Counterfactual Explanation papers, 2023–2026

Key findings

• Counterfactual Explanation went from 21 papers in 2023 to 26 in 2026, roughly 1.2x in three years.
• NeurIPS publishes the most Counterfactual Explanation work: 31 papers from 2023 to 2026, 34% of the four-venue total.
• The fastest-growing overlap is with Counterfactual Fairness: papers tagged with both rose from 8 in 2023 to 10 in 2026.
• Among the 5 topics under Interpretability, it ranks #4 by 2026 paper count; the fastest grower in the group, Mechanistic Interpretability, is up 8.1x versus 1.2x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026Offloading Score: Measuring AI Reliance through Counterfactual Workflows
• ICML 2026Density-Guided Robust Counterfactual Explanations on Tabular Data under Model Multiplicity
• ICLR 2026Training-free Counterfactual Explanation for Temporal Graph Model Inference
• CVPR 2026Back to the Feature Explaining Video Classifiers with Video Counterfactual
• NeurIPS 2025Causal Explanation-Guided Learning for Organ Allocation
• ICML 2025Exogenous Isomorphism for Counterfactual Identifiability
• ICLR 2025Generating Likely Counterfactuals Using Sum-Product Networks
• CVPR 2025Towards Fine-Grained Interpretability: Counterfactual Explanations for Misclassification with Saliency Partition
• NeurIPS 2024AR-Pro: Counterfactual Explanations for Anomaly Repair with Formal Properties
• ICML 2024CF-OPT: Counterfactual Explanations for Structured Prediction
• ICLR 2024Counterfactual Density Estimation using Kernel Stein Discrepancies
• CVPR 2024Looking Similar Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning
• NeurIPS 2023[Re] FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles
• ICML 2023Counterfactual Analysis in Dynamic Latent State Models
• ICLR 2023Measuring Forgetting of Memorized Training Examples
• CVPR 2023OCTET: Object-Aware Counterfactual Explanations
• NeurIPS 2026Tracing Actual Causes with Counterfactual Witness Maps
• ICML 2026Algorithmic Recourse of In-Context Learning for Tabular Data
• ICLR 2026ATEX-CF: Attack-Informed Counterfactual Explanations for Graph Neural Networks
• CVPR 2026Making the Classification Explanation Faithful to the Confidence Score

All Counterfactual Explanation papers

90 papers, page 2 of 2

51. CVPR 2024Revisiting Counterfactual Problems in Referring Expression Comprehension
52. ICLR 2024Counterfactual Density Estimation using Kernel Stein Discrepancies
53. ICLR 2024Dynamic Discounted Counterfactual Regret Minimization
54. ICLR 2024UNR-Explainer: Counterfactual Explanations for Unsupervised Node Representation Learning Models
55. ICML 2024A Dual-module Framework for Counterfactual Estimation over Time
56. ICML 2024An Empirical Examination of Balancing Strategy for Counterfactual Estimation on Time Series
57. ICML 2024CF-OPT: Counterfactual Explanations for Structured Prediction
58. ICML 2024Counterfactual Image Editing
59. ICML 2024Counterfactual Metarules for Local and Global Recourse
60. ICML 2024Designing Decision Support Systems using Counterfactual Prediction Sets
61. ICML 2024Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicates
62. ICML 2024Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations
63. ICML 2024Et Tu Certifications: Robustness Certificates Yield Better Adversarial Examples
64. ICML 2024On Gradient-like Explanation under a Black-box Setting: When Black-box Explanations Become as Good as White-box
65. NeurIPS 2024A Neural Network Approach for Efficiently Answering Most Probable Explanation Queries in Probabilistic Models
66. NeurIPS 2024AR-Pro: Counterfactual Explanations for Anomaly Repair with Formal Properties
67. NeurIPS 2024Exogenous Matching: Learning Good Proposals for Tractable Counterfactual Estimation
68. NeurIPS 2024Extensive-Form Game Solving via Blackwell Approachability on Treeplexes
69. NeurIPS 2024Training for Stable Explanation for Free
70. CVPR 2023Adversarial Counterfactual Visual Explanations
71. CVPR 2023Grounding Counterfactual Explanation of Image Classifiers to Textual Concept Space
72. CVPR 2023IDGI: A Framework To Eliminate Explanation Noise From Integrated Gradients
73. CVPR 2023Masked Images Are Counterfactual Samples for Robust Fine-Tuning
74. CVPR 2023OCTET: Object-Aware Counterfactual Explanations
75. CVPR 2023Spatial-Temporal Concept Based Explanation of 3D ConvNets
76. CVPR 2023Towards Transferable Targeted Adversarial Examples
77. ICLR 2023Measuring Forgetting of Memorized Training Examples
78. ICLR 2023Robust Explanation Constraints for Neural Networks
79. ICML 2023Cluster Explanation via Polyhedral Descriptions
80. ICML 2023Counterfactual Analysis in Dynamic Latent State Models
81. ICML 2023Eventual Discounting Temporal Logic Counterfactual Experience Replay
82. ICML 2023GLOBE-CE: A Translation Based Approach for Global Counterfactual Explanations
83. ICML 2023PWSHAP: A Path-Wise Explanation Model for Targeted Variables
84. ICML 2023Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees
85. ICML 2023Sequential Counterfactual Risk Minimization
86. ICML 2023Trustworthy Policy Learning under the Counterfactual No-Harm Criterion
87. NeurIPS 2023[Re] FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles
88. NeurIPS 2023Counterfactual Evaluation of Peer-Review Assignment Policies
89. NeurIPS 2023Learning with Explanation Constraints
90. NeurIPS 2023The Utility of “Even if” Semifactual Explanation to Optimise Positive Outcomes

FAQ

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

90 in total: 21 in 2023, 20 in 2024, 23 in 2025, 26 in 2026.

How many Counterfactual Explanation papers are at NeurIPS 2026?

NeurIPS 2026 has 15 Counterfactual Explanation papers, versus 7 the year before.

How many Counterfactual Explanation papers are at ICLR 2026?

ICLR 2026 has 5 Counterfactual Explanation papers, versus 5 the year before.

How many Counterfactual Explanation papers are at ICML 2026?

ICML 2026 has 4 Counterfactual Explanation papers, versus 9 the year before.

How many Counterfactual Explanation papers are at CVPR 2026?

CVPR 2026 has 2 Counterfactual Explanation papers, versus 2 the year before.

Which conference publishes the most Counterfactual Explanation papers?

NeurIPS, with 31 papers from 2023 to 2026.