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

589 papers, page 11 of 12

501. NeurIPS 2024Provable Benefit of Cutout and CutMix for Feature Learning
502. NeurIPS 2024Provable Tempered Overfitting of Minimal Nets and Typical Nets
503. NeurIPS 2024QTIP: Quantization with Trellises and Incoherence Processing
504. NeurIPS 2024Quality-Improved and Property-Preserved Polarimetric Imaging via Complementarily Fusing
505. NeurIPS 2024QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
506. NeurIPS 2024Questioning the Survey Responses of Large Language Models
507. NeurIPS 2024RashomonGB: Analyzing the Rashomon Effect and Mitigating Predictive Multiplicity in Gradient Boosting
508. NeurIPS 2024Realizable $H$-Consistent and Bayes-Consistent Loss Functions for Learning to Defer
509. NeurIPS 2024ReFT: Representation Finetuning for Language Models
510. NeurIPS 2024Refusal in Language Models Is Mediated by a Single Direction
511. NeurIPS 2024RegExplainer: Generating Explanations for Graph Neural Networks in Regression Tasks
512. NeurIPS 2024Relational Concept Bottleneck Models
513. NeurIPS 2024Replicability in Learning: Geometric Partitions and KKM-Sperner Lemma
514. NeurIPS 2024Reproducibility study of "Robust Fair Clustering: A Novel Fairness Attack and Defense Framework"
515. NeurIPS 2024Reproducibility Study of "Robust Fair Clustering: A Novel Fairness Attack and Defense Framework"
516. NeurIPS 2024Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspective
517. NeurIPS 2024Revisiting K-mer Profile for Effective and Scalable Genome Representation Learning
518. NeurIPS 2024Robust group and simultaneous inferences for high-dimensional single index model
519. NeurIPS 2024Safe Exploitative Play with Untrusted Type Beliefs
520. NeurIPS 2024SCAFFLSA: Taming Heterogeneity in Federated Linear Stochastic Approximation and TD Learning
521. NeurIPS 2024Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations
522. NeurIPS 2024Selective Explanations
523. NeurIPS 2024Semantics and Spatiality of Emergent Communication
524. NeurIPS 2024Semi-Discrete Optimal Transport: Nearly Minimax Estimation With Stochastic Gradient Descent and Adaptive Entropic Regularization
525. NeurIPS 2024Separation and Bias of Deep Equilibrium Models on Expressivity and Learning Dynamics
526. NeurIPS 2024Separations in the Representational Capabilities of Transformers and Recurrent Architectures
527. NeurIPS 2024Sequoia: Scalable and Robust Speculative Decoding
528. NeurIPS 2024SETBENCH: Assessing the Analytical and Semantic Robustness of Language Models
529. NeurIPS 2024Soft ascent-descent as a stable and flexible alternative to flooding
530. NeurIPS 2024SpeedLoader: An I/O efficient scheme for heterogeneous and distributed LLM operation
531. NeurIPS 2024Stability and Generalization of Asynchronous SGD: Sharper Bounds Beyond Lipschitz and Smoothness
532. NeurIPS 2024Statistical and Geometrical properties of the Kernel Kullback-Leibler divergence
533. NeurIPS 2024STL: Still Tricky Logic (for System Validation, Even When Showing Your Work)
534. NeurIPS 2024Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution
535. NeurIPS 2024Stochastic Concept Bottleneck Models
536. NeurIPS 2024Stochastic Optimal Control and Estimation with Multiplicative and Internal Noise
537. NeurIPS 2024Studying How to Efficiently and Effectively Guide Models with Explanations - A Reproducibility Study
538. NeurIPS 2024Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling
539. NeurIPS 2024Symmetry Discovery Beyond Affine Transformations
540. NeurIPS 2024Talking Heads: Understanding Inter-Layer Communication in Transformer Language Models
541. NeurIPS 2024Taming Heavy-Tailed Losses in Adversarial Bandits and the Best-of-Both-Worlds Setting
542. NeurIPS 2024Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization
543. NeurIPS 2024TEG-DB: A Comprehensive Dataset and Benchmark of Textual-Edge Graphs
544. NeurIPS 2024Test Where Decisions Matter: Importance-driven Testing for Deep Reinforcement Learning
545. NeurIPS 2024Test-Time Dynamic Image Fusion
546. NeurIPS 2024Testing Calibration in Nearly-Linear Time
547. NeurIPS 2024Testing Semantic Importance via Betting
548. NeurIPS 2024The Closeness of In-Context Learning and Weight Shifting for Softmax Regression
549. NeurIPS 2024The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More
550. NeurIPS 2024The Intelligible and Effective Graph Neural Additive Network

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.