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

3,411 papers, page 7 of 69

301. ICLR 2026Oversmoothing, "Oversquashing'', Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learning
302. ICLR 2026Paradigm Shift of GNN Explainer from Label Space to Prototypical Representation Space
303. ICLR 2026Path Channels and Plan Extension Kernels: a Mechanistic Description of Planning in a Sokoban RNN
304. ICLR 2026Patronus: Interpretable Diffusion Models with Prototypes
305. ICLR 2026PerFit: Exploring Personalization Shifts in Representation Space of LLMs
306. ICLR 2026PlantRSR: A New Plant Dataset and Method for Reference-based Super-Resolution
307. ICLR 2026Polynomial, trigonometric, and tropical activations
308. ICLR 2026PolySHAP: Extending KernelSHAP with Interaction-Informed Polynomial Regression
309. ICLR 2026Practical estimation of the optimal classification error with soft labels and calibration
310. ICLR 2026Precise and Interpretable Editing of Code Knowledge in Large Language Models
311. ICLR 2026Priors in time: Missing inductive biases for language model interpretability
312. ICLR 2026PRISM: Partial-label Relational Inference with Spatial and Spectral Cues
313. ICLR 2026PRISON: Unmasking the Criminal Potential of Large Language Models
314. ICLR 2026Probability Distributions Computed by Autoregressive Transformers
315. ICLR 2026ProtoTS: Learning Hierarchical Prototypes for Explainable Time Series Forecasting
316. ICLR 2026Provable Separations between Memorization and Generalization in Diffusion Models
317. ICLR 2026Provably Explaining Neural Additive Models
318. ICLR 2026Provably Tracking Equivalent Mechanistic Interpretations Across Neural Networks
319. ICLR 2026Random Spiking Neural Networks are Stable and Spectrally Simple
320. ICLR 2026Random-projection ensemble dimension reduction
321. ICLR 2026Reinforcement Learning Fine-Tuning Enhances Activation Intensity and Diversity in the Internal Circuitry of LLMs
322. ICLR 2026RepIt: Steering Language Models with Concept-Specific Refusal Vectors
323. ICLR 2026Rethinking Continual Learning with Progressive Neural Collapse
324. ICLR 2026Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity
325. ICLR 2026Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry
326. ICLR 2026Rethinking the Gold Standard: Why Discrete Curvature Fails to Fully Capture Over-squashing in GNNs?
327. ICLR 2026Reverse Distillation: Disentangling and Scaling Protein Language Model Representations
328. ICLR 2026Revisiting [CLS] and Patch Token Interaction in Vision Transformers
329. ICLR 2026Revisiting Confidence Calibration for Misclassification Detection in VLMs
330. ICLR 2026Risk Phase Transitions in Spiked Regression: Alignment Driven Benign and Catastrophic Overfitting
331. ICLR 2026Robust Training of Neural Networks at Arbitrary Precision and Sparsity
332. ICLR 2026SASFT: Sparse Autoencoder-guided Supervised Finetuning to Mitigate Unexpected Code-Switching in LLMs
333. ICLR 2026Scaling Reasoning Hop Exposes Weaknesses: Demystifying and Improving Hop Generalization in Large Language Models
334. ICLR 2026Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in VLMs
335. ICLR 2026Seesaw: Accelerating Training by Balancing Batch Size and Learning Rate Scheduling
336. ICLR 2026Self-Speculative Decoding Accelerates Lossless Inference in Any-Order and Any-Subset Autoregressive Models
337. ICLR 2026Semantic Regexes: Auto-Interpreting LLM Features with a Structured Language
338. ICLR 2026Signal in the Noise: Polysemantic Interference Transfers and Predicts Cross-Model Influence
339. ICLR 2026SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors
340. ICLR 2026SNAPHARD CONTRAST LEARNING
341. ICLR 2026Social Agents: Collective Intelligence Improves LLM Predictions
342. ICLR 2026Sparling: End-to-End Spatial Concept Learning via Extremely Sparse Activations
343. ICLR 2026Sparse Autoencoders Trained on the Same Data Learn Different Features
344. ICLR 2026Sparse CLIP: Co-Optimizing Interpretability and Performance in Contrastive Learning
345. ICLR 2026Spectral Bellman Method: Unifying Representation and Exploration in RL
346. ICLR 2026Spectrum Tuning: Post-Training for Distributional Coverage and In-Context Steerability
347. ICLR 2026Stackelberg Coupling of Online Representation Learning and Reinforcement Learning
348. ICLR 2026Steering Embedding Models with Geometric Rotation: Mapping Semantic Relationships Across Languages and Models
349. ICLR 2026Steering Evaluation-Aware Language Models To Act Like They Are Deployed
350. ICLR 2026Steering the Herd: A Framework for LLM-based Control of Social Learning

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.