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 9 of 12

401. NeurIPS 2024Divergences between Language Models and Human Brains
402. NeurIPS 2024Do LLMs dream of elephants (when told not to)? Latent concept association and associative memory in transformers
403. NeurIPS 2024Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning
404. NeurIPS 2024DU-Shapley: A Shapley Value Proxy for Efficient Dataset Valuation
405. NeurIPS 2024Dynamic Service Fee Pricing under Strategic Behavior: Actions as Instruments and Phase Transition
406. NeurIPS 2024EEVR: A Virtual Reality-Based Emotion Dataset Featuring Paired Physiological Signals and Textual Descriptions
407. NeurIPS 2024Efficient Sketches for Training Data Attribution and Studying the Loss Landscape
408. NeurIPS 2024Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space
409. NeurIPS 2024emg2pose: A Large and Diverse Benchmark for Surface Electromyographic Hand Pose Estimation
410. NeurIPS 2024Enhancing Semi-Supervised Learning via Representative and Diverse Sample Selection
411. NeurIPS 2024Evidence of Learned Look-Ahead in a Chess-Playing Neural Network
412. NeurIPS 2024Expectile Regularization for Fast and Accurate Training of Neural Optimal Transport
413. NeurIPS 2024Explanations that reveal all through the definition of encoding
414. NeurIPS 2024Exploring and Exploiting the Asymmetric Valley of Deep Neural Networks
415. NeurIPS 2024Fairness in Social Influence Maximization via Optimal Transport
416. NeurIPS 2024FastSurvival: Hidden Computational Blessings in Training Cox Proportional Hazards Models
417. NeurIPS 2024FFAM: Feature Factorization Activation Map for Explanation of 3D Detectors
418. NeurIPS 2024Finding Transformer Circuits With Edge Pruning
419. NeurIPS 2024Graph Neural Networks and Arithmetic Circuits
420. NeurIPS 2024Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models
421. NeurIPS 2024Great Minds Think Alike: The Universal Convergence Trend of Input Salience
422. NeurIPS 2024GREATS: Online Selection of High-Quality Data for LLM Training in Every Iteration
423. NeurIPS 2024Grokking of Implicit Reasoning in Transformers: A Mechanistic Journey to the Edge of Generalization
424. NeurIPS 2024HyperLogic: Enhancing Diversity and Accuracy in Rule Learning with HyperNets
425. NeurIPS 2024Hypothesis Testing the Circuit Hypothesis in LLMs
426. NeurIPS 2024Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
427. NeurIPS 2024Improving Decision Sparsity
428. NeurIPS 2024Improving Sparse Decomposition of Language Model Activations with Gated Sparse Autoencoders
429. NeurIPS 2024In-Context Learning State Vector with Inner and Momentum Optimization
430. NeurIPS 2024Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models
431. NeurIPS 2024Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing
432. NeurIPS 2024Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models
433. NeurIPS 2024Integrating GNN and Neural ODEs for Estimating Non-Reciprocal Two-Body Interactions in Mixed-Species Collective Motion
434. NeurIPS 2024InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques
435. NeurIPS 2024Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents
436. NeurIPS 2024Interpretable Concept-Based Memory Reasoning
437. NeurIPS 2024Interpretable Generalized Additive Models for Datasets with Missing Values
438. NeurIPS 2024Interpretable Image Classification with Adaptive Prototype-based Vision Transformers
439. NeurIPS 2024Interpretable Mesomorphic Networks for Tabular Data
440. NeurIPS 2024Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge
441. NeurIPS 2024Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)
442. NeurIPS 2024Interpreting Learned Feedback Patterns in Large Language Models
443. NeurIPS 2024Intervention and Conditioning in Causal Bayesian Networks
444. NeurIPS 2024InversionView: A General-Purpose Method for Reading Information from Neural Activations
445. NeurIPS 2024Is the MMI Criterion Necessary for Interpretability? Degenerating Non-causal Features to Plain Noise for Self-Rationalization
446. NeurIPS 2024Iteration Head: A Mechanistic Study of Chain-of-Thought
447. NeurIPS 2024Language Model as Visual Explainer
448. NeurIPS 2024Learnability of high-dimensional targets by two-parameter models and gradient flow
449. NeurIPS 2024Learning Cortico-Muscular Dependence through Orthonormal Decomposition of Density Ratios
450. NeurIPS 2024Learning from higher-order correlations, efficiently: hypothesis tests, random features, and neural networks

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.