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

292 papers, page 1 of 6

1. ICLR 2026$\mathbf{Li_2}$: A Framework on Dynamics of Feature Emergence and Delayed Generalization
2. ICLR 2026A Comprehensive Information-Decomposition Analysis of Large Vision-Language Models
3. ICLR 2026A Probabilistic Hard Concept Bottleneck for Steerable Generative Models
4. ICLR 2026AbsTopK: Rethinking Sparse Autoencoders For Bidirectional Features
5. ICLR 2026ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall
6. ICLR 2026Adaptive Social Learning via Mode Policy Optimization for Language Agents
7. ICLR 2026Addressing divergent representations from causal interventions on neural networks
8. ICLR 2026An Information-Theoretic Parameter-Free Bayesian Framework for Probing Labeled Dependency Trees from Attention Score
9. ICLR 2026ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack
10. ICLR 2026Asymptotic analysis of shallow and deep forgetting in replay with neural collapse
11. ICLR 2026Attribution-Guided Decoding
12. ICLR 2026Automated Interpretability Metrics Do Not Distinguish Trained and Random Transformers
13. ICLR 2026Bandits with Single-Peaked Preferences and Limited Resources
14. ICLR 2026Bayesian Influence Functions for Hessian-Free Data Attribution
15. ICLR 2026Bayesian Neural Networks for Functional ANOVA Model
16. ICLR 2026Behavior Learning (BL)
17. ICLR 2026Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective
18. ICLR 2026Best-of-N through the Smoothing Lens: KL Divergence and Regret Analysis
19. ICLR 2026Beyond Linear Probes: Dynamic Safety Monitoring for Language Models
20. ICLR 2026Beyond RLHF and NLHF: Population-Proportional Alignment under an Axiomatic Framework
21. ICLR 2026Beyond Uniformity: Sample and Frequency Meta Weighting for Post-Training Quantization of Diffusion Models
22. ICLR 2026Bi-Criteria Metric Distortion
23. ICLR 2026BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses
24. ICLR 2026Bilinear relational structure fixes reversal curse and enables consistent model editing
25. ICLR 2026Block Recurrent Dynamics in Vision Transformers
26. ICLR 2026Boosting for Predictive Sufficiency
27. ICLR 2026Bridging Explainability and Embeddings: BEE Aware of Spuriousness
28. ICLR 2026Bridging ML and algorithms: comparison of hyperbolic embeddings
29. ICLR 2026Bringing Stability to Diffusion: Decomposing and Reducing Variance of Training Masked Diffusion Models
30. ICLR 2026Can SAEs reveal and mitigate racial biases of LLMs in healthcare?
31. ICLR 2026Can Small Training Runs Reliably Guide Data Curation? Rethinking Proxy-Model Practice
32. ICLR 2026Causality ≠ Invariance: Function and Concept Vectors in LLMs
33. ICLR 2026Change Point Localization and Inference in Dynamic Multilayer Networks
34. ICLR 2026Characterizing and Mitigating Reasoning Drift in Large Language Models
35. ICLR 2026Characterizing Deep Research: A Benchmark and Formal Definition
36. ICLR 2026Characterizing Pattern Matching and Its Limits on Compositional Task Structures
37. ICLR 2026Circuit Insights: Towards Interpretability Beyond Activations
38. ICLR 2026Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models
39. ICLR 2026CLUE: Conflict-guided Localization for LLM Unlearning Framework
40. ICLR 2026CodeBrain: Towards Decoupled Interpretability and Multi-Scale Architecture for EEG Foundation Model
41. ICLR 2026Command-V: Training-Free Representation Finetuning Transfer
42. ICLR 2026Completed Hyperparameter Transfer across Modules, Width, Depth, Batch and Duration
43. ICLR 2026Composable Sparse Subnetworks via Maximum-Entropy Principle
44. ICLR 2026Concepts' Information Bottleneck Models
45. ICLR 2026Conjuring Semantic Similarity
46. ICLR 2026ContextBench: Modifying Contexts for Targeted Latent Activation and Behaviour Elicitation
47. ICLR 2026Controlling Repetition in Protein Language Models
48. ICLR 2026Copy-Paste to Mitigate Large Language Model Hallucinations
49. ICLR 2026Correlations in the Data Lead to Semantically Rich Feature Geometry Under Superposition
50. ICLR 2026Counterfactual Explanations on Robust Perceptual Geodesics

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.