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

522 papers, page 8 of 11

351. NeurIPS 2025Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry
352. NeurIPS 2025ProtoPairNet: Interpretable Regression through Prototypical Pair Reasoning
353. NeurIPS 2025Provable Gradient Editing of Deep Neural Networks
354. NeurIPS 2025Proxy-SPEX: Sample-Efficient Interpretability via Sparse Feature Interactions in LLMs
355. NeurIPS 2025Purifying Approximate Differential Privacy with Randomized Post-processing
356. NeurIPS 2025Quantifying Cross-Modality Memorization in Vision-Language Models
357. NeurIPS 2025Query-Efficient Locally Private Hypothesis Selection via the Scheffe Graph
358. NeurIPS 2025Randomized-MLP Regularization Improves Domain Adaptation and Interpretability in DINOv2
359. NeurIPS 2025Reasoning Models Sometimes Output Illegible Chains of Thought
360. NeurIPS 2025Rectifying Shortcut Behaviors in Preference-based Reward Learning
361. NeurIPS 2025Redefining Experts: Interpretable Decomposition of Language Models for Toxicity Mitigation
362. NeurIPS 2025Regional Explanations: Bridging Local and Global Variable Importance
363. NeurIPS 2025Regression Trees Know Calculus
364. NeurIPS 2025Regression-adjusted Monte Carlo Estimators for Shapley Values and Probabilistic Values
365. NeurIPS 2025Removing Concepts from Text-to-Image Models with Only Negative Samples
366. NeurIPS 2025Replicable Online pricing
367. NeurIPS 2025Representational Difference Explanations
368. NeurIPS 2025Rescaled Influence Functions: Accurate Data Attribution in High Dimension
369. NeurIPS 2025Residual Stream Analysis of Overfitting And Structural Disruptions
370. NeurIPS 2025Rethinking Circuit Completeness in Language Models: AND, OR, and ADDER Gates
371. NeurIPS 2025Rethinking Fair Federated Learning from Parameter and Client View
372. NeurIPS 2025Rethinking Gradient Step Denoiser: Towards Truly Pseudo-Contractive Operator
373. NeurIPS 2025Rethinking the Role of Verbatim Memorization in LLM Privacy
374. NeurIPS 2025Revising and Falsifying Sparse Autoencoder Feature Explanations
375. NeurIPS 2025Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability
376. NeurIPS 2025Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions
377. NeurIPS 2025Ridge Boosting is Both Robust and Efficient
378. NeurIPS 2025Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor
379. NeurIPS 2025Robust and Scalable Autonomous Reinforcement Learning in Irreversible Environments
380. NeurIPS 2025Robust Distributed Estimation: Extending Gossip Algorithms to Ranking and Trimmed Means
381. NeurIPS 2025Robust Explanations of Graph Neural Networks via Graph Curvatures
382. NeurIPS 2025Robust Integrated Learning and Pauli Noise Mitigation for Parametrized Quantum Circuits
383. NeurIPS 2025Robust SuperAlignment: Weak-to-Strong Robustness Generalization for Vision-Language Models
384. NeurIPS 2025RUAGO: Effective and Practical Retain-Free Unlearning via Adversarial Attack and OOD Generator
385. NeurIPS 2025SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders
386. NeurIPS 2025Safety Depth in Large Language Models: A Markov Chain Perspective
387. NeurIPS 2025SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification
388. NeurIPS 2025Sample-efficient Learning of Concepts with Theoretical Guarantees: from Data to Concepts without Interventions
389. NeurIPS 2025Scalable Fingerprinting of Large Language Models
390. NeurIPS 2025Scalable Neural Network Geometric Robustness Validation via Hölder Optimisation
391. NeurIPS 2025Scalable Valuation of Human Feedback through Provably Robust Model Alignment
392. NeurIPS 2025SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations
393. NeurIPS 2025Second-Order Convergence in Private Stochastic Non-Convex Optimization
394. NeurIPS 2025Secure and Confidential Certificates of Online Fairness
395. NeurIPS 2025Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition
396. NeurIPS 2025Selective Omniprediction and Fair Abstention
397. NeurIPS 2025Semantic Representation Attack against Aligned Large Language Models
398. NeurIPS 2025Sequentially Auditing Differential Privacy
399. NeurIPS 2025SHAP Meets Tensor Networks: Provably Tractable Explanations with Parallelism
400. NeurIPS 2025SHAP values via sparse Fourier representation

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.