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

643 papers, page 5 of 13

201. ICLR 2026Practical estimation of the optimal classification error with soft labels and calibration
202. ICLR 2026Precise and Interpretable Editing of Code Knowledge in Large Language Models
203. ICLR 2026Priors in time: Missing inductive biases for language model interpretability
204. ICLR 2026PRISM: Partial-label Relational Inference with Spatial and Spectral Cues
205. ICLR 2026PRISON: Unmasking the Criminal Potential of Large Language Models
206. ICLR 2026Probability Distributions Computed by Autoregressive Transformers
207. ICLR 2026ProtoTS: Learning Hierarchical Prototypes for Explainable Time Series Forecasting
208. ICLR 2026Provable Separations between Memorization and Generalization in Diffusion Models
209. ICLR 2026Provably Explaining Neural Additive Models
210. ICLR 2026Provably Tracking Equivalent Mechanistic Interpretations Across Neural Networks
211. ICLR 2026Random Spiking Neural Networks are Stable and Spectrally Simple
212. ICLR 2026Random-projection ensemble dimension reduction
213. ICLR 2026Reinforcement Learning Fine-Tuning Enhances Activation Intensity and Diversity in the Internal Circuitry of LLMs
214. ICLR 2026RepIt: Steering Language Models with Concept-Specific Refusal Vectors
215. ICLR 2026Rethinking Continual Learning with Progressive Neural Collapse
216. ICLR 2026Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity
217. ICLR 2026Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry
218. ICLR 2026Rethinking the Gold Standard: Why Discrete Curvature Fails to Fully Capture Over-squashing in GNNs?
219. ICLR 2026Reverse Distillation: Disentangling and Scaling Protein Language Model Representations
220. ICLR 2026Revisiting [CLS] and Patch Token Interaction in Vision Transformers
221. ICLR 2026Revisiting Confidence Calibration for Misclassification Detection in VLMs
222. ICLR 2026Risk Phase Transitions in Spiked Regression: Alignment Driven Benign and Catastrophic Overfitting
223. ICLR 2026Robust Training of Neural Networks at Arbitrary Precision and Sparsity
224. ICLR 2026SASFT: Sparse Autoencoder-guided Supervised Finetuning to Mitigate Unexpected Code-Switching in LLMs
225. ICLR 2026Scaling Reasoning Hop Exposes Weaknesses: Demystifying and Improving Hop Generalization in Large Language Models
226. ICLR 2026Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in VLMs
227. ICLR 2026Seesaw: Accelerating Training by Balancing Batch Size and Learning Rate Scheduling
228. ICLR 2026Self-Speculative Decoding Accelerates Lossless Inference in Any-Order and Any-Subset Autoregressive Models
229. ICLR 2026Semantic Regexes: Auto-Interpreting LLM Features with a Structured Language
230. ICLR 2026Signal in the Noise: Polysemantic Interference Transfers and Predicts Cross-Model Influence
231. ICLR 2026SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors
232. ICLR 2026SNAPHARD CONTRAST LEARNING
233. ICLR 2026Social Agents: Collective Intelligence Improves LLM Predictions
234. ICLR 2026Sparling: End-to-End Spatial Concept Learning via Extremely Sparse Activations
235. ICLR 2026Sparse Autoencoders Trained on the Same Data Learn Different Features
236. ICLR 2026Sparse CLIP: Co-Optimizing Interpretability and Performance in Contrastive Learning
237. ICLR 2026Spectral Bellman Method: Unifying Representation and Exploration in RL
238. ICLR 2026Spectrum Tuning: Post-Training for Distributional Coverage and In-Context Steerability
239. ICLR 2026Stackelberg Coupling of Online Representation Learning and Reinforcement Learning
240. ICLR 2026Steering Embedding Models with Geometric Rotation: Mapping Semantic Relationships Across Languages and Models
241. ICLR 2026Steering Evaluation-Aware Language Models To Act Like They Are Deployed
242. ICLR 2026Steering the Herd: A Framework for LLM-based Control of Social Learning
243. ICLR 2026Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs
244. ICLR 2026Structural Inference: Interpreting Small Language Models with Susceptibilities
245. ICLR 2026Subquadratic Algorithms and Hardness for Attention with Any Temperature
246. ICLR 2026Tackling the XAI Disagreement Problem with Adaptive Feature Grouping
247. ICLR 2026Task Vectors, Learned Not Extracted: Performance Gains and Mechanistic Insights
248. ICLR 2026Temporal Concept Dynamics in Diffusion Models via Prompt-Conditioned Interventions
249. ICLR 2026Temporal Generalization: A Reality Check
250. ICLR 2026Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for 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.