Social aspects · accountability transparency and interpretability papers, 2023–2026

Key findings

• Social aspects · accountability transparency and interpretability went from 301 papers in 2023 to 1,357 in 2026, roughly 4.5x in three years.
• NeurIPS publishes the most Social aspects · accountability transparency and interpretability work: 1,275 papers from 2023 to 2026, 37% of the four-venue total.
• The fastest-growing overlap is with Social aspects · privacy: papers tagged with both rose from 0 in 2023 to 93 in 2026.
• Among the 5 topics under Alignment and Responsible AI, it ranks #2 by 2026 paper count; the fastest grower in the group, Social aspects · safety, is up 93x versus 4.5x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Social aspects · accountability transparency and interpretability papers

255 papers, page 1 of 6

1. NeurIPS 20242D-OOB: Attributing Data Contribution Through Joint Valuation Framework
2. NeurIPS 20243-in-1: 2D Rotary Adaptation for Efficient Finetuning, Efficient Batching and Composability
3. NeurIPS 2024A Concept-Based Explainability Framework for Large Multimodal Models
4. NeurIPS 2024A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening
5. NeurIPS 2024A Functional Extension of Semi-Structured Networks
6. NeurIPS 2024A hierarchical decomposition for explaining ML performance discrepancies
7. NeurIPS 2024A Polar coordinate system represents syntax in large language models
8. NeurIPS 2024A Simple and Optimal Approach for Universal Online Learning with Gradient Variations
9. NeurIPS 2024A Systematic Review of NeurIPS Dataset Management Practices
10. NeurIPS 2024A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis
11. NeurIPS 2024A-FedPD: Aligning Dual-Drift is All Federated Primal-Dual Learning Needs
12. NeurIPS 2024Abrupt Learning in Transformers: A Case Study on Matrix Completion
13. NeurIPS 2024Abstracted Shapes as Tokens - A Generalizable and Interpretable Model for Time-series Classification
14. NeurIPS 2024AdaNovo: Towards Robust \emph{De Novo} Peptide Sequencing in Proteomics against Data Biases
15. NeurIPS 2024Aggregate-and-Adapt Natural Language Prompts for Downstream Generalization of CLIP
16. NeurIPS 2024Aggregating Quantitative Relative Judgments: From Social Choice to Ranking Prediction
17. NeurIPS 2024Algorithmic Capabilities of Random Transformers
18. NeurIPS 2024Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems Reconstruction
19. NeurIPS 2024ALPINE: Unveiling The Planning Capability of Autoregressive Learning in Language Models
20. NeurIPS 2024An Analysis of Tokenization: Transformers under Markov Data
21. NeurIPS 2024An Equivalence Between Static and Dynamic Regret Minimization
22. NeurIPS 2024Analysing the Generalisation and Reliability of Steering Vectors
23. NeurIPS 2024AR-Pro: Counterfactual Explanations for Anomaly Repair with Formal Properties
24. NeurIPS 2024Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?
25. NeurIPS 2024Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning
26. NeurIPS 2024Auditing Local Explanations is Hard
27. NeurIPS 2024Automating Data Annotation under Strategic Human Agents: Risks and Potential Solutions
28. NeurIPS 2024B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable
29. NeurIPS 2024Bandit-Feedback Online Multiclass Classification: Variants and Tradeoffs
30. NeurIPS 2024Barely Random Algorithms and Collective Metrical Task Systems
31. NeurIPS 2024BEACON: Benchmark for Comprehensive RNA Tasks and Language Models
32. NeurIPS 2024BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices
33. NeurIPS 2024Beyond Accuracy: Ensuring Correct Predictions With Correct Rationales
34. NeurIPS 2024Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?
35. NeurIPS 2024Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects
36. NeurIPS 2024Binding in hippocampal-entorhinal circuits enables compositionality in cognitive maps
37. NeurIPS 2024BricksRL: A Platform for Democratizing Robotics and Reinforcement Learning Research and Education with LEGO
38. NeurIPS 2024Bridging OOD Detection and Generalization: A Graph-Theoretic View
39. NeurIPS 2024Capturing the denoising effect of PCA via compression ratio
40. NeurIPS 2024Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model
41. NeurIPS 2024Causal Dependence Plots
42. NeurIPS 2024Cherry on Top: Parameter Heterogeneity and Quantization in Large Language Models
43. NeurIPS 2024ChronoEpilogi: Scalable Time Series Selection with Multiple Solutions
44. NeurIPS 2024Coarse-to-Fine Concept Bottleneck Models
45. NeurIPS 2024Codec Avatar Studio: Paired Human Captures for Complete, Driveable, and Generalizable Avatars
46. NeurIPS 2024Compact Language Models via Pruning and Knowledge Distillation
47. NeurIPS 2024Compact Proofs of Model Performance via Mechanistic Interpretability
48. NeurIPS 2024Computational Aspects of Bayesian Persuasion under Approximate Best Response
49. NeurIPS 2024Confidence Regulation Neurons in Language Models
50. NeurIPS 2024Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence Challenge

FAQ

How many Social aspects · accountability transparency and interpretability papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

3,411 in total: 301 in 2023, 589 in 2024, 1,164 in 2025, 1,357 in 2026.

How many Social aspects · accountability transparency and interpretability papers are at NeurIPS 2026?

NeurIPS 2026 has 416 Social aspects · accountability transparency and interpretability papers, versus 522 the year before.

How many Social aspects · accountability transparency and interpretability papers are at ICLR 2026?

ICLR 2026 has 292 Social aspects · accountability transparency and interpretability papers, versus 211 the year before.

How many Social aspects · accountability transparency and interpretability papers are at ICML 2026?

ICML 2026 has 541 Social aspects · accountability transparency and interpretability papers, versus 337 the year before.

How many Social aspects · accountability transparency and interpretability papers are at CVPR 2026?

CVPR 2026 has 108 Social aspects · accountability transparency and interpretability papers, versus 94 the year before.

Which conference publishes the most Social aspects · accountability transparency and interpretability papers?

NeurIPS, with 1,275 papers from 2023 to 2026.