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

1,124 papers, page 12 of 23

551. ICML 2025A Parameter-Free and Near-Optimal Zeroth-Order Algorithm for Stochastic Convex Optimization
552. ICML 2025A Unified Approach to Routing and Cascading for LLMs
553. ICML 2025A Versatile Influence Function for Data Attribution with Non-Decomposable Loss
554. ICML 2025Accelerating Spectral Clustering under Fairness Constraints
555. ICML 2025Accurate Identification of Communication Between Multiple Interacting Neural Populations
556. ICML 2025Activation Space Interventions Can Be Transferred Between Large Language Models
557. ICML 2025Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization
558. ICML 2025Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets
559. ICML 2025Adversarial Inception Backdoor Attacks against Reinforcement Learning
560. ICML 2025Adversaries Can Misuse Combinations of Safe Models
561. ICML 2025Algorithmic Recourse for Long-Term Improvement
562. ICML 2025An analytic theory of creativity in convolutional diffusion models
563. ICML 2025An Efficient Private GPT Never Autoregressively Decodes
564. ICML 2025An End-to-End Model for Logits-Based Large Language Models Watermarking
565. ICML 2025Analyze Feature Flow to Enhance Interpretation and Steering in Language Models
566. ICML 2025Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning Attack
567. ICML 2025Approximate Differential Privacy of the $\ell_2$ Mechanism
568. ICML 2025Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models
569. ICML 2025Are Sparse Autoencoders Useful? A Case Study in Sparse Probing
570. ICML 2025Attributes Shape the Embedding Space of Face Recognition Models
571. ICML 2025Auditing $f$-differential privacy in one run
572. ICML 2025Auditing Prompt Caching in Language Model APIs
573. ICML 2025AutoAdvExBench: Benchmarking Autonomous Exploitation of Adversarial Example Defenses
574. ICML 2025Automatically Interpreting Millions of Features in Large Language Models
575. ICML 2025Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts
576. ICML 2025AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
577. ICML 2025B-score: Detecting biases in large language models using response history
578. ICML 2025BaxBench: Can LLMs Generate Correct and Secure Backends?
579. ICML 2025Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence
580. ICML 2025Beyond Log-Concavity and Score Regularity: Improved Convergence Bounds for Score-Based Generative Models in W2-distance
581. ICML 2025Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspective
582. ICML 2025BiMark: Unbiased Multilayer Watermarking for Large Language Models
583. ICML 2025Black-Box Adversarial Attacks on LLM-Based Code Completion
584. ICML 2025BOPO: Neural Combinatorial Optimization via Best-anchored and Objective-guided Preference Optimization
585. ICML 2025Breaking the $n^{1.5}$ Additive Error Barrier for Private and Efficient Graph Sparsification via Private Expander Decomposition
586. ICML 2025Breaking the Quadratic Barrier: Robust Cardinality Sketches for Adaptive Queries
587. ICML 2025Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging
588. ICML 2025Byzantine-Resilient Federated Alternating Gradient Descent and Minimization for Partly-Decoupled Low Rank Matrix Learning
589. ICML 2025Calibrated Language Models and How to Find Them with Label Smoothing
590. ICML 2025CAN: Leveraging Clients As Navigators for Generative Replay in Federated Continual Learning
591. ICML 2025Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs
592. ICML 2025Cape: Context-Aware Prompt Perturbation Mechanism with Differential Privacy
593. ICML 2025CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models
594. ICML 2025Categorical Distributional Reinforcement Learning with Kullback-Leibler Divergence: Convergence and Asymptotics
595. ICML 2025Categorical Schrödinger Bridge Matching
596. ICML 2025Certification for Differentially Private Prediction in Gradient-Based Training
597. ICML 2025Certified Unlearning for Neural Networks
598. ICML 2025Circumventing Backdoor Space via Weight Symmetry
599. ICML 2025Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off
600. ICML 2025Clone-Robust AI Alignment

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.