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 9 of 13

401. ICLR 2025Logic-Logit: A Logic-Based Approach to Choice Modeling
402. ICLR 2025Look Before You Leap: Universal Emergent Mechanism for Retrieval in Language Models
403. ICLR 2025Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escape, and Network Embedding
404. ICLR 2025LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision
405. ICLR 2025MANTRA: The Manifold Triangulations Assemblage
406. ICLR 2025Measuring And Improving Persuasiveness Of Large Language Models
407. ICLR 2025Mechanism and Emergence of Stacked Attention Heads in Multi-Layer Transformers
408. ICLR 2025Mechanistic Permutability: Match Features Across Layers
409. ICLR 2025MIND over Body: Adaptive Thinking using Dynamic Computation
410. ICLR 2025Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity
411. ICLR 2025Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds
412. ICLR 2025Modeling dynamic social vision highlights gaps between deep learning and humans
413. ICLR 2025Monet: Mixture of Monosemantic Experts for Transformers
414. ICLR 2025Monitoring Latent World States in Language Models with Propositional Probes
415. ICLR 2025Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretability
416. ICLR 2025Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence
417. ICLR 2025NetFormer: An interpretable model for recovering dynamical connectivity in neuronal population dynamics
418. ICLR 2025Neural Causal Graph for Interpretable and Intervenable Classification
419. ICLR 2025NeurFlow: Interpreting Neural Networks through Neuron Groups and Functional Interactions
420. ICLR 2025Neuron-based Multifractal Analysis of Neuron Interaction Dynamics in Large Models
421. ICLR 2025NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals
422. ICLR 2025No Equations Needed: Learning System Dynamics Without Relying on Closed-Form ODEs
423. ICLR 2025Not All Language Model Features Are One-Dimensionally Linear
424. ICLR 2025On Linear Representations and Pretraining Data Frequency in Language Models
425. ICLR 2025On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax Optimality
426. ICLR 2025On the expressiveness and spectral bias of KANs
427. ICLR 2025On the Role of Attention Heads in Large Language Model Safety
428. ICLR 2025Open-Set Graph Anomaly Detection via Normal Structure Regularisation
429. ICLR 2025Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression
430. ICLR 2025Partially Observed Trajectory Inference using Optimal Transport and a Dynamics Prior
431. ICLR 2025PhyloLM: Inferring the Phylogeny of Large Language Models and Predicting their Performances in Benchmarks
432. ICLR 2025PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs
433. ICLR 2025Precise Localization of Memories: A Fine-grained Neuron-level Knowledge Editing Technique for LLMs
434. ICLR 2025Probabilistic Learning to Defer: Handling Missing Expert Annotations and Controlling Workload Distribution
435. ICLR 2025Prompting Fairness: Integrating Causality to Debias Large Language Models
436. ICLR 2025ProtoSnap: Prototype Alignment For Cuneiform Signs
437. ICLR 2025Provably Accurate Shapley Value Estimation via Leverage Score Sampling
438. ICLR 2025QPM: Discrete Optimization for Globally Interpretable Image Classification
439. ICLR 2025Reassessing How to Compare and Improve the Calibration of Machine Learning Models
440. ICLR 2025Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs
441. ICLR 2025Recovering Manifold Structure Using Ollivier Ricci Curvature
442. ICLR 2025ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability
443. ICLR 2025Representational Similarity via Interpretable Visual Concepts
444. ICLR 2025Residual Connections and Normalization Can Provably Prevent Oversmoothing in GNNs
445. ICLR 2025Residual Stream Analysis with Multi-Layer SAEs
446. ICLR 2025Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words
447. ICLR 2025Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond
448. ICLR 2025Rethinking Self-Distillation: Label Averaging and Enhanced Soft Label Refinement with Partial Labels
449. ICLR 2025Rethinking Shapley Value for Negative Interactions in Non-convex Games
450. ICLR 2025Revealing and Mitigating Over-Attention in Knowledge Editing

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.