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

211 papers, page 1 of 5

1. ICLR 20253D-Properties: Identifying Challenges in DPO and Charting a Path Forward
2. ICLR 2025A General Framework for Producing Interpretable Semantic Text Embeddings
3. ICLR 2025A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals
4. ICLR 2025Accelerating neural network training: An analysis of the AlgoPerf competition
5. ICLR 2025Adaptive Transformer Programs: Bridging the Gap Between Performance and Interpretability in Transformers
6. ICLR 2025Agree to Disagree: Demystifying Homogeneous Deep Ensembles through Distributional Equivalence
7. ICLR 2025AI2TALE: An Innovative Information Theory-based Approach for Learning to Localize Phishing Attacks
8. ICLR 2025An Efficient Framework for Crediting Data Contributors of Diffusion Models
9. ICLR 2025Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions
10. ICLR 2025Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning
11. ICLR 2025Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count
12. ICLR 2025Arithmetic Without Algorithms: Language Models Solve Math with a Bag of Heuristics
13. ICLR 2025Ask, and it shall be given: On the Turing completeness of prompting
14. ICLR 2025Attention as a Hypernetwork
15. ICLR 2025Attention with Markov: A Curious Case of Single-layer Transformers
16. ICLR 2025AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution
17. ICLR 2025Attributing Culture-Conditioned Generations to Pretraining Corpora
18. ICLR 2025Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness
19. ICLR 2025Beyond Surface Structure: A Causal Assessment of LLMs' Comprehension ability
20. ICLR 2025Bilinear MLPs enable weight-based mechanistic interpretability
21. ICLR 2025Boosting Methods for Interval-censored Data with Regression and Classification
22. ICLR 2025Boosting the visual interpretability of CLIP via adversarial fine-tuning
23. ICLR 2025BrainOOD: Out-of-distribution Generalizable Brain Network Analysis
24. ICLR 2025Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization
25. ICLR 2025Can Transformers Do Enumerative Geometry?
26. ICLR 2025Capability Localization: Capabilities Can be Localized rather than Individual Knowledge
27. ICLR 2025Capturing the Temporal Dependence of Training Data Influence
28. ICLR 2025Causal Concept Graph Models: Beyond Causal Opacity in Deep Learning
29. ICLR 2025Comparing Targeting Strategies for Maximizing Social Welfare with Limited Resources
30. ICLR 2025Competition Dynamics Shape Algorithmic Phases of In-Context Learning
31. ICLR 2025Complementary Label Learning with Positive Label Guessing and Negative Label Enhancement
32. ICLR 2025Concept Bottleneck Large Language Models
33. ICLR 2025Controllable Context Sensitivity and the Knob Behind It
34. ICLR 2025Controlling Language and Diffusion Models by Transporting Activations
35. ICLR 2025Counterfactual Concept Bottleneck Models
36. ICLR 2025Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models
37. ICLR 2025Data Shapley in One Training Run
38. ICLR 2025Data-centric Prediction Explanation via Kernelized Stein Discrepancy
39. ICLR 2025Deep Networks Learn Features From Local Discontinuities in the Label Function
40. ICLR 2025DICE: Data Influence Cascade in Decentralized Learning
41. ICLR 2025Differentiable Rule Induction from Raw Sequence Inputs
42. ICLR 2025Differential learning kinetics govern the transition from memorization to generalization during in-context learning
43. ICLR 2025Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient
44. ICLR 2025Diverse Preference Learning for Capabilities and Alignment
45. ICLR 2025Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models
46. ICLR 2025Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?
47. ICLR 2025Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting
48. ICLR 2025Dynamic Assortment Selection and Pricing with Censored Preference Feedback
49. ICLR 2025Efficient and Accurate Explanation Estimation with Distribution Compression
50. ICLR 2025Efficient Dictionary Learning with Switch Sparse Autoencoders

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.