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

211 papers, page 4 of 5

151. ICLR 2025Representational Similarity via Interpretable Visual Concepts
152. ICLR 2025Residual Connections and Normalization Can Provably Prevent Oversmoothing in GNNs
153. ICLR 2025Residual Stream Analysis with Multi-Layer SAEs
154. ICLR 2025Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words
155. ICLR 2025Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond
156. ICLR 2025Rethinking Self-Distillation: Label Averaging and Enhanced Soft Label Refinement with Partial Labels
157. ICLR 2025Rethinking Shapley Value for Negative Interactions in Non-convex Games
158. ICLR 2025Revealing and Mitigating Over-Attention in Knowledge Editing
159. ICLR 2025Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs)
160. ICLR 2025Revisiting In-context Learning Inference Circuit in Large Language Models
161. ICLR 2025Revisiting Mode Connectivity in Neural Networks with Bezier Surface
162. ICLR 2025Revisiting Zeroth-Order Optimization: Minimum-Variance Two-Point Estimators and Directionally Aligned Perturbations
163. ICLR 2025RGB-Event ISP: The Dataset and Benchmark
164. ICLR 2025Robust LLM safeguarding via refusal feature adversarial training
165. ICLR 2025Scalable Influence and Fact Tracing for Large Language Model Pretraining
166. ICLR 2025Scaling and evaluating sparse autoencoders
167. ICLR 2025Scaling Laws for Adversarial Attacks on Language Model Activations and Tokens
168. ICLR 2025Selective Induction Heads: How Transformers Select Causal Structures in Context
169. ICLR 2025Shared-AE: Automatic Identification of Shared Subspaces in High-dimensional Neural and Behavioral Activity
170. ICLR 2025Shedding Light on Time Series Classification using Interpretability Gated Networks
171. ICLR 2025SimXRD-4M: Big Simulated X-ray Diffraction Data and Crystal Symmetry Classification Benchmark
172. ICLR 2025Sketching for Convex and Nonconvex Regularized Least Squares with Sharp Guarantees
173. ICLR 2025Sparse Autoencoders Do Not Find Canonical Units of Analysis
174. ICLR 2025Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models
175. ICLR 2025Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
176. ICLR 2025Start Smart: Leveraging Gradients For Enhancing Mask-based XAI Methods
177. ICLR 2025Strength Estimation and Human-Like Strength Adjustment in Games
178. ICLR 2025Structuring Benchmark into Knowledge Graphs to Assist Large Language Models in Retrieving and Designing Models
179. ICLR 2025Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation
180. ICLR 2025Swing-by Dynamics in Concept Learning and Compositional Generalization
181. ICLR 2025Systematic Outliers in Large Language Models
182. ICLR 2025TGB-Seq Benchmark: Challenging Temporal GNNs with Complex Sequential Dynamics
183. ICLR 2025The Computational Complexity of Circuit Discovery for Inner Interpretability
184. ICLR 2025The Geometry of Categorical and Hierarchical Concepts in Large Language Models
185. ICLR 2025The Hidden Cost of Waiting for Accurate Predictions
186. ICLR 2025The Same but Different: Structural Similarities and Differences in Multilingual Language Modeling
187. ICLR 2025The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities
188. ICLR 2025Towards a Unified and Verified Understanding of Group-Operation Networks
189. ICLR 2025Towards Bridging Generalization and Expressivity of Graph Neural Networks
190. ICLR 2025Towards Calibrated Deep Clustering Network
191. ICLR 2025Towards Interpreting Visual Information Processing in Vision-Language Models
192. ICLR 2025Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control
193. ICLR 2025Towards Synergistic Path-based Explanations for Knowledge Graph Completion: Exploration and Evaluation
194. ICLR 2025Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It
195. ICLR 2025Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures
196. ICLR 2025Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity
197. ICLR 2025Trained Transformer Classifiers Generalize and Exhibit Benign Overfitting In-Context
198. ICLR 2025Transformer Block Coupling and its Correlation with Generalization in LLMs
199. ICLR 2025Transformer Encoder Satisfiability: Complexity and Impact on Formal Reasoning
200. ICLR 2025Transformers Learn Low Sensitivity Functions: Investigations and Implications

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.