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

541 papers, page 8 of 11

351. ICML 2026PEARL: Differentially Private and Entropy-Aware Regulated Language Generation
352. ICML 2026Peer-Preservation in Frontier Models
353. ICML 2026PersistBench: When Should Long-Term Memories Be Forgotten by LLMs?
354. ICML 2026PICACO: Pluralistic In-Context Value Alignment via Total Correlation Optimization
355. ICML 2026PINNfluence: Interpreting PINNs through Influence Functions
356. ICML 2026PlugGuard: A Streaming Safeguard for Large Models via Latent Dynamics-Guided Risk Detection
357. ICML 2026Pluralistic Leaderboards
358. ICML 2026Poison with Style: A Practical Poisoning Attack on Code Large Language Models
359. ICML 2026Policies Permitting LLM Use for Polishing Peer Reviews Are Currently Not Enforceable
360. ICML 2026PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding
361. ICML 2026Post-Training with Policy Gradients: Optimality and the Base Model Barrier
362. ICML 2026PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts
363. ICML 2026Predicting the Emergence of Induction Heads in Language Model Pretraining
364. ICML 2026Priority-Aware Shapley Value
365. ICML 2026Privacy Amplification in Differentially Private Zeroth-Order Optimization with Hidden States
366. ICML 2026Privacy-Aware Data Integration for Enhanced Quantile Inference under Heterogeneity
367. ICML 2026Privasis: Synthesizing the Largest "Public" Private Dataset from Scratch
368. ICML 2026Private Learning with Public Feature Conditioning
369. ICML 2026PrivGate: Steering Contextual Integrity in LLMs via Latent Space Geometry
370. ICML 2026Proactive Defense Benchmark against Deepfake Generation
371. ICML 2026Probing Cross-modal Information Hubs in Audio-Visual LLMs
372. ICML 2026Probing RLVR Training Instability through the Lens of Objective-Level Hacking
373. ICML 2026Prompt Injection as Role Confusion
374. ICML 2026Prototype-Grounded Concept Models for Verifiable Concept Alignment
375. ICML 2026Quadratically Regularized Optimal Transport: Localization Bounds and Affine Case Analysis
376. ICML 2026Quantifying and Optimizing Simplicity via Polynomial Representations
377. ICML 2026Quantifying Biases in LLM-as-a-Judge Evaluations
378. ICML 2026Quantifying LLM Attention-Head Stability: Implications for Circuit Universality
379. ICML 2026Quantifying the Salience of Geo-Cultural Values for Pluralistic Safety Alignment
380. ICML 2026Query Circuits: Explaining How Language Models Answer User Prompts
381. ICML 2026Query Lens: Interpreting Sparse Key-Value Features with Indirect Effects
382. ICML 2026Questioning the Coverage-Length Metric in Conformal Prediction: When Shorter Intervals Are Not Better
383. ICML 2026RAIGen: Rare Attribute Identification in Text-to-Image Generative Models
384. ICML 2026Rationality Measurement and Theory for Reinforcement Learning Agents
385. ICML 2026Reading Between the Tokens: Improving Preference Predictions through Mechanistic Forecasting
386. ICML 2026Real Data Lies: Unveiling and Closing the Quality Shortcut in Generalizable AI-Generated Video Detection
387. ICML 2026Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs
388. ICML 2026Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought
389. ICML 2026RECAST: Model Reconstruction via Counterfactual-Aware Wasserstein Geometry under Limited Data
390. ICML 2026RedVisor: Reasoning-Aware Prompt Injection Defense via Zero-Copy KV Cache Reuse
391. ICML 2026Reinforcement Learning with Verifiable Rewards: GRPO's Loss, Dynamics, and Success Amplification
392. ICML 2026RepetitionCurse: Measuring and Understanding Router Imbalance in Mixture-of-Experts LLMs under DoS Stress
393. ICML 2026Representational Curvature Modulates Behavioral Uncertainty in Large Language Models
394. ICML 2026Resilient Coresets and Clustering
395. ICML 2026Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity
396. ICML 2026Rethinking Forgery Attacks on Semantic Watermarks in Black-Box Settings: A Geometric Distortion Perspective
397. ICML 2026Revealing Long-context Potential of Attention Heads via Frequency Kernels
398. ICML 2026Reverse-Engineering Model Editing on Language Models
399. ICML 2026Revisiting Asymmetries in Black-box Link Stealing against Graph Neural Networks
400. ICML 2026Revisiting ML Training under Fully Homomorphic Encryption: Convergence Guarantees, Differential Privacy, and Efficient Algorithms

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.