社会层面 · accountability transparency and interpretability论文趋势 2023–2026

主要结论

• 社会层面 · accountability transparency and interpretability论文从 2023 年的 301 篇增长到 2026 年的 1,357 篇，三年间扩大到约 4.5 倍。
• NeurIPS 是发社会层面 · accountability transparency and interpretability论文最多的会议，2023–2026 年共 1,275 篇，占四个会议总量的 37%。
• 交叉方向里涨得最快的是社会层面 · privacy：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 93 篇。
• 在「对齐与负责任 AI」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的社会层面 · safety是 93 倍，社会层面 · accountability transparency and interpretability是 4.5 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 2026A Unifying Perspective on Language Model Interpretability
• ICML 2026$\texttt{PRISM}$:A 3D Probabilistic Neural Representation for Interpretable Shape Modeling
• ICLR 2026Automated Interpretability Metrics Do Not Distinguish Trained and Random Transformers
• CVPR 2026Beyond Matching to Tiles Bridging Unaligned Aerial and Satellite Views
• NeurIPS 2025$\mathcal{X}^2$-DFD: A framework for e$\mathcal{X}$plainable and e$\mathcal{X}$tendable Deepfake Detection
• ICML 2025(How) Can Transformers Predict Pseudo-Random Numbers?
• ICLR 2025Adaptive Transformer Programs: Bridging the Gap Between Performance and Interpretability in Transformers
• CVPR 2025Attribute-formed Class-specific Concept Space: Endowing Language Bottleneck Model with Better Interpretability and Scalability
• NeurIPS 20242D-OOB: Attributing Data Contribution Through Joint Valuation Framework
• ICML 2024Attention Meets Post-hoc Interpretability: A Mathematical Perspective
• ICLR 2024"What Data Benefits My Classifier?" Enhancing Model Performance and Interpretability through Influence-Based Data Selection
• CVPR 2024Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation
• NeurIPS 2023(S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability
• ICML 2023A Modern Look at the Relationship between Sharpness and Generalization
• ICLR 2023Deep Learning From Crowdsourced Labels: Coupled Cross-Entropy Minimization, Identifiability, and Regularization
• CVPR 2023Analyzing and Diagnosing Pose Estimation With Attributions
• NeurIPS 2026AdKnob: Ad Intensity Control and Labeling for LLM-Native Advertising
• ICML 2026$\texttt{ShaplEIG}$: Bayesian Experimental Design for Shapley Value Estimation
• ICLR 2026Bandits with Single-Peaked Preferences and Limited Resources
• CVPR 2026IEBGLAn Interpretability-Enhanced Brain Graph Learning Framework with LLM-Instructed Topology and

全部社会层面 · accountability transparency and interpretability论文

共 337 篇，第 1 / 7 页

1. ICML 2025"Who experiences large model decay and why?" A Hierarchical Framework for Diagnosing Heterogeneous Performance Drift
2. ICML 2025(How) Can Transformers Predict Pseudo-Random Numbers?
3. ICML 2025(How) Do Language Models Track State?
4. ICML 2025$S^2$FGL: Spatial Spectral Federated Graph Learning
5. ICML 2025A Checks-and-Balances Framework for Context-Aware Ethical AI Alignment
6. ICML 2025A Lens into Interpretable Transformer Mistakes via Semantic Dependency
7. ICML 2025A Mathematical Framework for AI-Human Integration in Work
8. ICML 2025A New Approach to Backtracking Counterfactual Explanations: A Unified Causal Framework for Efficient Model Interpretability
9. ICML 2025A Non-Asymptotic Convergent Analysis for Scored-Based Graph Generative Model via a System of Stochastic Differential Equations
10. ICML 2025A Parameter-Free and Near-Optimal Zeroth-Order Algorithm for Stochastic Convex Optimization
11. ICML 2025A Unified Approach to Routing and Cascading for LLMs
12. ICML 2025A Versatile Influence Function for Data Attribution with Non-Decomposable Loss
13. ICML 2025Accelerating Spectral Clustering under Fairness Constraints
14. ICML 2025Accurate Identification of Communication Between Multiple Interacting Neural Populations
15. ICML 2025Activation Space Interventions Can Be Transferred Between Large Language Models
16. ICML 2025Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization
17. ICML 2025Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets
18. ICML 2025Adversarial Inception Backdoor Attacks against Reinforcement Learning
19. ICML 2025Adversaries Can Misuse Combinations of Safe Models
20. ICML 2025Algorithmic Recourse for Long-Term Improvement
21. ICML 2025An analytic theory of creativity in convolutional diffusion models
22. ICML 2025An Efficient Private GPT Never Autoregressively Decodes
23. ICML 2025An End-to-End Model for Logits-Based Large Language Models Watermarking
24. ICML 2025Analyze Feature Flow to Enhance Interpretation and Steering in Language Models
25. ICML 2025Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning Attack
26. ICML 2025Approximate Differential Privacy of the $\ell_2$ Mechanism
27. ICML 2025Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models
28. ICML 2025Are Sparse Autoencoders Useful? A Case Study in Sparse Probing
29. ICML 2025Attributes Shape the Embedding Space of Face Recognition Models
30. ICML 2025Auditing $f$-differential privacy in one run
31. ICML 2025Auditing Prompt Caching in Language Model APIs
32. ICML 2025AutoAdvExBench: Benchmarking Autonomous Exploitation of Adversarial Example Defenses
33. ICML 2025Automatically Interpreting Millions of Features in Large Language Models
34. ICML 2025Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts
35. ICML 2025AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
36. ICML 2025B-score: Detecting biases in large language models using response history
37. ICML 2025BaxBench: Can LLMs Generate Correct and Secure Backends?
38. ICML 2025Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence
39. ICML 2025Beyond Log-Concavity and Score Regularity: Improved Convergence Bounds for Score-Based Generative Models in W2-distance
40. ICML 2025Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspective
41. ICML 2025BiMark: Unbiased Multilayer Watermarking for Large Language Models
42. ICML 2025Black-Box Adversarial Attacks on LLM-Based Code Completion
43. ICML 2025BOPO: Neural Combinatorial Optimization via Best-anchored and Objective-guided Preference Optimization
44. ICML 2025Breaking the $n^{1.5}$ Additive Error Barrier for Private and Efficient Graph Sparsification via Private Expander Decomposition
45. ICML 2025Breaking the Quadratic Barrier: Robust Cardinality Sketches for Adaptive Queries
46. ICML 2025Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging
47. ICML 2025Byzantine-Resilient Federated Alternating Gradient Descent and Minimization for Partly-Decoupled Low Rank Matrix Learning
48. ICML 2025Calibrated Language Models and How to Find Them with Label Smoothing
49. ICML 2025CAN: Leveraging Clients As Navigators for Generative Replay in Federated Continual Learning
50. ICML 2025Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs

常见问题

2023–2026 年四大会议一共有多少篇社会层面 · accountability transparency and interpretability论文？

共 3,411 篇，按年份分别是 2023 年 301 篇、2024 年 589 篇、2025 年 1,164 篇、2026 年 1,357 篇。

NeurIPS 2026 有多少篇社会层面 · accountability transparency and interpretability论文？

NeurIPS 2026 有 416 篇社会层面 · accountability transparency and interpretability论文，上一届是 522 篇。

ICLR 2026 有多少篇社会层面 · accountability transparency and interpretability论文？

ICLR 2026 有 292 篇社会层面 · accountability transparency and interpretability论文，上一届是 211 篇。

ICML 2026 有多少篇社会层面 · accountability transparency and interpretability论文？

ICML 2026 有 541 篇社会层面 · accountability transparency and interpretability论文，上一届是 337 篇。

CVPR 2026 有多少篇社会层面 · accountability transparency and interpretability论文？

CVPR 2026 有 108 篇社会层面 · accountability transparency and interpretability论文，上一届是 94 篇。

哪个会议的社会层面 · accountability transparency and interpretability论文最多？

NeurIPS，2023–2026 年共 1,275 篇。