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

1,357 papers, page 25 of 28

1201. NeurIPS 2026PatchBench: Measuring Collateral Damage in Activation Patching
1202. NeurIPS 2026Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning
1203. NeurIPS 2026PDHFormer: Progressive Dual-Head Transformer for Behavioral Choice Prediction
1204. NeurIPS 2026Per-Starting-Point Plausibility and Diversity Bounds for Score-Based Diffusion Models
1205. NeurIPS 2026Persona Vectors: Monitoring and Controlling Character Traits in Language Models
1206. NeurIPS 2026Persona-Model Collapse in Emergent Misalignment
1207. NeurIPS 2026Plug-and-Play ADMM for Inverse Problems with Flow Matching Denoiser
1208. NeurIPS 2026Pose-Free Feed-Forward 3D Inpainting via Learnable Mask Attention and Support Token Refinement
1209. NeurIPS 2026Position-aware eXplanation: A Model-Agnostic Framework for Positional Attributions
1210. NeurIPS 2026Position: Life-Logging Video Streams Make the Privacy–Utility Trade-off Inevitable
1211. NeurIPS 2026Position: Machine Learning Conferences Should Introduce an Autonomous Research Track
1212. NeurIPS 2026Position: Reconciling Open Access with Owner Control in AI Model Distribution Deserves More Research Effort
1213. NeurIPS 2026Position: We Need Greater Transparency to Maintain Research Pipeline Reliability Despite GenAI
1214. NeurIPS 2026Positional Encoding and Prompt-Order Sensitivity in In-Context Learning
1215. NeurIPS 2026PP-Mark: Provable and Publicly Verifiable Watermarking for Generative AI
1216. NeurIPS 2026Practical Estimation of the Bayes Optimal Fairness-Accuracy Tradeoff with Soft Labels
1217. NeurIPS 2026Prediction-Intervention Games and Invariant Sets
1218. NeurIPS 2026Predictive Concept Decoders: Training Scalable End-to-End Interpretability Assistants
1219. NeurIPS 2026Prevailing Bisimulation Metric Learning Is Biased: Implicit Regularization and Its Remedy
1220. NeurIPS 2026PRISM: Polarimetric Road-surface Intelligent Sensing and Measurement Dataset
1221. NeurIPS 2026Privacy Amplification Persists under Unlimited Synthetic Data Release
1222. NeurIPS 2026Privacy Risk Scales with Effective Dimension in Federated Learning
1223. NeurIPS 2026PrivacySIM: Evaluating LLM Simulation of User Privacy Behavior
1224. NeurIPS 2026Private Online Prediction from Experts with Small Losses
1225. NeurIPS 2026PrivateSeal: Low-Sensitivity Latent Directions for Diffusion-Resilient User-Specific Watermarking
1226. NeurIPS 2026PROACT-Agent: Progressive Runtime Oversight and Active Circuit-breaking for Real-Time Safety
1227. NeurIPS 2026ProjKAN: Model Compression via KAN Projections to Bridge the Hypothesis and Capacity Gaps
1228. NeurIPS 2026Prompts to Proxies: Emulating Human Preferences via a Compact LLM Ensemble
1229. NeurIPS 2026Provable Explanations for Any-Order Neural Additive Models
1230. NeurIPS 2026Proxy-Based Approximation of Shapley and Banzhaf Interactions
1231. NeurIPS 2026quanda: An Interpretability Toolkit for Training Data Attribution Evaluation
1232. NeurIPS 2026Rank-Constrained Adaptation for Reliable Real-World Performance
1233. NeurIPS 2026Reaching a Consensus in Predictive Loops
1234. NeurIPS 2026Reading the Finetuning Prior: Verbatim Content Recovery via Contrastive Decoding Diffing
1235. NeurIPS 2026Recursively Trained Diffusion Models: Limiting Collapse Distribution and Spectral Characterization
1236. NeurIPS 2026Register Anything Model for Generalizable and Robust Point Cloud Registration
1237. NeurIPS 2026Reinforcement Learning for Exponential Utility: Algorithms and Convergence in Discounted MDPs
1238. NeurIPS 2026Rep2Text: Decoding Full Text from a Single LLM Token Representation
1239. NeurIPS 2026Representation Rigidity in Face Embeddings: Orthogonal Identifiability and Backfill-Free Compatibility
1240. NeurIPS 2026Response Time Enhances Alignment with Heterogeneous Preferences
1241. NeurIPS 2026Retain-Neutral Surrogates for Min-Max Unlearning
1242. NeurIPS 2026Rethinking Sequential Locate-Then-Edit: Optimality and Stability
1243. NeurIPS 2026Rethinking XAI Evaluation: A Human-Centered Audit of Shapley Benchmarks in High-Stakes Settings
1244. NeurIPS 2026Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic Saliency
1245. NeurIPS 2026Revisiting Incremental Learning: A Three-Interface Diagnosis of Stability and Plasticity
1246. NeurIPS 2026Revisiting Subgradient Dominance in Robust MDPs: Counterexamples, Hardness, and Sufficient Conditions
1247. NeurIPS 2026Revisiting Value Iteration: Unified Analysis of Discounted and Average-Reward Cases
1248. NeurIPS 2026Risks Create a Jagged Frontier of LLM Productivity Gains Across Computer Occupations
1249. NeurIPS 2026Robust and Efficient Continual Model Merging via Global Singular Subspace Separation and Restoration
1250. NeurIPS 2026Robust and Scalable Collaborative Learning via Pull-Based Epidemic Communication

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.