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

301 papers, page 6 of 7

251. NeurIPS 2023Generalized equivalences between subsampling and ridge regularization
252. NeurIPS 2023GLIME: General, Stable and Local LIME Explanation
253. NeurIPS 2023How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model
254. NeurIPS 2023Human-Guided Complexity-Controlled Abstractions
255. NeurIPS 2023Improved Bayes Risk Can Yield Reduced Social Welfare Under Competition
256. NeurIPS 2023Initialization-Dependent Sample Complexity of Linear Predictors and Neural Networks
257. NeurIPS 2023Interpretability at Scale: Identifying Causal Mechanisms in Alpaca
258. NeurIPS 2023LEACE: Perfect linear concept erasure in closed form
259. NeurIPS 2023Maximum State Entropy Exploration using Predecessor and Successor Representations
260. NeurIPS 2023Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension
261. NeurIPS 2023Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage
262. NeurIPS 2023On Masked Pre-training and the Marginal Likelihood
263. NeurIPS 2023On the Identifiability and Interpretability of Gaussian Process Models
264. NeurIPS 2023On the impact of activation and normalization in obtaining isometric embeddings at initialization
265. NeurIPS 2023On the Interplay between Social Welfare and Tractability of Equilibria
266. NeurIPS 2023On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective
267. NeurIPS 2023On the Relationship Between Relevance and Conflict in Online Social Link Recommendations
268. NeurIPS 2023Online (Multinomial) Logistic Bandit: Improved Regret and Constant Computation Cost
269. NeurIPS 2023Online Corrupted User Detection and Regret Minimization
270. NeurIPS 2023Optimized Covariance Design for AB Test on Social Network under Interference
271. NeurIPS 2023ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP
272. NeurIPS 2023Participatory Personalization in Classification
273. NeurIPS 2023PopSign ASL v1.0: An Isolated American Sign Language Dataset Collected via Smartphones
274. NeurIPS 2023Regret Matching+: (In)Stability and Fast Convergence in Games
275. NeurIPS 2023Resolving the Tug-of-War: A Separation of Communication and Learning in Federated Learning
276. NeurIPS 2023Robust covariance estimation with missing values and cell-wise contamination
277. NeurIPS 2023Scalable Fair Influence Maximization
278. NeurIPS 2023Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer
279. NeurIPS 2023Sequential Predictive Two-Sample and Independence Testing
280. NeurIPS 2023SmoothHess: ReLU Network Feature Interactions via Stein's Lemma
281. NeurIPS 2023Social Motion Prediction with Cognitive Hierarchies
282. NeurIPS 2023Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases
283. NeurIPS 2023Stability and Generalization of the Decentralized Stochastic Gradient Descent Ascent Algorithm
284. NeurIPS 2023Stability of Random Forests and Coverage of Random-Forest Prediction Intervals
285. NeurIPS 2023Strategyproof Voting under Correlated Beliefs
286. NeurIPS 2023Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training
287. NeurIPS 2023The Best of Both Worlds in Network Population Games: Reaching Consensus and Convergence to Equilibrium
288. NeurIPS 2023The Distortion of Binomial Voting Defies Expectation
289. NeurIPS 2023The Equivalence of Dynamic and Strategic Stability under Regularized Learning in Games
290. NeurIPS 2023The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation
291. NeurIPS 2023Thin and deep Gaussian processes
292. NeurIPS 2023Towards a fuller understanding of neurons with Clustered Compositional Explanations
293. NeurIPS 2023Towards Better Dynamic Graph Learning: New Architecture and Unified Library
294. NeurIPS 2023Tracr: Compiled Transformers as a Laboratory for Interpretability
295. NeurIPS 2023Trade-off Between Efficiency and Consistency for Removal-based Explanations
296. NeurIPS 2023Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammars
297. NeurIPS 2023Transitivity Recovering Decompositions: Interpretable and Robust Fine-Grained Relationships
298. NeurIPS 2023Triple Eagle: Simple, Fast and Practical Budget-Feasible Mechanisms
299. NeurIPS 2023Uncovering and Quantifying Social Biases in Code Generation
300. NeurIPS 2023Visual Programming for Step-by-Step Text-to-Image Generation and Evaluation

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.