
100. ICLR 2023Malign Overfitting: Interpolation and Invariance are Fundamentally at Odds

FAQ

How many Fairness Metrics papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

368 in total: 78 in 2023, 118 in 2024, 94 in 2025, 78 in 2026.

How many Fairness Metrics papers are at NeurIPS 2026?

NeurIPS 2026 has 26 Fairness Metrics papers, versus 33 the year before.

How many Fairness Metrics papers are at ICLR 2026?

ICLR 2026 has 27 Fairness Metrics papers, versus 30 the year before.

How many Fairness Metrics papers are at ICML 2026?

ICML 2026 has 17 Fairness Metrics papers, versus 24 the year before.

How many Fairness Metrics papers are at CVPR 2026?

CVPR 2026 has 8 Fairness Metrics papers, versus 7 the year before.

Which conference publishes the most Fairness Metrics papers?

NeurIPS, with 137 papers from 2023 to 2026.