偏见缓解论文趋势 2023–2026

主要结论

• 偏见缓解论文从 2023 年的 50 篇增长到 2026 年的 76 篇，三年间扩大到约 1.5 倍。
• ICLR 是发偏见缓解论文最多的会议，2023–2026 年共 85 篇，占四个会议总量的 30%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 15 篇。
• 在「因果与公平」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的因果发现是 2.4 倍，偏见缓解是 1.5 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 2026Controlling for Omitted Variable Bias in Deep Neural Networks
• ICML 2026BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation
• ICLR 2026Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying Prompts
• CVPR 2026BAMI Training-Free Bias Mitigation in GUI Grounding
• NeurIPS 2025Any Large Language Model Can Be a Reliable Judge: Debiasing with a Reasoning-based Bias Detector
• ICML 2025Clipped SGD Algorithms for Performative Prediction: Tight Bounds for Stochastic Bias and Remedies
• ICLR 2025ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition
• CVPR 2025Data Distributional Properties As Inductive Bias for Systematic Generalization
• NeurIPS 2024Bayesian Identification of the Hamiltonian Inductive Bias in Dynamical Systems
• ICML 2024Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks
• ICLR 2024A 2-Dimensional State Space Layer for Spatial Inductive Bias
• CVPR 2024Diffeomorphic Template Registration for Atmospheric Turbulence Mitigation
• NeurIPS 2023Fast Model DeBias with Machine Unlearning
• ICML 2023FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reduction
• ICLR 2023Bias Propagation in Federated Learning
• CVPR 2023Bias Mimicking: A Simple Sampling Approach for Bias Mitigation
• NeurIPS 2026Empirical Bayes Rebiasing
• ICML 2026DISCO: Mitigating Bias in Deep Learning with Conditional Distance Correlation
• ICLR 2026BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses
• CVPR 2026Bias at the End of the Score

全部偏见缓解论文

共 85 篇，第 1 / 2 页

1. ICLR 2026BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models
2. ICLR 2026Benchmarking Bias Mitigation Toward Fairness Without Harm from Vision to LVLMs
3. ICLR 2026Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying Prompts
4. ICLR 2026BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models
5. ICLR 2026BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses
6. ICLR 2026Directional Convergence, Benign Overfitting of Gradient Descent in leaky ReLU two-layer Neural Networks
7. ICLR 2026Discovering alternative solutions beyond the simplicity bias in recurrent neural networks
8. ICLR 2026GRADIEND: Feature Learning within Neural Networks Exemplified through Biases
9. ICLR 2026How does the optimizer implicitly bias the model merging loss landscape?
10. ICLR 2026Hyperbolic Aware Minimization: Implicit Bias for Sparsity
11. ICLR 2026Implicit Bias of Per-sample Adam on Separable Data: Departure from the Full-batch Regime
12. ICLR 2026Implicit bias produces neural scaling laws in learning curves, from perceptrons to deep networks
13. ICLR 2026Iterative Training of Physics-Informed Neural Networks with Fourier-enhanced Features
14. ICLR 2026Minor First, Major Last: A Depth-Induced Implicit Bias of Sharpness-Aware Minimization
15. ICLR 2026Never Saddle: Reparameterized Steepest Descent as Mirror Flow
16. ICLR 2026Noise Stability of Transformer Models
17. ICLR 2026OrderDP: A Theoretically Guaranteed Lossless Dynamic Data Pruning Framework
18. ICLR 2026Saddle-to-Saddle Dynamics Explains A Simplicity Bias Across Neural Network Architectures
19. ICLR 2026Saddle-To-Saddle Dynamics in Deep ReLU Networks: Low-Rank Bias in the First Saddle Escape
20. ICLR 2026The First Impression Problem: Internal Bias Triggers Overthinking in Reasoning Models
21. ICLR 2026Transformers with Endogenous In-Context Learning: Bias Characterization and Mitigation
22. ICLR 2026Trapped by simplicity: When Transformers fail to learn from noisy features
23. ICLR 2026Variational Deep Learning via Implicit Regularization
24. ICLR 2026WRING Out The Bias: A Rotation-Based Alternative To Projection Debiasing
25. ICLR 2025A Decade's Battle on Dataset Bias: Are We There Yet?
26. ICLR 2025ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition
27. ICLR 2025Anti-Exposure Bias in Diffusion Models
28. ICLR 2025Balancing Bias in Two-sided Markets for Fair Stable Matchings
29. ICLR 2025Beyond Circuit Connections: A Non-Message Passing Graph Transformer Approach for Quantum Error Mitigation
30. ICLR 2025Bias Mitigation in Graph Diffusion Models
31. ICLR 2025Causally Motivated Sycophancy Mitigation for Large Language Models
32. ICLR 2025Efficient stagewise pretraining via progressive subnetworks
33. ICLR 2025Eliminating Position Bias of Language Models: A Mechanistic Approach
34. ICLR 2025Exploring the Camera Bias of Person Re-identification
35. ICLR 2025Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks
36. ICLR 2025Implicit Bias of Mirror Flow for Shallow Neural Networks in Univariate Regression
37. ICLR 2025Interference Among First-Price Pacing Equilibria: A Bias and Variance Analysis
38. ICLR 2025Language Models Need Inductive Biases to Count Inductively
39. ICLR 2025Manifold Constraint Reduces Exposure Bias in Accelerated Diffusion Sampling
40. ICLR 2025MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
41. ICLR 2025NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models
42. ICLR 2025Post-hoc Reward Calibration: A Case Study on Length Bias
43. ICLR 2025SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP
44. ICLR 2025SEBRA : Debiasing through Self-Guided Bias Ranking
45. ICLR 2025Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late In Training
46. ICLR 2025Tuning Frequency Bias of State Space Models
47. ICLR 2025Unlearning-based Neural Interpretations
48. ICLR 2024A 2-Dimensional State Space Layer for Spatial Inductive Bias
49. ICLR 2024Bounds on Representation-Induced Confounding Bias for Treatment Effect Estimation
50. ICLR 2024Debiasing Algorithm through Model Adaptation

常见问题

2023–2026 年四大会议一共有多少篇偏见缓解论文？

共 284 篇，按年份分别是 2023 年 50 篇、2024 年 73 篇、2025 年 85 篇、2026 年 76 篇。

NeurIPS 2026 有多少篇偏见缓解论文？

NeurIPS 2026 有 14 篇偏见缓解论文，上一届是 38 篇。

ICLR 2026 有多少篇偏见缓解论文？

ICLR 2026 有 24 篇偏见缓解论文，上一届是 23 篇。

ICML 2026 有多少篇偏见缓解论文？

ICML 2026 有 24 篇偏见缓解论文，上一届是 17 篇。

CVPR 2026 有多少篇偏见缓解论文？

CVPR 2026 有 14 篇偏见缓解论文，上一届是 7 篇。

哪个会议的偏见缓解论文最多？

ICLR，2023–2026 年共 85 篇。