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 84 篇，第 1 / 2 页

1. NeurIPS 2026Auditing the Judge: Human-Grounded Bias Discovery, Quantification, and Mitigation in LLM Judges
2. NeurIPS 2026Beyond the Training Distribution: Evaluating Predictions Under Distribution Shift and Selection Bias
3. NeurIPS 2026Controlling for Omitted Variable Bias in Deep Neural Networks
4. NeurIPS 2026Differentiable Exact Learning of Algorithms
5. NeurIPS 2026Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias
6. NeurIPS 2026Efficiently Representing Algorithms With Chain-of-Thought Transformers
7. NeurIPS 2026Empirical Bayes Rebiasing
8. NeurIPS 2026Latency-Conditioned Selection Bias in RLHF
9. NeurIPS 2026Learning Augmented Exact Exponential Algorithms
10. NeurIPS 2026Leveraging Dale’s Principle as an Inductive Bias in Recurrent Neural Networks
11. NeurIPS 2026On the Primacy Bias in RLVR Training
12. NeurIPS 2026PAVE: Prefill-Conditioned Activation Editing for Hallucination Mitigation in LVLMs
13. NeurIPS 2026Treat Bias as Noise: Training Bias-Robust LLM Reasoning via Reinforcement Learning
14. NeurIPS 2026VIGOR: Visual Gain Ordering for Hallucination Mitigation in Multimodal Discrete Diffusion Language Models
15. NeurIPS 2025A Black-Box Debiasing Framework for Conditional Sampling
16. NeurIPS 2025Any Large Language Model Can Be a Reliable Judge: Debiasing with a Reasoning-based Bias Detector
17. NeurIPS 2025Approximate Gradient Coding for Distributed Learning with Heterogeneous Stragglers
18. NeurIPS 2025Auto-Search and Refinement: An Automated Framework for Gender Bias Mitigation in Large Language Models
19. NeurIPS 2025Benford’s Curse: Tracing Digit Bias to Numerical Hallucination in LLMs
20. NeurIPS 2025Decoupling Contrastive Decoding: Robust Hallucination Mitigation in Multimodal Large Language Models
21. NeurIPS 2025Diffusing DeBias: Synthetic Bias Amplification for Model Debiasing
22. NeurIPS 2025Disentangled Representation Learning via Modular Compositional Bias
23. NeurIPS 2025FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models
24. NeurIPS 2025FairNet: Dynamic Fairness Correction without Performance Loss via Contrastive Conditional LoRA
25. NeurIPS 2025FlashBias: Fast Computation of Attention with Bias
26. NeurIPS 2025Fourier Clouds: Fast Bias Correction for Imbalanced Semi-Supervised Learning
27. NeurIPS 2025How Does Topology Bias Distort Message Passing in Graph Recommender? A Dirichlet Energy Perspective
28. NeurIPS 2025How Memory in Optimization Algorithms Implicitly Modifies the Loss
29. NeurIPS 2025Implicit Bias of Spectral Descent and Muon on Multiclass Separable Data
30. NeurIPS 2025Improving Diffusion-based Inverse Algorithms under Few-Step Constraint via Linear Extrapolation
31. NeurIPS 2025Intervene-All-Paths: Unified Mitigation of LVLM Hallucinations across Alignment Formats
32. NeurIPS 2025Language‑Bias‑Resilient Visual Question Answering via Adaptive Multi‑Margin Collaborative Debiasing
33. NeurIPS 2025Learning to cluster neuronal function
34. NeurIPS 2025LightFair: Towards an Efficient Alternative for Fair T2I Diffusion via Debiasing Pre-trained Text Encoders
35. NeurIPS 2025Meta Guidance: Incorporating Inductive Biases into Deep Time Series Imputers
36. NeurIPS 2025More of the Same: Persistent Representational Harms Under Increased Representation
37. NeurIPS 2025Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data
38. NeurIPS 2025Obliviator Reveals the Cost of Nonlinear Guardedness in Concept Erasure
39. NeurIPS 2025On Inductive Biases That Enable Generalization in Diffusion Transformers
40. NeurIPS 2025On the Bias of Next-Token Predictors Toward Systematically Inefficient Reasoning: A Shortest-Path Case Study
41. NeurIPS 2025Position: If Innovation in AI systematically Violates Fundamental Rights, Is It Innovation at All?
42. NeurIPS 2025Rectifying Soft-Label Entangled Bias in Long-Tailed Dataset Distillation
43. NeurIPS 2025Robust Graph Condensation via Classification Complexity Mitigation
44. NeurIPS 2025Silencer: From Discovery to Mitigation of Self-Bias in LLM-as-Benchmark-Generator
45. NeurIPS 2025Tackling Biased Evaluators in Dueling Bandits
46. NeurIPS 2025The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels
47. NeurIPS 2025The Persistence of Neural Collapse Despite Low-Rank Bias
48. NeurIPS 2025Training the Untrainable: Introducing Inductive Bias via Representational Alignment
49. NeurIPS 2025TranSUN: A Preemptive Paradigm to Eradicate Retransformation Bias Intrinsically from Regression Models in Recommender Systems
50. NeurIPS 2025Uncovering the Spectral Bias in Diagonal State Space Models

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。