Social aspects · fairness papers, 2023–2026

Key findings

• Social aspects · fairness went from 36 papers in 2023 to 111 in 2026, roughly 3.1x in three years.
• NeurIPS publishes the most Social aspects · fairness work: 180 papers from 2023 to 2026, 50% of the four-venue total.
• The fastest-growing overlap is with Social aspects · safety: papers tagged with both rose from 1 in 2023 to 56 in 2026.
• Among the 5 topics under Alignment and Responsible AI, it ranks #5 by 2026 paper count; the fastest grower in the group, Social aspects · safety, is up 93x versus 3.1x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026Beyond Feature Disruption: Boundary-Diverting Unlearnable Examples against Linear Probing
• ICML 2026A Game-Theoretic Framework for Measuring and Explaining Metric Compatibility in Fair Machine Learning
• ICLR 2026Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying Prompts
• CVPR 2026Omni-MMSI Toward Identity-attributed Social Interaction Understanding
• NeurIPS 2025Discretization-free Multicalibration through Loss Minimization over Tree Ensembles
• ICML 2025Dissecting Submission Limit in Desk-Rejections: A Mathematical Analysis of Fairness in AI Conference Policies
• ICLR 2025Prompting Fairness: Integrating Causality to Debias Large Language Models
• CVPR 2025Revisiting Fairness in Multitask Learning: A Performance-Driven Approach for Variance Reduction
• NeurIPS 2024A Closer Look at AUROC and AUPRC under Class Imbalance
• ICML 2024Position: Scarce Resource Allocations That Rely On Machine Learning Should Be Randomized
• ICLR 2024Procedural Fairness Through Decoupling Objectionable Data Generating Components
• CVPR 2024Preserving Fairness Generalization in Deepfake Detection
• NeurIPS 2023[Re] Fairness Guarantees under Demographic Shift
• ICML 2023Fairness in Streaming Submodular Maximization over a Matroid Constraint
• ICLR 2023Fairness-aware Contrastive Learning with Partially Annotated Sensitive Attributes
• CVPR 2023Improving Fairness in Facial Albedo Estimation via Visual-Textual Cues
• NeurIPS 2026Chatter Attack: Resource Consumption Attack for Large Language Models
• ICML 2026Adaptive Generation of Bias-Eliciting Questions for LLMs
• ICLR 2026Bi-Criteria Metric Distortion
• CVPR 2026Decoupling Bias Aligning Distributions Synergistic Fairness Optimization for Deepfake Detection

All Social aspects · fairness papers

139 papers, page 3 of 3

101. ICML 2025Position: The Categorization of Race in ML is a Flawed Premise
102. ICML 2025Prediction via Shapley Value Regression
103. ICML 2025Preserving AUC Fairness in Learning with Noisy Protected Groups
104. ICML 2025Relative Error Fair Clustering in the Weak-Strong Oracle Model
105. ICML 2025Representative Ranking for Deliberation in the Public Sphere
106. ICML 2025Selective Preference Aggregation
107. ICML 2025Settling the Maximin Share Fairness for Scheduling among Groups of Machines
108. ICML 2025Statistical Collusion by Collectives on Learning Platforms
109. ICML 2025Subgroups Matter for Robust Bias Mitigation
110. ICML 2025Tensor Product Neural Networks for Functional ANOVA Model
111. ICML 2025The Disparate Benefits of Deep Ensembles
112. ICML 2025The Elicitation Game: Evaluating Capability Elicitation Techniques
113. ICML 2025The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them)
114. ICML 2025The Value of Prediction in Identifying the Worst-Off
115. ICML 2025TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference
116. ICML 2025Towards Attributions of Input Variables in a Coalition
117. ICML 2025Two Tickets are Better than One: Fair and Accurate Hiring Under Strategic LLM Manipulations
118. ICML 2025Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data Silos
119. ICML 2025What makes an Ensemble (Un) Interpretable?
120. ICML 2025X-Hacking: The Threat of Misguided AutoML
121. ICML 2025You Get What You Give: Reciprocally Fair Federated Learning
122. ICML 2024FRAPPÉ: A Group Fairness Framework for Post-Processing Everything
123. ICML 2024How Far Can Fairness Constraints Help Recover From Biased Data?
124. ICML 2024Individual Fairness in Graph Decomposition
125. ICML 2024Monotone Individual Fairness
126. ICML 2024On The Fairness Impacts of Hardware Selection in Machine Learning
127. ICML 2024On the Maximal Local Disparity of Fairness-Aware Classifiers
128. ICML 2024Optimally Improving Cooperative Learning in a Social Setting
129. ICML 2024Position: Scarce Resource Allocations That Rely On Machine Learning Should Be Randomized
130. ICML 2024Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision Making
131. ICML 2024Stability and Multigroup Fairness in Ranking with Uncertain Predictions
132. ICML 2024Standardized Interpretable Fairness Measures for Continuous Risk Scores
133. ICML 2023A Closer Look at the Intervention Procedure of Concept Bottleneck Models
134. ICML 2023FAIRER: Fairness as Decision Rationale Alignment
135. ICML 2023Fairness in Matching under Uncertainty
136. ICML 2023Fairness in Streaming Submodular Maximization over a Matroid Constraint
137. ICML 2023Matrix Estimation for Individual Fairness
138. ICML 2023On the Within-Group Fairness of Screening Classifiers
139. ICML 2023Superhuman Fairness

FAQ

How many Social aspects · fairness papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

358 in total: 36 in 2023, 79 in 2024, 132 in 2025, 111 in 2026.

How many Social aspects · fairness papers are at NeurIPS 2026?

NeurIPS 2026 has 43 Social aspects · fairness papers, versus 62 the year before.

How many Social aspects · fairness papers are at ICLR 2026?

ICLR 2026 has 4 Social aspects · fairness papers, versus 8 the year before.

How many Social aspects · fairness papers are at ICML 2026?

ICML 2026 has 60 Social aspects · fairness papers, versus 61 the year before.

How many Social aspects · fairness papers are at CVPR 2026?

CVPR 2026 has 4 Social aspects · fairness papers, versus 1 the year before.

Which conference publishes the most Social aspects · fairness papers?

NeurIPS, with 180 papers from 2023 to 2026.