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

255 papers, page 5 of 6

201. NeurIPS 2024Stochastic Concept Bottleneck Models
202. NeurIPS 2024Stochastic Optimal Control and Estimation with Multiplicative and Internal Noise
203. NeurIPS 2024Studying How to Efficiently and Effectively Guide Models with Explanations - A Reproducibility Study
204. NeurIPS 2024Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling
205. NeurIPS 2024Symmetry Discovery Beyond Affine Transformations
206. NeurIPS 2024Talking Heads: Understanding Inter-Layer Communication in Transformer Language Models
207. NeurIPS 2024Taming Heavy-Tailed Losses in Adversarial Bandits and the Best-of-Both-Worlds Setting
208. NeurIPS 2024Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization
209. NeurIPS 2024TEG-DB: A Comprehensive Dataset and Benchmark of Textual-Edge Graphs
210. NeurIPS 2024Test Where Decisions Matter: Importance-driven Testing for Deep Reinforcement Learning
211. NeurIPS 2024Test-Time Dynamic Image Fusion
212. NeurIPS 2024Testing Calibration in Nearly-Linear Time
213. NeurIPS 2024Testing Semantic Importance via Betting
214. NeurIPS 2024The Closeness of In-Context Learning and Weight Shifting for Softmax Regression
215. NeurIPS 2024The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More
216. NeurIPS 2024The Intelligible and Effective Graph Neural Additive Network
217. NeurIPS 2024The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models
218. NeurIPS 2024The Representation Landscape of Few-Shot Learning and Fine-Tuning in Large Language Models
219. NeurIPS 2024The State of Data Curation at NeurIPS: An Assessment of Dataset Development Practices in the Datasets and Benchmarks Track
220. NeurIPS 2024The Surprising Effectiveness of SP Voting with Partial Preferences
221. NeurIPS 2024The tree autoencoder model, with application to hierarchical data visualization
222. NeurIPS 2024Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networks
223. NeurIPS 2024Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox
224. NeurIPS 2024Towards Neuron Attributions in Multi-Modal Large Language Models
225. NeurIPS 2024Towards Scalable and Stable Parallelization of Nonlinear RNNs
226. NeurIPS 2024Towards Understanding How Transformers Learn In-context Through a Representation Learning Lens
227. NeurIPS 2024Trading off Consistency and Dimensionality of Convex Surrogates for Multiclass Classification
228. NeurIPS 2024Training Data Attribution via Approximate Unrolling
229. NeurIPS 2024Training for Stable Explanation for Free
230. NeurIPS 2024Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear $q^\pi$-Realizability and Concentrability
231. NeurIPS 2024Transcoders find interpretable LLM feature circuits
232. NeurIPS 2024Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalization
233. NeurIPS 2024Transformer Doctor: Diagnosing and Treating Vision Transformers
234. NeurIPS 2024Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression
235. NeurIPS 2024Transformers on Markov data: Constant depth suffices
236. NeurIPS 2024Transformers Represent Belief State Geometry in their Residual Stream
237. NeurIPS 2024Truth is Universal: Robust Detection of Lies in LLMs
238. NeurIPS 2024Understanding and Minimising Outlier Features in Transformer Training
239. NeurIPS 2024Understanding Information Storage and Transfer in Multi-Modal Large Language Models
240. NeurIPS 2024Understanding the Expressivity and Trainability of Fourier Neural Operator: A Mean-Field Perspective
241. NeurIPS 2024Understanding Transformers via N-Gram Statistics
242. NeurIPS 2024Understanding Visual Feature Reliance through the Lens of Complexity
243. NeurIPS 2024Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback
244. NeurIPS 2024Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers
245. NeurIPS 2024Using Noise to Infer Aspects of Simplicity Without Learning
246. NeurIPS 2024VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance
247. NeurIPS 2024What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
248. NeurIPS 2024What makes unlearning hard and what to do about it
249. NeurIPS 2024What Rotary Position Embedding Can Tell Us: Identifying Query and Key Weights Corresponding to Basic Syntactic or High-level Semantic Information
250. NeurIPS 2024When is an Embedding Model More Promising than Another?

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.