反事实公平论文趋势 2023–2026

主要结论

• 反事实公平论文从 2023 年的 31 篇降到 2026 年的 21 篇，热度在回落。
• NeurIPS 是发反事实公平论文最多的会议，2023–2026 年共 39 篇，占四个会议总量的 38%。
• 交叉方向里涨得最快的是反事实解释：同时属于两个主题的论文从 2023 年的 8 篇增至 2026 年的 10 篇。
• 在「因果与公平」的 5 个主题里，它的 2026 年论文数排第 5；同组增长最快的因果发现是 2.4 倍，反事实公平是 0.7 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 2026CounterFlowNet: From Minimal Changes to Meaningful Counterfactual Explanations
• ICML 2026Density-Guided Robust Counterfactual Explanations on Tabular Data under Model Multiplicity
• ICLR 2026Counterfactual Explanations on Robust Perceptual Geodesics
• NeurIPS 2025Statistical Parity with Exponential Weights
• ICML 2025Causal Logistic Bandits with Counterfactual Fairness Constraints
• ICLR 2025Certifying Counterfactual Bias in LLMs
• NeurIPS 2024Reproducibility Study: Equal Improvability: A New Fairness Notion Considering the Long-Term Impact
• ICML 2024CF-OPT: Counterfactual Explanations for Structured Prediction
• ICLR 2024Counterfactual Density Estimation using Kernel Stein Discrepancies
• CVPR 2024FADES: Fair Disentanglement with Sensitive Relevance
• NeurIPS 2023[Re] Fairness Guarantees under Demographic Shift
• ICML 2023Counterfactual Analysis in Dynamic Latent State Models
• ICLR 2023FairGBM: Gradient Boosting with Fairness Constraints
• CVPR 2023Improving Fairness in Facial Albedo Estimation via Visual-Textual Cues
• NeurIPS 2026Offloading Score: Measuring AI Reliance through Counterfactual Workflows
• ICML 2026The Fairness Hierarchy: A viewpoint from causal inference
• ICLR 2026Counterfactual LLM-based Framework for Measuring Rhetorical Style
• NeurIPS 2025On Hierarchies of Fairness Notions in Cake Cutting: From Proportionality to Super Envy-Freeness
• ICML 2025Counterfactual Graphical Models: Constraints and Inference
• ICLR 2025Towards counterfactual fairness through auxiliary variables

全部反事实公平论文

共 39 篇，第 1 / 1 页

1. NeurIPS 2026Batched Stochastic Linear Bandits with 1-Bit Communication Constraints
2. NeurIPS 2026Can the Parts Fool the Test? Counterfactual Pairing Cycles for Relational OOD
3. NeurIPS 2026Counterfactual Estimation under Composite Treatments via Progressive Distribution Alignment
4. NeurIPS 2026Counterfactual Predictive State Representations: The Intrinsic Dimension of Partial-Information Games
5. NeurIPS 2026Counterfactual Rollout Replay: Forkable Environments as Free Process Rewards for Software Engineering Agents
6. NeurIPS 2026CounterFlowNet: From Minimal Changes to Meaningful Counterfactual Explanations
7. NeurIPS 2026Neural-DISCO: Source-Conditioned Counterfactual Editing of Neural Population Activity
8. NeurIPS 2026Offloading Score: Measuring AI Reliance through Counterfactual Workflows
9. NeurIPS 2026The Pok\'emon Theorem and other Fairness Impossibility Results
10. NeurIPS 2026Tracing Actual Causes with Counterfactual Witness Maps
11. NeurIPS 2025A Counterfactual Semantics for Hybrid Dynamical Systems
12. NeurIPS 2025A Hierarchy of Graphical Models for Counterfactual Inferences
13. NeurIPS 2025Learning with Statistical Equality Constraints
14. NeurIPS 2025On Hierarchies of Fairness Notions in Cake Cutting: From Proportionality to Super Envy-Freeness
15. NeurIPS 2025Statistical Parity with Exponential Weights
16. NeurIPS 2024ABCFair: an Adaptable Benchmark approach for Comparing Fairness Methods
17. NeurIPS 2024Counterfactual Fairness by Combining Factual and Counterfactual Predictions
18. NeurIPS 2024Do Counterfactually Fair Image Classifiers Satisfy Group Fairness? -- A Theoretical and Empirical Study
19. NeurIPS 2024OxonFair: A Flexible Toolkit for Algorithmic Fairness
20. NeurIPS 2024Proportional Fairness in Non-Centroid Clustering
21. NeurIPS 2024Regression under demographic parity constraints via unlabeled post-processing
22. NeurIPS 2024Reproducibility Study: Equal Improvability: A New Fairness Notion Considering the Long-Term Impact
23. NeurIPS 2024Statistical Inference for Fairness Auditing
24. NeurIPS 2024The Fairness-Quality Tradeoff in Clustering
25. NeurIPS 2024The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning
26. NeurIPS 2024Towards Harmless Rawlsian Fairness Regardless of Demographic Prior
27. NeurIPS 2024When is Multicalibration Post-Processing Necessary?
28. NeurIPS 2023[Re] Fairness Guarantees under Demographic Shift
29. NeurIPS 2023[Re] FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles
30. NeurIPS 2023Adapting Fairness Interventions to Missing Values
31. NeurIPS 2023Auditing Fairness by Betting
32. NeurIPS 2023Constant Approximation for Individual Preference Stable Clustering
33. NeurIPS 2023Counterfactually Fair Representation
34. NeurIPS 2023Doubly Constrained Fair Clustering
35. NeurIPS 2023Fairness Aware Counterfactuals for Subgroups
36. NeurIPS 2023Fast Model DeBias with Machine Unlearning
37. NeurIPS 2023Group Fairness in Peer Review
38. NeurIPS 2023Mitigating Source Bias for Fairer Weak Supervision
39. NeurIPS 2023Small Total-Cost Constraints in Contextual Bandits with Knapsacks, with Application to Fairness

常见问题

2023–2026 年四大会议一共有多少篇反事实公平论文？

共 102 篇，按年份分别是 2023 年 31 篇、2024 年 31 篇、2025 年 19 篇、2026 年 21 篇。

NeurIPS 2026 有多少篇反事实公平论文？

NeurIPS 2026 有 10 篇反事实公平论文，上一届是 5 篇。

ICLR 2026 有多少篇反事实公平论文？

ICLR 2026 有 4 篇反事实公平论文，上一届是 6 篇。

ICML 2026 有多少篇反事实公平论文？

ICML 2026 有 7 篇反事实公平论文，上一届是 8 篇。

CVPR 2024 有多少篇反事实公平论文？

CVPR 2024 有 3 篇反事实公平论文，上一届是 2 篇。

哪个会议的反事实公平论文最多？

NeurIPS，2023–2026 年共 39 篇。