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

643 papers, page 2 of 13

51. ICLR 2026Critical Confabulation: Can LLMs Hallucinate for Social Good?
52. ICLR 2026Cross-Modal Redundancy and the Geometry of Vision–Language Embeddings
53. ICLR 2026CUPID: A Plug-in Framework for Joint Aleatoric and Epistemic Uncertainty Estimation with a Single Model
54. ICLR 2026Debugging Concept Bottleneck Models through Removal and Retraining
55. ICLR 2026Decentralized Nonconvex Optimization under Heavy-Tailed Noise: Normalization and Optimal Convergence
56. ICLR 2026Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learning
57. ICLR 2026Deconstructing Positional Information: From Attention Logits to Training Biases
58. ICLR 2026Decoupling Positional and Symbolic Attention in Transformers
59. ICLR 2026Detecting and Mitigating Memorization in Diffusion Models through Anisotropy of the Log-Probability
60. ICLR 2026Deterministic Bounds and Random Estimates of Metric Tensors on Neuromanifolds
61. ICLR 2026Discovering and Steering Interpretable Concepts in Large Generative Music Models
62. ICLR 2026Dissecting Representation Misalignment in Contrastive Learning via Influence Function
63. ICLR 2026Does Higher Interpretability Imply Better Utility? A Pairwise Analysis on Sparse Autoencoders
64. ICLR 2026DR-GGAD: Dual Residual Centering for Mitigating Anomaly Non‑Discriminativity in Generalist Graph Anomaly Detection
65. ICLR 2026DTP: Delta-Guided Two Stage Pruning for Mamba-based Multimodal Large Language Models
66. ICLR 2026Efficient Testing for Correlation Clustering: Improved Algorithms and Optimal Bounds
67. ICLR 2026ELEPHANT: Measuring and understanding social sycophancy in LLMs
68. ICLR 2026ELViS: Efficient Visual Similarity from Local Descriptors that Generalizes Across Domains
69. ICLR 2026Emergent Misalignment is Easy, Narrow Misalignment is Hard
70. ICLR 2026Emotions Where Art Thou: Understanding and Characterizing the Emotional Latent Space of Large Language Models
71. ICLR 2026Enforcing Axioms for AI Alignment under Loss-Based Rules
72. ICLR 2026Entropic Confinement and Mode Connectivity in Overparameterized Neural Networks
73. ICLR 2026Escaping Low-Rank Traps: Interpretable Visual Concept Learning via Implicit Vector Quantization
74. ICLR 2026Evaluating Data Influence in Meta Learning
75. ICLR 2026Evaluating SAE interpretability without generating explanations
76. ICLR 2026Evaluating Text Creativity across Diverse Domains: a Dataset and Large Language Model Evaluator
77. ICLR 2026Every Language Model Has a Forgery-Resistant Signature
78. ICLR 2026Evolution and compression in LLMs: on the emergence of human-aligned categorization
79. ICLR 2026Evolution of Concepts in Language Model Pre-Training
80. ICLR 2026EXP-Bench: Can AI Conduct AI Research Experiments?
81. ICLR 2026Expert Heads: Robust Evidence Identification for Large Language Models
82. ICLR 2026Explainable Mixture Models through Differentiable Rule Learning
83. ICLR 2026Exploratory Causal Inference in SAEnce
84. ICLR 2026Exploring Interpretability for Visual Prompt Tuning with Cross-layer Concepts
85. ICLR 2026f-INE: A Hypothesis Testing Framework for Estimating Influence under Training Randomness
86. ICLR 2026Fair Policy Aggregation from Standard Policy Optimization
87. ICLR 2026Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions
88. ICLR 2026FAME: $\underline{F}$ormal $\underline{A}$bstract $\underline{M}$inimal $\underline{E}$xplanation for neural networks
89. ICLR 2026Fantastic Pretraining Optimizers and Where to Find Them
90. ICLR 2026Fast and Stable Riemannian Metrics on SPD Manifolds via Cholesky Product Geometry
91. ICLR 2026Feature segregation by signed weights in artificial vision systems and biological models
92. ICLR 2026Financial fraud collusion among generative AI agents in social networks
93. ICLR 2026First is Not Really Better Than Last: Evaluating Layer Choice and Aggregation Strategies in Language Model Data Influence Estimation
94. ICLR 2026Fixing the Broken Compass: Diagnosing and Improving Inference-Time Reward Modeling
95. ICLR 2026Flattery, Fluff, and Fog: Diagnosing and Mitigating Idiosyncratic Biases in Preference Models
96. ICLR 2026FlexHiNM-GP: Flexible Hierarchical Pruning via Region Allocation and Channel Permutation
97. ICLR 2026Flow Straight and Fast in Hilbert Space: Functional Rectified Flow
98. ICLR 2026Flow-Disentangled Feature Importance
99. ICLR 2026Formal Mechanistic Interpretability: Automated Circuit Discovery with Provable Guarantees
100. ICLR 2026FRABench and UFEval: Unified Fine-grained Evaluation with Task and Aspect Generalization

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.