Bias Mitigation papers, 2023–2026

Key findings

• Bias Mitigation went from 50 papers in 2023 to 76 in 2026, roughly 1.5x in three years.
• ICLR publishes the most Bias Mitigation work: 85 papers from 2023 to 2026, 30% of the four-venue total.
• The fastest-growing overlap is with Multimodal LLMs: papers tagged with both rose from 0 in 2023 to 15 in 2026.
• Among the 5 topics under Causal and Fairness, it ranks #4 by 2026 paper count; the fastest grower in the group, Causal Discovery, is up 2.4x versus 1.5x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Bias Mitigation papers

283 papers, page 2 of 6

51. ICML 2026Romberg-Extrapolated Zeroth-Order Gradient Estimator: Higher-Order Bias Reduction with Preserved Leading Directional Variance
52. ICML 2026Self-correcting for Debiasing Large Language Models
53. ICML 2026Steer Where It Matters: Token-Level Visual-Sensitivity Steering for LVLMs Hallucination Mitigation
54. ICML 2026Taming the Recent-Data Bias: Towards Robust Time Series Forecasting with Global Context
55. ICML 2026The Implicit Bias of Adam and Muon on Smooth Homogeneous Neural Networks
56. ICML 2026The Implicit Bias of Depth: From Neural Collapse to Softmax Codes
57. ICML 2026The Implicit Bias of Steepest Descent with Mini-batch Stochastic Gradient
58. ICML 2026Weak-to-Strong Generalization via Bregman Bias–Variance Decomposition
59. ICML 2026When Generalized Zero-Shot Learning Meets PU Learning: A Plug-and-Play Framework for Seen-Class Bias Mitigation
60. ICML 2026When Sample Selection Bias Precipitates Model Collapse
61. ICML 2026You Need Better Attention Priors
62. NeurIPS 2026Auditing the Judge: Human-Grounded Bias Discovery, Quantification, and Mitigation in LLM Judges
63. NeurIPS 2026Beyond the Training Distribution: Evaluating Predictions Under Distribution Shift and Selection Bias
64. NeurIPS 2026Controlling for Omitted Variable Bias in Deep Neural Networks
65. NeurIPS 2026Differentiable Exact Learning of Algorithms
66. NeurIPS 2026Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias
67. NeurIPS 2026Efficiently Representing Algorithms With Chain-of-Thought Transformers
68. NeurIPS 2026Empirical Bayes Rebiasing
69. NeurIPS 2026Latency-Conditioned Selection Bias in RLHF
70. NeurIPS 2026Learning Augmented Exact Exponential Algorithms
71. NeurIPS 2026Leveraging Dale’s Principle as an Inductive Bias in Recurrent Neural Networks
72. NeurIPS 2026On the Primacy Bias in RLVR Training
73. NeurIPS 2026PAVE: Prefill-Conditioned Activation Editing for Hallucination Mitigation in LVLMs
74. NeurIPS 2026Treat Bias as Noise: Training Bias-Robust LLM Reasoning via Reinforcement Learning
75. NeurIPS 2026VIGOR: Visual Gain Ordering for Hallucination Mitigation in Multimodal Discrete Diffusion Language Models
76. CVPR 2025ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large Language Models
77. CVPR 2025D2SP: Dynamic Dual-Stage Purification Framework for Dual Noise Mitigation in Vision-based Affective Recognition.
78. CVPR 2025Data Distributional Properties As Inductive Bias for Systematic Generalization
79. CVPR 2025Do We Always Need the Simplicity Bias? Looking for Optimal Inductive Biases in the Wild
80. CVPR 2025FreqDebias: Towards Generalizable Deepfake Detection via Consistency-Driven Frequency Debiasing
81. CVPR 2025Joint Vision-Language Social Bias Removal for CLIP
82. CVPR 2025Perceptual Inductive Bias Is What You Need Before Contrastive Learning
83. ICLR 2025A Decade's Battle on Dataset Bias: Are We There Yet?
84. ICLR 2025ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition
85. ICLR 2025Anti-Exposure Bias in Diffusion Models
86. ICLR 2025Balancing Bias in Two-sided Markets for Fair Stable Matchings
87. ICLR 2025Beyond Circuit Connections: A Non-Message Passing Graph Transformer Approach for Quantum Error Mitigation
88. ICLR 2025Bias Mitigation in Graph Diffusion Models
89. ICLR 2025Causally Motivated Sycophancy Mitigation for Large Language Models
90. ICLR 2025Efficient stagewise pretraining via progressive subnetworks
91. ICLR 2025Eliminating Position Bias of Language Models: A Mechanistic Approach
92. ICLR 2025Exploring the Camera Bias of Person Re-identification
93. ICLR 2025Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks
94. ICLR 2025Implicit Bias of Mirror Flow for Shallow Neural Networks in Univariate Regression
95. ICLR 2025Interference Among First-Price Pacing Equilibria: A Bias and Variance Analysis
96. ICLR 2025Language Models Need Inductive Biases to Count Inductively
97. ICLR 2025Manifold Constraint Reduces Exposure Bias in Accelerated Diffusion Sampling
98. ICLR 2025MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
99. ICLR 2025NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models
100. ICLR 2025Post-hoc Reward Calibration: A Case Study on Length Bias

FAQ

How many Bias Mitigation papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

284 in total: 50 in 2023, 73 in 2024, 85 in 2025, 76 in 2026.

How many Bias Mitigation papers are at NeurIPS 2026?

NeurIPS 2026 has 14 Bias Mitigation papers, versus 38 the year before.

How many Bias Mitigation papers are at ICLR 2026?

ICLR 2026 has 24 Bias Mitigation papers, versus 23 the year before.

How many Bias Mitigation papers are at ICML 2026?

ICML 2026 has 24 Bias Mitigation papers, versus 17 the year before.

How many Bias Mitigation papers are at CVPR 2026?

CVPR 2026 has 14 Bias Mitigation papers, versus 7 the year before.

Which conference publishes the most Bias Mitigation papers?

ICLR, with 85 papers from 2023 to 2026.