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

643 papers, page 6 of 13

251. ICLR 2026Temporal superposition and feature geometry of RNNs under memory demands
252. ICLR 2026Testing Most Influential Sets
253. ICLR 2026The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think
254. ICLR 2026The Deleuzian Representation Hypothesis
255. ICLR 2026The Geometry and Topology of Circuits: the Manifolds of Modular Addition
256. ICLR 2026The Lattice Geometry of Neural Network Quantization: A Short Equivalence Proof of GPTQ and Babai's Algorithm
257. ICLR 2026The Lattice Representation Hypothesis and Concept Algebra in LLMs
258. ICLR 2026The Price of Amortized inference in Sparse Autoencoders
259. ICLR 2026The Shape of Adversarial Influence: Characterizing LLM Latent Spaces with Persistent Homology
260. ICLR 2026The Tutor-Pupil Augmentation: Enhancing Learning and Interpretability via Input Corrections
261. ICLR 2026The Value of Information in Human-AI Decision-making
262. ICLR 2026TileLang: Bridge Programmability and Performance in Modern Neural Kernels
263. ICLR 2026TimeSeg: An Information-Theoretic Segment-Wise Explainer for Time-Series Predictions
264. ICLR 2026TIMESLIVER : SYMBOLIC-LINEAR DECOMPOSITION FOR EXPLAINABLE TIME SERIES CLASSIFICATION
265. ICLR 2026To Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space Models
266. ICLR 2026Topology and geometry of the learning space of ReLU networks: connectivity and singularities
267. ICLR 2026Toward Practical Equilibrium Propagation: Brain-inspired Recurrent Neural Network with Feedback Regulation and Residual Connections
268. ICLR 2026Towards a Theoretical Understanding of In-context Learning: Stability and Non-I.I.D Generalisation
269. ICLR 2026Towards Interpretable Visual Decoding with Attention to Brain Representations
270. ICLR 2026Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a Measurement
271. ICLR 2026Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition
272. ICLR 2026Tracing and Reversing Edits in LLMs
273. ICLR 2026Tracing the Traces: Latent Temporal Signals for Efficient and Accurate Reasoning
274. ICLR 2026Training-free Counterfactual Explanation for Temporal Graph Model Inference
275. ICLR 2026Transformers as Measure-Theoretic Associative Memory: A Statistical Perspective and Minimax Optimality
276. ICLR 2026Transformers Don’t Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and Implications for Mechanistic Interpretability
277. ICLR 2026Tucker-FNO: Tensor Tucker-Fourier Neural Operator and its Universal Approximation Theory
278. ICLR 2026Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders
279. ICLR 2026Understanding and Relaxing the Limitations of Transformers for Linear Algebra
280. ICLR 2026Understanding the Emergence of Seemingly Useless Features in Next-Token Predictors
281. ICLR 2026Unifying Formal Explanations: A Complexity-Theoretic Perspective
282. ICLR 2026VeriTrail: Closed-Domain Hallucination Detection with Traceability
283. ICLR 2026Visual symbolic mechanisms: Emergent symbol processing in Vision Language Models
284. ICLR 2026Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs
285. ICLR 2026Welfarist Formulations for Diverse Similarity Search
286. ICLR 2026What Do Large Language Models Know About Opinions?
287. ICLR 2026When Bias Helps Learning: Bridging Initial Prejudice and Trainability
288. ICLR 2026When Shift Happens - Confounding Is to Blame
289. ICLR 2026When Thinking Backfires: Mechanistic Insights into Reason-induced Misalignment
290. ICLR 2026Why Do Unlearnable Examples Work: A Novel Perspective of Mutual Information
291. ICLR 2026xRFM: Accurate, scalable, and interpretable feature learning models for tabular data
292. ICLR 2026ZeroTuning: Unlocking the Initial Token's Power to Enhance Large Language Models Without Training
293. ICLR 20253D-Properties: Identifying Challenges in DPO and Charting a Path Forward
294. ICLR 2025A General Framework for Producing Interpretable Semantic Text Embeddings
295. ICLR 2025A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals
296. ICLR 2025Accelerating neural network training: An analysis of the AlgoPerf competition
297. ICLR 2025Adaptive Transformer Programs: Bridging the Gap Between Performance and Interpretability in Transformers
298. ICLR 2025Agree to Disagree: Demystifying Homogeneous Deep Ensembles through Distributional Equivalence
299. ICLR 2025AI2TALE: An Innovative Information Theory-based Approach for Learning to Localize Phishing Attacks
300. ICLR 2025An Efficient Framework for Crediting Data Contributors of 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.