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

416 papers, page 6 of 9

251. NeurIPS 2026Optimal Rates for Adaptive Private $k$-PCA
252. NeurIPS 2026Optimal Rates for Differentially Private Hypothesis Testing with E-values
253. NeurIPS 2026Optimistic Dual Averaging Unifies Modern Optimizers
254. NeurIPS 2026Optimizer-Induced Mode Connectivity: From AdamW to Muon
255. NeurIPS 2026Optimizing Social Utility in Sequential Experiments
256. NeurIPS 2026Outbidding and Outbluffing Elite Humans: Mastering Liar’s Poker via Self-Play and Reinforcement Learning
257. NeurIPS 2026PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization
258. NeurIPS 2026Parasite Features: Causal Abstraction Through Spurious Pathways
259. NeurIPS 2026Participatory ML for Social Harm Should be Constructed, Validated and Reasoned Through First-Person Accounts
260. NeurIPS 2026PatchBench: Measuring Collateral Damage in Activation Patching
261. NeurIPS 2026Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning
262. NeurIPS 2026PDHFormer: Progressive Dual-Head Transformer for Behavioral Choice Prediction
263. NeurIPS 2026Per-Starting-Point Plausibility and Diversity Bounds for Score-Based Diffusion Models
264. NeurIPS 2026Persona Vectors: Monitoring and Controlling Character Traits in Language Models
265. NeurIPS 2026Persona-Model Collapse in Emergent Misalignment
266. NeurIPS 2026Plug-and-Play ADMM for Inverse Problems with Flow Matching Denoiser
267. NeurIPS 2026Pose-Free Feed-Forward 3D Inpainting via Learnable Mask Attention and Support Token Refinement
268. NeurIPS 2026Position-aware eXplanation: A Model-Agnostic Framework for Positional Attributions
269. NeurIPS 2026Position: Life-Logging Video Streams Make the Privacy–Utility Trade-off Inevitable
270. NeurIPS 2026Position: Machine Learning Conferences Should Introduce an Autonomous Research Track
271. NeurIPS 2026Position: Reconciling Open Access with Owner Control in AI Model Distribution Deserves More Research Effort
272. NeurIPS 2026Position: We Need Greater Transparency to Maintain Research Pipeline Reliability Despite GenAI
273. NeurIPS 2026Positional Encoding and Prompt-Order Sensitivity in In-Context Learning
274. NeurIPS 2026PP-Mark: Provable and Publicly Verifiable Watermarking for Generative AI
275. NeurIPS 2026Practical Estimation of the Bayes Optimal Fairness-Accuracy Tradeoff with Soft Labels
276. NeurIPS 2026Prediction-Intervention Games and Invariant Sets
277. NeurIPS 2026Predictive Concept Decoders: Training Scalable End-to-End Interpretability Assistants
278. NeurIPS 2026Prevailing Bisimulation Metric Learning Is Biased: Implicit Regularization and Its Remedy
279. NeurIPS 2026PRISM: Polarimetric Road-surface Intelligent Sensing and Measurement Dataset
280. NeurIPS 2026Privacy Amplification Persists under Unlimited Synthetic Data Release
281. NeurIPS 2026Privacy Risk Scales with Effective Dimension in Federated Learning
282. NeurIPS 2026PrivacySIM: Evaluating LLM Simulation of User Privacy Behavior
283. NeurIPS 2026Private Online Prediction from Experts with Small Losses
284. NeurIPS 2026PrivateSeal: Low-Sensitivity Latent Directions for Diffusion-Resilient User-Specific Watermarking
285. NeurIPS 2026PROACT-Agent: Progressive Runtime Oversight and Active Circuit-breaking for Real-Time Safety
286. NeurIPS 2026ProjKAN: Model Compression via KAN Projections to Bridge the Hypothesis and Capacity Gaps
287. NeurIPS 2026Prompts to Proxies: Emulating Human Preferences via a Compact LLM Ensemble
288. NeurIPS 2026Provable Explanations for Any-Order Neural Additive Models
289. NeurIPS 2026Proxy-Based Approximation of Shapley and Banzhaf Interactions
290. NeurIPS 2026quanda: An Interpretability Toolkit for Training Data Attribution Evaluation
291. NeurIPS 2026Rank-Constrained Adaptation for Reliable Real-World Performance
292. NeurIPS 2026Reaching a Consensus in Predictive Loops
293. NeurIPS 2026Reading the Finetuning Prior: Verbatim Content Recovery via Contrastive Decoding Diffing
294. NeurIPS 2026Recursively Trained Diffusion Models: Limiting Collapse Distribution and Spectral Characterization
295. NeurIPS 2026Register Anything Model for Generalizable and Robust Point Cloud Registration
296. NeurIPS 2026Reinforcement Learning for Exponential Utility: Algorithms and Convergence in Discounted MDPs
297. NeurIPS 2026Rep2Text: Decoding Full Text from a Single LLM Token Representation
298. NeurIPS 2026Representation Rigidity in Face Embeddings: Orthogonal Identifiability and Backfill-Free Compatibility
299. NeurIPS 2026Response Time Enhances Alignment with Heterogeneous Preferences
300. NeurIPS 2026Retain-Neutral Surrogates for Min-Max Unlearning

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.