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

1,124 papers, page 7 of 23

301. ICML 2026Low-Rank and Sparsity Are All You Need: Exploring Robust Hierarchical Latent Subspaces for Transferable Adversarial Attack
302. ICML 2026MAD: Manifold Attracted Diffusion
303. ICML 2026MADA-Attack: Transferable Multi-modal Attention Distraction Adversarial Attack against Vision Language Models
304. ICML 2026Making Models Unmergeable via Scaling-Sensitive Loss Landscape
305. ICML 2026MAnchors: Memorization-Based Acceleration of Anchors via Rule Reuse and Transformation
306. ICML 2026Mechanisms of Introspective Awareness
307. ICML 2026Mechanistic Anomaly Detection via Functional Attribution
308. ICML 2026Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units
309. ICML 2026Mechanistic Interpretability as Statistical Estimation: A Variance Analysis
310. ICML 2026MemIncept: Steering LLM Agents via Cooperative Stealthy Memory Injections
311. ICML 2026MetaOthello: A Controlled Study of Multiple World Models in Transformers
312. ICML 2026MINIM: Privacy-Aware Minimal View for Agents via Trusted Local Sanitization
313. ICML 2026Mitigating Visual Hallucinations via Semantic Curriculum Preference Optimization in MLLMs
314. ICML 2026Mixture of Concept Bottleneck Experts
315. ICML 2026MoCo-EA: Exploiting Adversarial Mode Connectivity for Efficient Evolutionary Attacks
316. ICML 2026Monitoring Monitorability
317. ICML 2026More Edits, More Stable: Understanding the Lifelong Normalization in Sequential Model Editing
318. ICML 2026Multi-agent imitation learning with function approximation: linear Markov games and beyond
319. ICML 2026Multi-scale Explainer for Graph Neural Networks
320. ICML 2026MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
321. ICML 2026Multilingual Unlearning in LLMs: Transfer, Dynamics, and Reversibility
322. ICML 2026Near-Optimal Private Linear Regression via Iterative Hessian Mixing
323. ICML 2026Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings
324. ICML 2026Neural Vector Lyapunov–Razumikhin Certificates for Delayed Interconnected Systems
325. ICML 2026Next-Gen CAPTCHAs: Leveraging the Cognitive Gap for Scalable and Diverse GUI-Agent Defense
326. ICML 2026Next-Token Prediction and Regret Minimization
327. ICML 2026Noise as a Natural Regularizer in Markov Decision Processes: Connecting Environmental Stochasticity and Policy Simplicity
328. ICML 2026OC-space: a Unifying Perspective on Verification of Tree Ensembles
329. ICML 2026Old Habits Die Hard: How Conversational History Geometrically Traps LLMs
330. ICML 2026OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization
331. ICML 2026OmniVL-Guard: Towards Unified Vision-Language Forgery Detection and Grounding via Balanced RL
332. ICML 2026On the Accuracy of Newton Step and Influence Function Data Attributions
333. ICML 2026On the Epistemic Uncertainty of Overparametrized Neural Networks
334. ICML 2026On the Relationship Between Activation Outliers and Feature Death in Sparse Autoencoders
335. ICML 2026One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models
336. ICML 2026One Probe Won’t Catch Them All: Towards Targeted Deception Detection
337. ICML 2026Online Packet Scheduling with Deadlines and Learning
338. ICML 2026Online Social Welfare Function-based Resource Allocation
339. ICML 2026Optimal and Scalable MAPF via Multi-Marginal Optimal Transport and Schrödinger Bridges
340. ICML 2026Optimal Fair Aggregation of Crowdsourced Noisy Labels using Demographic Parity Constraints
341. ICML 2026Optimal Regularization for Performative Learning
342. ICML 2026Optimal structure learning and conditional independence testing
343. ICML 2026Optimal Transport Group Counterfactual Explanations
344. ICML 2026OrchJail: Jailbreaking Tool-Calling Text-to-Image Agents by Orchestration-Guided Fuzzing
345. ICML 2026Orthogonal Concept Erasure for Diffusion Models
346. ICML 2026OSCS: Online Selection with Provable FAR Control for LLM Safety
347. ICML 2026OSNIP: Balancing the Privacy-Utility-Efficiency Trilemma in LLM Inference via Obfuscated Semantic Null Space
348. ICML 2026Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning
349. ICML 2026Partial Identification under High-Dimensional Potential Outcomes and Confounders via Optimal Transport
350. ICML 2026Patterning: The Dual of 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.