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

522 papers, page 3 of 11

101. NeurIPS 2025CTRL-ALT-DECEIT Sabotage Evaluations for Automated AI R&D
102. NeurIPS 2025CVGL: Causal Learning and Geometric Topology
103. NeurIPS 2025Data-Free Model Extraction for Black-box Recommender Systems via Graph Convolutions
104. NeurIPS 2025Deep Learning with Plausible Deniability
105. NeurIPS 2025Deep Value Benchmark: Measuring Whether Models Generalize Deep values or Shallow Preferences
106. NeurIPS 2025Deferring Concept Bottleneck Models: Learning to Defer Interventions to Inaccurate Experts
107. NeurIPS 2025Defining and Discovering Hyper-meta-paths for Heterogeneous Hypergraphs
108. NeurIPS 2025DEGauss: Defending Against Malicious 3D Editing for Gaussian Splatting
109. NeurIPS 2025Dense SAE Latents Are Features, Not Bugs
110. NeurIPS 2025DePass: Unified Feature Attributing by Simple Decomposed Forward Pass
111. NeurIPS 2025DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patches
112. NeurIPS 2025Detecting Generated Images by Fitting Natural Image Distributions
113. NeurIPS 2025Detecting High-Stakes Interactions with Activation Probes
114. NeurIPS 2025Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing
115. NeurIPS 2025DiCoFlex: Model-Agnostic Diverse Counterfactuals with Flexible Control
116. NeurIPS 2025DictPFL: Efficient and Private Federated Learning on Encrypted Gradients
117. NeurIPS 2025DiffBreak: Is Diffusion-Based Purification Robust?
118. NeurIPS 2025Differentiable Sparsity via $D$-Gating: Simple and Versatile Structured Penalization
119. NeurIPS 2025Differential Privacy on Fully Dynamic Streams
120. NeurIPS 2025Differentially Private Bilevel Optimization: Efficient Algorithms with Near-Optimal Rates
121. NeurIPS 2025Differentially Private Gomory-Hu Trees
122. NeurIPS 2025Differentially Private High-dimensional Variable Selection via Integer Programming
123. NeurIPS 2025Differentially Private Quantiles with Smaller Error
124. NeurIPS 2025Differentially Private Relational Learning with Entity-level Privacy Guarantees
125. NeurIPS 2025Diffusion Models and the Manifold Hypothesis: Log-Domain Smoothing is Geometry Adaptive
126. NeurIPS 2025Dimensionality Mismatch Between Brains and Artificial Neural Networks
127. NeurIPS 2025Direct Alignment with Heterogeneous Preferences
128. NeurIPS 2025Discovering Opinion Intervals from Conflicts in Signed Graphs
129. NeurIPS 2025Discretization-free Multicalibration through Loss Minimization over Tree Ensembles
130. NeurIPS 2025Disentangling Superpositions: Interpretable Brain Encoding Model with Sparse Concept Atoms
131. NeurIPS 2025Distillation Robustifies Unlearning
132. NeurIPS 2025DKDR: Dynamic Knowledge Distillation for Reliability in Federated Learning
133. NeurIPS 2025Do different prompting methods yield a common task representation in language models?
134. NeurIPS 2025Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness
135. NeurIPS 2025Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?
136. NeurIPS 2025Does Representation Guarantee Welfare?
137. NeurIPS 2025Don’t Give Up on Democratizing AI for the Wrong Reasons
138. NeurIPS 2025Double Descent Meets Out-of-Distribution Detection: Theoretical Insights and Empirical Analysis on the Role of Model Complexity
139. NeurIPS 2025DPA: A one-stop metric to measure bias amplification in classification datasets
140. NeurIPS 2025DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents
141. NeurIPS 2025DUAL: Learning Diverse Kernels for Aggregated Two-sample and Independence Testing
142. NeurIPS 2025DualOptim: Enhancing Efficacy and Stability in Machine Unlearning with Dual Optimizers
143. NeurIPS 2025E2E-VGuard: Adversarial Prevention for Production LLM-based End-To-End Speech Synthesis
144. NeurIPS 2025EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification
145. NeurIPS 2025EAReranker: Efficient Embedding Adequacy Assessment for Retrieval Augmented Generation
146. NeurIPS 2025Efficient Algorithms for Robust and Partial Semi-Discrete Optimal Transport
147. NeurIPS 2025Efficient Fairness-Performance Pareto Front Computation
148. NeurIPS 2025Efficient Utility-Preserving Machine Unlearning with Implicit Gradient Surgery
149. NeurIPS 2025ElliCE: Efficient and Provably Robust Algorithmic Recourse via the Rashomon Sets
150. NeurIPS 2025Emergence and Evolution of Interpretable Concepts in Diffusion Models

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.