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

75 papers, page 1 of 2

1. CVPR 2026BAMI Training-Free Bias Mitigation in GUI Grounding
2. CVPR 2026BD-Merging Bias-Aware Dynamic Model Merging with Evidence-Guided Contrastive Learning
3. CVPR 2026Bias at the End of the Score
4. CVPR 2026Bias Is a Subspace Not a Coordinate A Geometric Rethinking
5. CVPR 2026Cross-Modal Attention Calibration for LVLM Hallucination Mitigation
6. CVPR 2026DSO Direct Steering Optimization for Bias Mitigation
7. CVPR 2026Elucidating the SNR-t Bias of Diffusion Probabilistic Models
8. CVPR 2026Envision Attend Then Respond Counterfactual Hallucination Mitigation in Large Vision-Language
9. CVPR 2026Mitigating Simplicity Bias in OOD Detection through Object Co-occurrence Analysis
10. CVPR 2026MixFlow Training Alleviating Exposure Bias with Slowed Interpolation Mixture
11. CVPR 2026Multimodal Semantic Bias Mitigation for Diverse Text-To-3D Generation
12. CVPR 2026Physically-Grounded Turbulence Mitigation with Frame-Shared Degradation Parameters
13. CVPR 2026Rank-Guided Pseudo-Bias Learning for Robust Black-Box Adaptation
14. ICLR 2026BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models
15. ICLR 2026Benchmarking Bias Mitigation Toward Fairness Without Harm from Vision to LVLMs
16. ICLR 2026Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying Prompts
17. ICLR 2026BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models
18. ICLR 2026BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses
19. ICLR 2026Directional Convergence, Benign Overfitting of Gradient Descent in leaky ReLU two-layer Neural Networks
20. ICLR 2026Discovering alternative solutions beyond the simplicity bias in recurrent neural networks
21. ICLR 2026GRADIEND: Feature Learning within Neural Networks Exemplified through Biases
22. ICLR 2026How does the optimizer implicitly bias the model merging loss landscape?
23. ICLR 2026Hyperbolic Aware Minimization: Implicit Bias for Sparsity
24. ICLR 2026Implicit Bias of Per-sample Adam on Separable Data: Departure from the Full-batch Regime
25. ICLR 2026Implicit bias produces neural scaling laws in learning curves, from perceptrons to deep networks
26. ICLR 2026Iterative Training of Physics-Informed Neural Networks with Fourier-enhanced Features
27. ICLR 2026Minor First, Major Last: A Depth-Induced Implicit Bias of Sharpness-Aware Minimization
28. ICLR 2026Never Saddle: Reparameterized Steepest Descent as Mirror Flow
29. ICLR 2026Noise Stability of Transformer Models
30. ICLR 2026OrderDP: A Theoretically Guaranteed Lossless Dynamic Data Pruning Framework
31. ICLR 2026Saddle-to-Saddle Dynamics Explains A Simplicity Bias Across Neural Network Architectures
32. ICLR 2026Saddle-To-Saddle Dynamics in Deep ReLU Networks: Low-Rank Bias in the First Saddle Escape
33. ICLR 2026The First Impression Problem: Internal Bias Triggers Overthinking in Reasoning Models
34. ICLR 2026Transformers with Endogenous In-Context Learning: Bias Characterization and Mitigation
35. ICLR 2026Trapped by simplicity: When Transformers fail to learn from noisy features
36. ICLR 2026Variational Deep Learning via Implicit Regularization
37. ICLR 2026WRING Out The Bias: A Rotation-Based Alternative To Projection Debiasing
38. ICML 2026ABCD: All Biases Come Disguised
39. ICML 2026BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation
40. ICML 2026Breaking the Reversal Curse in Autoregressive Language Models via Identity Bridge
41. ICML 2026Capturing Gaze Shifts for Guidance: Cross-Modal Fusion Enhancement for VLM Hallucination Mitigation
42. ICML 2026DISCO: Mitigating Bias in Deep Learning with Conditional Distance Correlation
43. ICML 2026FedScar: Correcting Geometric Bias for Flatness-Consistent Federated Learning
44. ICML 2026FIBER: A Differentially Private Optimizer with Filter-Aware Innovation Bias Correction
45. ICML 2026Iterative Refinement Neural Operators are Learned Fixed-Point Solvers: A Principled Approach to Spectral Bias Mitigation
46. ICML 2026LLM Watermark Evasion via Bias Inversion
47. ICML 2026Logit-Attention Divergence: Mitigating Position Bias in Multi-Image Retrieval via Attention-Guided Calibration
48. ICML 2026Mitigating Bias in Locally Constrained Decoding via Tractable Proposals
49. ICML 2026Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneck
50. ICML 2026Omitted Variable Bias in Language Models Under Distribution Shift

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.