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 4 of 23

151. ICML 2026Domain Restriction via SAE Multi-Layer Transitions
152. ICML 2026DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning
153. ICML 2026DPsurv: Dual-Prototype Evidential Fusion for Uncertainty-Aware and Interpretable Whole Slide Image Survival Prediction
154. ICML 2026Drop-in Circulant Structural Priors for Transformer Decoding of Cyclic Codes
155. ICML 2026Dual Mechanisms of Value Expression: Intrinsic vs. Prompted Values in Large Language Models
156. ICML 2026Dual-branch Robust Unlearnable Examples
157. ICML 2026DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language Models
158. ICML 2026Dynamic Linear Attention
159. ICML 2026Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure
160. ICML 2026ECCO: Evidence-Driven Causal Reasoning for Compiler Optimization
161. ICML 2026Echoes within the Reasoning: Stealthy and Effective Watermarking via Chain of Thought
162. ICML 2026Efficient Bayesian Inference from Noisy Pairwise Comparisons
163. ICML 2026Efficient LLM Moderation with Multi-Layer Latent Prototypes
164. ICML 2026Efficient privacy loss accounting for subsampling and random allocation
165. ICML 2026Efficient Public Verification of Private ML via Regularization
166. ICML 2026Eliminating Solution Bias in Differentially Private Optimization
167. ICML 2026Emergence of Hierarchical Emotion Organization in Large Language Models
168. ICML 2026Emergent Analogical Reasoning in Transformers
169. ICML 2026Emergent Communication Under Misinformation
170. ICML 2026Endogenous Resistance to Activation Steering in Language Models
171. ICML 2026Enhancing Conformal Prediction via Class Similarity
172. ICML 2026Ensembling Sparse Autoencoders
173. ICML 2026EPSVec: Efficient and Private Synthetic Data Generation via Dataset Vectors
174. ICML 2026Equalized Generative Treatment: Matching f-divergences for Fairness in Generative Models
175. ICML 2026Evaluating and Steering Modality Preferences in Multi-modal LLMs
176. ICML 2026Every Step Counts: Decoding Trajectories as Authorship Fingerprints of dLLMs
177. ICML 2026Evidential Copula Concept Embedding Models
178. ICML 2026Exact and Approximate Algorithms for Polytree Learning
179. ICML 2026Exact Functional ANOVA Decomposition for Categorical Inputs Models
180. ICML 2026Exactly Computing do-Shapley Values
181. ICML 2026Expand Neurons, Not Parameters
182. ICML 2026Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scaling
183. ICML 2026ExPLAIND: Unifying Model, Data, and Training Attribution to Study Model Behavior
184. ICML 2026Explanations are a Means to an End: Decision Theoretic Explanation Evaluation
185. ICML 2026Exploring Accurate and Transparent Domain Adaptation in Predictive Healthcare via Concept-Grounded Orthogonal Inference
186. ICML 2026Exposing Hidden Biases in Text-to-Image Models via Automated Prompt Search
187. ICML 2026Extending Fair Null-Space Projections for Continuous Attributes to Kernel Methods
188. ICML 2026Factorized Scheduling Principle: Learning Interpretable and Transferable Policies via Structured Additive Functions
189. ICML 2026Fair Classification with Efficient and Post-hoc Controllable Fairness-Accuracy Trade-off
190. ICML 2026Fair Dataset Distillation via Cross-Group Barycenter Alignment
191. ICML 2026Fair Decisions from Calibrated Scores: Achieving Optimal Classification While Satisfying Sufficiency
192. ICML 2026Fair Transit Stop Placement: A Clustering Perspective and Beyond
193. ICML 2026FairGB: A Fair Granular-Ball Generation Method for Data Classification
194. ICML 2026Fairness in Aggregation: Optimal Top-$k$ and Improved Full Ranking
195. ICML 2026FairRARI: A Plug and Play Framework for Fairness-Aware PageRank
196. ICML 2026FakeWorld 1.0: An Omni-modal Benchmark for Fake Media and Content
197. ICML 2026Falling Trees: A Model Class for Interpretable Risk Prioritization
198. ICML 2026Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process
199. ICML 2026Fast and Near-Optimal Algorithms for Private Hypothesis Selection
200. ICML 2026Fast and Scalable Analytical Diffusion

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.