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 283 篇，第 3 / 6 页

101. ICLR 2025SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP
102. ICLR 2025SEBRA : Debiasing through Self-Guided Bias Ranking
103. ICLR 2025Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late In Training
104. ICLR 2025Tuning Frequency Bias of State Space Models
105. ICLR 2025Unlearning-based Neural Interpretations
106. ICML 2025ADDQ: Adaptive distributional double Q-learning
107. ICML 2025Beyond Communication Overhead: A Multilevel Monte Carlo Approach for Mitigating Compression Bias in Distributed Learning
108. ICML 2025Clipped SGD Algorithms for Performative Prediction: Tight Bounds for Stochastic Bias and Remedies
109. ICML 2025Controlling Underestimation Bias in Constrained Reinforcement Learning for Safe Exploration
110. ICML 2025Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias
111. ICML 2025Implicit Bias of Gradient Descent for Non-Homogeneous Deep Networks
112. ICML 2025Inductive Gradient Adjustment for Spectral Bias in Implicit Neural Representations
113. ICML 2025Mirror, Mirror of the Flow: How Does Regularization Shape Implicit Bias?
114. ICML 2025NeuronTune: Towards Self-Guided Spurious Bias Mitigation
115. ICML 2025On Mitigating Affinity Bias through Bandits with Evolving Biased Feedback
116. ICML 2025On the Emergence of Position Bias in Transformers
117. ICML 2025Parametric Scaling Law of Tuning Bias in Conformal Prediction
118. ICML 2025Position: Political Neutrality in AI Is Impossible — But Here Is How to Approximate It
119. ICML 2025Resolving Lexical Bias in Model Editing
120. ICML 2025Rethinking the Bias of Foundation Model under Long-tailed Distribution
121. ICML 2025SCISSOR: Mitigating Semantic Bias through Cluster-Aware Siamese Networks for Robust Classification
122. ICML 2025Subgroups Matter for Robust Bias Mitigation
123. NeurIPS 2025A Black-Box Debiasing Framework for Conditional Sampling
124. NeurIPS 2025Any Large Language Model Can Be a Reliable Judge: Debiasing with a Reasoning-based Bias Detector
125. NeurIPS 2025Approximate Gradient Coding for Distributed Learning with Heterogeneous Stragglers
126. NeurIPS 2025Auto-Search and Refinement: An Automated Framework for Gender Bias Mitigation in Large Language Models
127. NeurIPS 2025Benford’s Curse: Tracing Digit Bias to Numerical Hallucination in LLMs
128. NeurIPS 2025Decoupling Contrastive Decoding: Robust Hallucination Mitigation in Multimodal Large Language Models
129. NeurIPS 2025Diffusing DeBias: Synthetic Bias Amplification for Model Debiasing
130. NeurIPS 2025Disentangled Representation Learning via Modular Compositional Bias
131. NeurIPS 2025FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models
132. NeurIPS 2025FairNet: Dynamic Fairness Correction without Performance Loss via Contrastive Conditional LoRA
133. NeurIPS 2025FlashBias: Fast Computation of Attention with Bias
134. NeurIPS 2025Fourier Clouds: Fast Bias Correction for Imbalanced Semi-Supervised Learning
135. NeurIPS 2025How Does Topology Bias Distort Message Passing in Graph Recommender? A Dirichlet Energy Perspective
136. NeurIPS 2025How Memory in Optimization Algorithms Implicitly Modifies the Loss
137. NeurIPS 2025Implicit Bias of Spectral Descent and Muon on Multiclass Separable Data
138. NeurIPS 2025Improving Diffusion-based Inverse Algorithms under Few-Step Constraint via Linear Extrapolation
139. NeurIPS 2025Intervene-All-Paths: Unified Mitigation of LVLM Hallucinations across Alignment Formats
140. NeurIPS 2025Language‑Bias‑Resilient Visual Question Answering via Adaptive Multi‑Margin Collaborative Debiasing
141. NeurIPS 2025Learning to cluster neuronal function
142. NeurIPS 2025LightFair: Towards an Efficient Alternative for Fair T2I Diffusion via Debiasing Pre-trained Text Encoders
143. NeurIPS 2025Meta Guidance: Incorporating Inductive Biases into Deep Time Series Imputers
144. NeurIPS 2025More of the Same: Persistent Representational Harms Under Increased Representation
145. NeurIPS 2025Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data
146. NeurIPS 2025Obliviator Reveals the Cost of Nonlinear Guardedness in Concept Erasure
147. NeurIPS 2025On Inductive Biases That Enable Generalization in Diffusion Transformers
148. NeurIPS 2025On the Bias of Next-Token Predictors Toward Systematically Inefficient Reasoning: A Shortest-Path Case Study
149. NeurIPS 2025Position: If Innovation in AI systematically Violates Fundamental Rights, Is It Innovation at All?
150. NeurIPS 2025Rectifying Soft-Label Entangled Bias in Long-Tailed Dataset Distillation

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。