公平指标论文趋势 2023–2026

主要结论

• 公平指标论文从 2023 年的 78 篇增长到 2026 年的 78 篇，三年间扩大到约 1.0 倍。
• NeurIPS 是发公平指标论文最多的会议，2023–2026 年共 137 篇，占四个会议总量的 37%。
• 交叉方向里涨得最快的是对齐与安全：同时属于两个主题的论文从 2023 年的 3 篇增至 2026 年的 18 篇。
• 在「因果与公平」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的因果发现是 2.4 倍，公平指标是 1.0 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• 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

全部公平指标论文

共 368 篇，第 2 / 8 页

51. ICML 2026Sequential Group Composition: A Window into the Mechanics of Deep Learning
52. ICML 2026The Fairness Hierarchy: A viewpoint from causal inference
53. NeurIPS 2026A Comprehensive View of Fairness through Distributional Stability
54. NeurIPS 2026Adversarial Group Fairness in Contextual Bandits: When Robust is Not Fair
55. NeurIPS 2026Auditing Cross-Lingual Fairness in Language Model Watermarking
56. NeurIPS 2026Beyond Proxy Metrics: MLLM-Based Human Surrogate Evaluation for Explainable AI
57. NeurIPS 2026Cost Efficient Fairness Audit Under Partial Feedback
58. NeurIPS 2026Data-Free Metrics Are Not Invariant Under Functionality-Preserving Reparametrisations
59. NeurIPS 2026Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth
60. NeurIPS 2026Forecasting Downstream Performance of LLMs With Proxy Metrics
61. NeurIPS 2026FRInGe: Distribution-Space Integrated Gradients with Fisher–Rao Geometry
62. NeurIPS 2026Geometry-Aware Similarity Metrics for Neural Representations on Riemannian and Statistical Manifolds
63. NeurIPS 2026How Does Pruning Change Decisions in Large Language Models?
64. NeurIPS 2026Inferring learning rules in deep neural network architectures from animal learning data
65. NeurIPS 2026Malicious Node Injection: A Transferable Adversarial Attack on GNN Fairness
66. NeurIPS 2026Matrix-Free Natural Gradient via Stochastic Truncated Metrics
67. NeurIPS 2026Overcoming the Resolution Limit: Significance-Aware Regularization for Intersectional Fairness
68. NeurIPS 2026Post-Processing Guarantees for Classification under Linear-Fractional Performance Metrics
69. NeurIPS 2026Practical Estimation of the Bayes Optimal Fairness-Accuracy Tradeoff with Soft Labels
70. NeurIPS 2026Recovering Clean Evaluation Metrics from Contaminated Benchmarks
71. NeurIPS 2026Reviewer Scores Are Not Comparable Across Research Areas in ML Peer Review
72. NeurIPS 2026Scalable Fair Learning via Cramér-von Mises Regularization
73. NeurIPS 2026Simultaneous Individual, Group and Multigroup Fairness in Set Covering Problems
74. NeurIPS 2026Space Group Conditional Flow Matching
75. NeurIPS 2026Spectral-Spatial Interpretation
76. NeurIPS 2026Stay Fair! Ensuring Group Fairness in Diffusion Models Across Guidance Scales
77. NeurIPS 2026Strategic Causal Policy Learning: Welfare, Safety, and Fairness Thresholds
78. NeurIPS 2026The Pok\'emon Theorem and other Fairness Impossibility Results
79. CVPR 2025AI-Face: A Million-Scale Demographically Annotated AI-Generated Face Dataset and Fairness Benchmark
80. CVPR 2025AIM-Fair: Advancing Algorithmic Fairness via Selectively Fine-Tuning Biased Models with Contextual Synthetic Data
81. CVPR 2025Data-Free Group-Wise Fully Quantized Winograd Convolution via Learnable Scales
82. CVPR 2025FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding
83. CVPR 2025Flexible Group Count Enables Hassle-Free Structured Pruning
84. CVPR 2025ID-Patch: Robust ID Association for Group Photo Personalization
85. CVPR 2025Revisiting Fairness in Multitask Learning: A Performance-Driven Approach for Variance Reduction
86. ICLR 2025A Generic Framework for Conformal Fairness
87. ICLR 2025A Probabilistic Perspective on Unlearning and Alignment for Large Language Models
88. ICLR 2025An Effective Theory of Bias Amplification
89. ICLR 2025Balancing Bias in Two-sided Markets for Fair Stable Matchings
90. ICLR 2025Bridging Jensen Gap for Max-Min Group Fairness Optimization in Recommendation
91. ICLR 2025CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models
92. ICLR 2025Collapsed Language Models Promote Fairness
93. ICLR 2025Comparing noisy neural population dynamics using optimal transport distances
94. ICLR 2025Competitive Fair Scheduling with Predictions
95. ICLR 2025DarkBench: Benchmarking Dark Patterns in Large Language Models
96. ICLR 2025Do as We Do, Not as You Think: the Conformity of Large Language Models
97. ICLR 2025Enhancing Robust Fairness via Confusional Spectral Regularization
98. ICLR 2025Expected Sliced Transport Plans
99. ICLR 2025Exploring Local Memorization in Diffusion Models via Bright Ending Attention
100. ICLR 2025Fair Submodular Cover

常见问题

2023–2026 年四大会议一共有多少篇公平指标论文？

共 368 篇，按年份分别是 2023 年 78 篇、2024 年 118 篇、2025 年 94 篇、2026 年 78 篇。

NeurIPS 2026 有多少篇公平指标论文？

NeurIPS 2026 有 26 篇公平指标论文，上一届是 33 篇。

ICLR 2026 有多少篇公平指标论文？

ICLR 2026 有 27 篇公平指标论文，上一届是 30 篇。

ICML 2026 有多少篇公平指标论文？

ICML 2026 有 17 篇公平指标论文，上一届是 24 篇。

CVPR 2026 有多少篇公平指标论文？

CVPR 2026 有 8 篇公平指标论文，上一届是 7 篇。

哪个会议的公平指标论文最多？

NeurIPS，2023–2026 年共 137 篇。