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 19 篇，第 1 / 1 页

1. ICLR 2026Benchmarking Stochastic Approximation Algorithms for Fairness-Constrained Training of Deep Neural Networks
2. ICLR 2026Counterfactual Explanations on Robust Perceptual Geodesics
3. ICLR 2026Counterfactual LLM-based Framework for Measuring Rhetorical Style
4. ICLR 2026Fair Classification by Direct Intervention on Operating Characteristics
5. ICLR 2025Certifying Counterfactual Bias in LLMs
6. ICLR 2025Counterfactual Realizability
7. ICLR 2025First-Person Fairness in Chatbots
8. ICLR 2025Learning Causal Alignment for Reliable Disease Diagnosis
9. ICLR 2025Towards counterfactual fairness through auxiliary variables
10. ICLR 2025Towards Marginal Fairness Sliced Wasserstein Barycenter
11. ICLR 2024Counterfactual Density Estimation using Kernel Stein Discrepancies
12. ICLR 2024Dynamic Discounted Counterfactual Regret Minimization
13. ICLR 2024Fair Classifiers that Abstain without Harm
14. ICLR 2024fairret: a Framework for Differentiable Fairness Regularization Terms
15. ICLR 2024Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks
16. ICLR 2023FairGBM: Gradient Boosting with Fairness Constraints
17. ICLR 2023FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Data
18. ICLR 2023Learning with Logical Constraints but without Shortcut Satisfaction
19. ICLR 2023Neural Causal Models for Counterfactual Identification and Estimation

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。