概念解释论文趋势 2023–2026

主要结论

• 概念解释论文从 2023 年的 91 篇增长到 2026 年的 117 篇，三年间扩大到约 1.3 倍。
• NeurIPS 是发概念解释论文最多的会议，2023–2026 年共 134 篇，占四个会议总量的 39%。
• 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 4 篇增至 2026 年的 23 篇。
• 在「可解释性」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的机制解释是 8.1 倍，概念解释是 1.3 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 2026CENDRe: Concept Extraction with Natural Domain Representations
• ICML 2026Evidential Copula Concept Embedding Models
• ICLR 2026Decoupling the Class Label and the Target Concept in Machine Unlearning
• CVPR 2026Agile Deliberation Concept Deliberation for Subjective Visual Classification
• NeurIPS 2025An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy Annotations
• ICML 2025Concept-Centric Token Interpretation for Vector-Quantized Generative Models
• ICLR 2025Causal Concept Graph Models: Beyond Causal Opacity in Deep Learning
• CVPR 2025Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models
• NeurIPS 2024[Re] On the Reproducibility of Post-Hoc Concept Bottleneck Models
• ICML 2024ContPhy: Continuum Physical Concept Learning and Reasoning from Videos
• ICLR 2024AttEXplore: Attribution for Explanation with model parameters eXploration
• CVPR 2024Fine-Grained Bipartite Concept Factorization for Clustering
• NeurIPS 2023[Re] Hierarchical Shrinkage: Improving the Accuracy and Interpretability of Tree-Based Methods
• ICML 2023A Closer Look at the Intervention Procedure of Concept Bottleneck Models
• ICLR 2023Concept Gradient: Concept-based Interpretation Without Linear Assumption
• CVPR 2023CRAFT: Concept Recursive Activation FacTorization for Explainability
• NeurIPS 2026Concept frustration: Aligning human concepts and machine representations
• ICML 2026On the Variability of Concept Activation Vectors
• ICLR 2026Hierarchical Concept-based Interpretable Models
• CVPR 2026DCoAR Deep Concept Injection into Unified Autoregressive Models for Personalized

全部概念解释论文

共 61 篇，第 1 / 2 页

1. ICLR 2026A Probabilistic Hard Concept Bottleneck for Steerable Generative Models
2. ICLR 2026CASteer: Cross-Attention Steering for Controllable Concept Erasure
3. ICLR 2026Causality ≠ Invariance: Function and Concept Vectors in LLMs
4. ICLR 2026Closing the Safety Gap: Surgical Concept Erasure in Visual Autoregressive Models
5. ICLR 2026Co-occurring Associated REtained concepts in Diffusion Unlearning
6. ICLR 2026Concept-based Adversarial Attack: a Probabilistic Perspective
7. ICLR 2026Debugging Concept Bottleneck Models through Removal and Retraining
8. ICLR 2026Decomposition of Concept-Level Rules in Visual Scenes
9. ICLR 2026Decoupling the Class Label and the Target Concept in Machine Unlearning
10. ICLR 2026Evaluating SAE interpretability without generating explanations
11. ICLR 2026Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Models
12. ICLR 2026Hierarchical Concept-based Interpretable Models
13. ICLR 2026LAMDA: A Longitudinal Android Malware Benchmark for Concept Drift Analysis
14. ICLR 2026Latent Concept Disentanglement in Transformer-based Language Models
15. ICLR 2026Leveraging Explanation to Improve Generalization of Meta Reinforcement Learning
16. ICLR 2026RepIt: Steering Language Models with Concept-Specific Refusal Vectors
17. ICLR 2026Sparling: End-to-End Spatial Concept Learning via Extremely Sparse Activations
18. ICLR 2026Tackling Time-Series Forecasting Generalization via Mitigating Concept Drift
19. ICLR 2026Temporal Concept Dynamics in Diffusion Models via Prompt-Conditioned Interventions
20. ICLR 2026The Lattice Representation Hypothesis and Concept Algebra in LLMs
21. ICLR 2026There Was Never a Bottleneck in Concept Bottleneck Models
22. ICLR 2026Training-free Counterfactual Explanation for Temporal Graph Model Inference
23. ICLR 2026When Machine Learning Gets Personal: Evaluating Prediction and Explanation
24. ICLR 2026When to Retrain after Drift: A Data-Only Test of Post-Drift Data Size Sufficiency
25. ICLR 2025Adapting Multi-modal Large Language Model to Concept Drift From Pre-training Onwards
26. ICLR 2025AutoCGP: Closed-Loop Concept-Guided Policies from Unlabeled Demonstrations
27. ICLR 2025Causal Concept Graph Models: Beyond Causal Opacity in Deep Learning
28. ICLR 2025CFD: Learning Generalized Molecular Representation via Concept-Enhanced Feedback Disentanglement
29. ICLR 2025Concept Bottleneck Large Language Models
30. ICLR 2025Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing
31. ICLR 2025ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning
32. ICLR 2025Counterfactual Concept Bottleneck Models
33. ICLR 2025Data-centric Prediction Explanation via Kernelized Stein Discrepancy
34. ICLR 2025Efficient and Accurate Explanation Estimation with Distribution Compression
35. ICLR 2025Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find Them
36. ICLR 2025From Tokens to Lattices: Emergent Lattice Structures in Language Models
37. ICLR 2025InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences
38. ICLR 2025MindSimulator: Exploring Brain Concept Localization via Synthetic fMRI
39. ICLR 2025Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence
40. ICLR 2025Restyling Unsupervised Concept Based Interpretable Networks with Generative Models
41. ICLR 2025Start Smart: Leveraging Gradients For Enhancing Mask-based XAI Methods
42. ICLR 2025Swing-by Dynamics in Concept Learning and Compositional Generalization
43. ICLR 2025XAIguiFormer: explainable artificial intelligence guided transformer for brain disorder identification
44. ICLR 2024AttEXplore: Attribution for Explanation with model parameters eXploration
45. ICLR 2024Classification with Conceptual Safeguards
46. ICLR 2024Concept Bottleneck Generative Models
47. ICLR 2024Effective pruning of web-scale datasets based on complexity of concept clusters
48. ICLR 2024Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations
49. ICLR 2024Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals
50. ICLR 2024On Error Propagation of Diffusion Models

常见问题

2023–2026 年四大会议一共有多少篇概念解释论文？

共 342 篇，按年份分别是 2023 年 91 篇、2024 年 63 篇、2025 年 71 篇、2026 年 117 篇。

NeurIPS 2026 有多少篇概念解释论文？

NeurIPS 2026 有 40 篇概念解释论文，上一届是 25 篇。

ICLR 2026 有多少篇概念解释论文？

ICLR 2026 有 24 篇概念解释论文，上一届是 19 篇。

ICML 2026 有多少篇概念解释论文？

ICML 2026 有 20 篇概念解释论文，上一届是 11 篇。

CVPR 2026 有多少篇概念解释论文？

CVPR 2026 有 33 篇概念解释论文，上一届是 16 篇。

哪个会议的概念解释论文最多？

NeurIPS，2023–2026 年共 134 篇。