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 49 of 69

2401. NeurIPS 2025Sharp Analysis for KL-Regularized Contextual Bandits and RLHF
2402. NeurIPS 2025Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence
2403. NeurIPS 2025Shortcut Features as Top Eigenfunctions of NTK: A Linear Neural Network Case and More
2404. NeurIPS 2025Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lens
2405. NeurIPS 2025Simple and Effective Specialized Representations for Fair Classifiers
2406. NeurIPS 2025Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
2407. NeurIPS 2025SimWorld: An Open-ended Simulator for Agents in Physical and Social Worlds
2408. NeurIPS 2025Size-adaptive Hypothesis Testing for Fairness
2409. NeurIPS 2025Sketched Gaussian Mechanism for Private Federated Learning
2410. NeurIPS 2025Smoothed Differentiation Efficiently Mitigates Shattered Gradients in Explanations
2411. NeurIPS 2025SNEAKDOOR: Stealthy Backdoor Attacks against Distribution Matching-based Dataset Condensation
2412. NeurIPS 2025Solving Discrete (Semi) Unbalanced Optimal Transport with Equivalent Transformation Mechanism and KKT-Multiplier Regularization
2413. NeurIPS 2025SOMBRL: Scalable and Optimistic Model-Based RL
2414. NeurIPS 2025Some Optimizers are More Equal: Understanding the Role of Optimizers in Group Fairness
2415. NeurIPS 2025Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models
2416. NeurIPS 2025Spectral Conditioning of Attention Improves Transformer Performance
2417. NeurIPS 2025SpEx: A Spectral Approach to Explainable Clustering
2418. NeurIPS 2025Spike-timing-dependent Hebbian learning as noisy gradient descent
2419. NeurIPS 2025Spurious-Aware Prototype Refinement for Reliable Out-of-Distribution Detection
2420. NeurIPS 2025Stability and Sharper Risk Bounds with Convergence Rate $\tilde{O}(1/n^2)$
2421. NeurIPS 2025Stable Matching with Ties: Approximation Ratios and Learning
2422. NeurIPS 2025StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models
2423. NeurIPS 2025STEAD: Robust Provably Secure Linguistic Steganography with Diffusion Language Model
2424. NeurIPS 2025SteerConf: Steering LLMs for Confidence Elicitation
2425. NeurIPS 2025Steering Information Utility in Key-Value Memory for Language Model Post-Training
2426. NeurIPS 2025StegoZip: Enhancing Linguistic Steganography Payload in Practice with Large Language Models
2427. NeurIPS 2025STEP: A Unified Spiking Transformer Evaluation Platform for Fair and Reproducible Benchmarking
2428. NeurIPS 2025Stop DDoS Attacking the Research Community with AI-Generated Survey Papers
2429. NeurIPS 2025Strassen Attention, Split VC Dimension and Compositionality in Transformers
2430. NeurIPS 2025Strategic Classification with Non-Linear Classifiers
2431. NeurIPS 2025Strategic Cost Selection in Participatory Budgeting
2432. NeurIPS 2025Strategic Costs of Perceived Bias in Fair Selection
2433. NeurIPS 2025Strategic Hypothesis Testing
2434. NeurIPS 2025StyleGuard: Preventing Text-to-Image-Model-based Style Mimicry Attacks by Style Perturbations
2435. NeurIPS 2025Subgraph Federated Learning via Spectral Methods
2436. NeurIPS 2025Sum Estimation under Personalized Local Differential Privacy
2437. NeurIPS 2025Synergistic Tensor and Pipeline Parallelism
2438. NeurIPS 2025Synthesize Privacy-Preserving High-Resolution Images via Private Textual Intermediaries
2439. NeurIPS 2025System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts
2440. NeurIPS 2025Taming Hyperparameter Sensitivity in Data Attribution: Practical Selection Without Costly Retraining
2441. NeurIPS 2025Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
2442. NeurIPS 2025The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation
2443. NeurIPS 2025The Boundaries of Fair AI in Medical Image Prognosis: A Causal Perspective
2444. NeurIPS 2025The Complexity of Correlated Equilibria in Generalized Games
2445. NeurIPS 2025The Cost of Compression: Tight Quadratic Black-Box Attacks on Sketches for $\ell_2$ Norm Estimation
2446. NeurIPS 2025The emergence of sparse attention: impact of data distribution and benefits of repetition
2447. NeurIPS 2025The Fluorescent Veil: A Stealthy and Effective Physical Adversarial Patch Against Traffic Sign Recognition
2448. NeurIPS 2025The Future Unmarked: Watermark Removal in AI-Generated Images via Next-Frame Prediction
2449. NeurIPS 2025The Hawthorne Effect in Reasoning Models: Evaluating and Steering Test Awareness
2450. NeurIPS 2025The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?

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.