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

358 papers, page 4 of 8

151. ICML 2025Learning to Route LLMs with Confidence Tokens
152. ICML 2025Leveraging Predictive Equivalence in Decision Trees
153. ICML 2025LIMEFLDL: A Local Interpretable Model-Agnostic Explanations Approach for Label Distribution Learning
154. ICML 2025Mind the Gap: A Practical Attack on GGUF Quantization
155. ICML 2025Multiaccuracy and Multicalibration via Proxy Groups
156. ICML 2025On the Alignment between Fairness and Accuracy: from the Perspective of Adversarial Robustness
157. ICML 2025On the Impact of Performative Risk Minimization for Binary Random Variables
158. ICML 2025Optimal Fair Learning Robust to Adversarial Distribution Shift
159. ICML 2025Policy Design for Two-sided Platforms with Participation Dynamics
160. ICML 2025Position: LLM Social Simulations Are a Promising Research Method
161. ICML 2025Position: The Categorization of Race in ML is a Flawed Premise
162. ICML 2025Prediction via Shapley Value Regression
163. ICML 2025Preserving AUC Fairness in Learning with Noisy Protected Groups
164. ICML 2025Relative Error Fair Clustering in the Weak-Strong Oracle Model
165. ICML 2025Representative Ranking for Deliberation in the Public Sphere
166. ICML 2025Selective Preference Aggregation
167. ICML 2025Settling the Maximin Share Fairness for Scheduling among Groups of Machines
168. ICML 2025Statistical Collusion by Collectives on Learning Platforms
169. ICML 2025Subgroups Matter for Robust Bias Mitigation
170. ICML 2025Tensor Product Neural Networks for Functional ANOVA Model
171. ICML 2025The Disparate Benefits of Deep Ensembles
172. ICML 2025The Elicitation Game: Evaluating Capability Elicitation Techniques
173. ICML 2025The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them)
174. ICML 2025The Value of Prediction in Identifying the Worst-Off
175. ICML 2025TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference
176. ICML 2025Towards Attributions of Input Variables in a Coalition
177. ICML 2025Two Tickets are Better than One: Fair and Accurate Hiring Under Strategic LLM Manipulations
178. ICML 2025Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data Silos
179. ICML 2025What makes an Ensemble (Un) Interpretable?
180. ICML 2025X-Hacking: The Threat of Misguided AutoML
181. ICML 2025You Get What You Give: Reciprocally Fair Federated Learning
182. NeurIPS 2025A Unified Framework for Fair Graph Generation: Theoretical Guarantees and Empirical Advances
183. NeurIPS 2025Additive Models Explained: A Computational Complexity Approach
184. NeurIPS 2025Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency
185. NeurIPS 2025Boosting the Uniqueness of Neural Networks Fingerprints with Informative Triggers
186. NeurIPS 2025Causally Reliable Concept Bottleneck Models
187. NeurIPS 2025Correcting misinterpretations of additive models
188. NeurIPS 2025Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing
189. NeurIPS 2025Discovering Opinion Intervals from Conflicts in Signed Graphs
190. NeurIPS 2025Discretization-free Multicalibration through Loss Minimization over Tree Ensembles
191. NeurIPS 2025Distributive Fairness in Large Language Models: Evaluating Alignment with Human Values
192. NeurIPS 2025Does Representation Guarantee Welfare?
193. NeurIPS 2025DPA: A one-stop metric to measure bias amplification in classification datasets
194. NeurIPS 2025Efficient Fairness-Performance Pareto Front Computation
195. NeurIPS 2025Fair Continuous Resource Allocation with Equality of Impact
196. NeurIPS 2025Fair Deepfake Detectors Can Generalize
197. NeurIPS 2025Fair Matroid Selection
198. NeurIPS 2025Fair Representation Learning with Controllable High Confidence Guarantees via Adversarial Inference
199. NeurIPS 2025FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning
200. NeurIPS 2025Fairness under Competition

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.