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

589 papers, page 4 of 12

151. ICLR 2024Piecewise Linear Parametrization of Policies: Towards Interpretable Deep Reinforcement Learning
152. ICLR 2024Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior Models
153. ICLR 2024PRIME: Prioritizing Interpretability in Failure Mode Extraction
154. ICLR 2024Quantifying the Plausibility of Context Reliance in Neural Machine Translation
155. ICLR 2024Reconciling Spatial and Temporal Abstractions for Goal Representation
156. ICLR 2024Respect the model: Fine-grained and Robust Explanation with Sharing Ratio Decomposition
157. ICLR 2024Role of Locality and Weight Sharing in Image-Based Tasks: A Sample Complexity Separation between CNNs, LCNs, and FCNs
158. ICLR 2024Simplicial Representation Learning with Neural $k$-Forms
159. ICLR 2024Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative Community
160. ICLR 2024Social-Transmotion: Promptable Human Trajectory Prediction
161. ICLR 2024Some Fundamental Aspects about Lipschitz Continuity of Neural Networks
162. ICLR 2024SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents
163. ICLR 2024Sparse Autoencoders Find Highly Interpretable Features in Language Models
164. ICLR 2024Stochastic Modified Equations and Dynamics of Dropout Algorithm
165. ICLR 2024Subtractive Mixture Models via Squaring: Representation and Learning
166. ICLR 2024Successor Heads: Recurring, Interpretable Attention Heads In The Wild
167. ICLR 2024Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs
168. ICLR 2024The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Language Models
169. ICLR 2024The Hidden Language of Diffusion Models
170. ICLR 2024The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting — An Analytical Model
171. ICLR 2024The mechanistic basis of data dependence and abrupt learning in an in-context classification task
172. ICLR 2024To Grok or not to Grok: Disentangling Generalization and Memorization on Corrupted Algorithmic Datasets
173. ICLR 2024Towards Best Practices of Activation Patching in Language Models: Metrics and Methods
174. ICLR 2024Towards Transparent Time Series Forecasting
175. ICLR 2024Towards Understanding Factual Knowledge of Large Language Models
176. ICLR 2024Understanding Addition in Transformers
177. ICLR 2024Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models
178. ICLR 2024Unraveling the Enigma of Double Descent: An In-depth Analysis through the Lens of Learned Feature Space
179. ICLR 2024Unveiling and Manipulating Prompt Influence in Large Language Models
180. ICLR 2024Vision Transformers Need Registers
181. ICLR 2024What Makes a Good Prune? Maximal Unstructured Pruning for Maximal Cosine Similarity
182. ICLR 2024What's In My Big Data?
183. ICML 2024A connection between Tempering and Entropic Mirror Descent
184. ICML 2024A Multimodal Automated Interpretability Agent
185. ICML 2024A Persuasive Approach to Combating Misinformation
186. ICML 2024A Unified View of FANOVA: A Comprehensive Bayesian Framework for Component Selection and Estimation
187. ICML 2024Accelerated Algorithms for Constrained Nonconvex-Nonconcave Min-Max Optimization and Comonotone Inclusion
188. ICML 2024Active Ranking and Matchmaking, with Perfect Matchings
189. ICML 2024AI Alignment with Changing and Influenceable Reward Functions
190. ICML 2024AlphaZero-Like Tree-Search can Guide Large Language Model Decoding and Training
191. ICML 2024An Online Optimization Perspective on First-Order and Zero-Order Decentralized Nonsmooth Nonconvex Stochastic Optimization
192. ICML 2024Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
193. ICML 2024Attack-free Evaluating and Enhancing Adversarial Robustness on Categorical Data
194. ICML 2024Attention Meets Post-hoc Interpretability: A Mathematical Perspective
195. ICML 2024Balanced Resonate-and-Fire Neurons
196. ICML 2024Benchmarking Deletion Metrics with the Principled Explanations
197. ICML 2024Bootstrapping Fisher Market Equilibrium and First-Price Pacing Equilibrium
198. ICML 2024Bridging Mini-Batch and Asymptotic Analysis in Contrastive Learning: From InfoNCE to Kernel-Based Losses
199. ICML 2024Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updates
200. ICML 2024Can Machines Learn the True Probabilities?

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.