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

1,275 papers, page 16 of 26

751. NeurIPS 2025Performative Validity of Recourse Explanations
752. NeurIPS 2025Personalized Safety in LLMs: A Benchmark and A Planning-Based Agent Approach
753. NeurIPS 2025Pinpointing Attention-Causal Communication in Language Models
754. NeurIPS 2025Position: If Innovation in AI systematically Violates Fundamental Rights, Is It Innovation at All?
755. NeurIPS 2025Position: Require Frontier AI Labs To Release Small "Analog" Models
756. NeurIPS 2025Practical Bayes-Optimal Membership Inference Attacks
757. NeurIPS 2025Practical do-Shapley Explanations with Estimand-Agnostic Causal Inference
758. NeurIPS 2025Predicting the Performance of Black-box Language Models with Follow-up Queries
759. NeurIPS 2025Prior Forgetting and In-Context Overfitting
760. NeurIPS 2025Privacy amplification by random allocation
761. NeurIPS 2025Private Continual Counting of Unbounded Streams
762. NeurIPS 2025Private Geometric Median in Nearly-Linear Time
763. NeurIPS 2025Private Hyperparameter Tuning with Ex-Post Guarantee
764. NeurIPS 2025Private Set Union with Multiple Contributions
765. NeurIPS 2025Private Zeroth-Order Optimization with Public Data
766. NeurIPS 2025Probabilistic Stability Guarantees for Feature Attributions
767. NeurIPS 2025Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry
768. NeurIPS 2025ProtoPairNet: Interpretable Regression through Prototypical Pair Reasoning
769. NeurIPS 2025Provable Gradient Editing of Deep Neural Networks
770. NeurIPS 2025Proxy-SPEX: Sample-Efficient Interpretability via Sparse Feature Interactions in LLMs
771. NeurIPS 2025Purifying Approximate Differential Privacy with Randomized Post-processing
772. NeurIPS 2025Quantifying Cross-Modality Memorization in Vision-Language Models
773. NeurIPS 2025Query-Efficient Locally Private Hypothesis Selection via the Scheffe Graph
774. NeurIPS 2025Randomized-MLP Regularization Improves Domain Adaptation and Interpretability in DINOv2
775. NeurIPS 2025Reasoning Models Sometimes Output Illegible Chains of Thought
776. NeurIPS 2025Rectifying Shortcut Behaviors in Preference-based Reward Learning
777. NeurIPS 2025Redefining Experts: Interpretable Decomposition of Language Models for Toxicity Mitigation
778. NeurIPS 2025Regional Explanations: Bridging Local and Global Variable Importance
779. NeurIPS 2025Regression Trees Know Calculus
780. NeurIPS 2025Regression-adjusted Monte Carlo Estimators for Shapley Values and Probabilistic Values
781. NeurIPS 2025Removing Concepts from Text-to-Image Models with Only Negative Samples
782. NeurIPS 2025Replicable Online pricing
783. NeurIPS 2025Representational Difference Explanations
784. NeurIPS 2025Rescaled Influence Functions: Accurate Data Attribution in High Dimension
785. NeurIPS 2025Residual Stream Analysis of Overfitting And Structural Disruptions
786. NeurIPS 2025Rethinking Circuit Completeness in Language Models: AND, OR, and ADDER Gates
787. NeurIPS 2025Rethinking Fair Federated Learning from Parameter and Client View
788. NeurIPS 2025Rethinking Gradient Step Denoiser: Towards Truly Pseudo-Contractive Operator
789. NeurIPS 2025Rethinking the Role of Verbatim Memorization in LLM Privacy
790. NeurIPS 2025Revising and Falsifying Sparse Autoencoder Feature Explanations
791. NeurIPS 2025Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability
792. NeurIPS 2025Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions
793. NeurIPS 2025Ridge Boosting is Both Robust and Efficient
794. NeurIPS 2025Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor
795. NeurIPS 2025Robust and Scalable Autonomous Reinforcement Learning in Irreversible Environments
796. NeurIPS 2025Robust Distributed Estimation: Extending Gossip Algorithms to Ranking and Trimmed Means
797. NeurIPS 2025Robust Explanations of Graph Neural Networks via Graph Curvatures
798. NeurIPS 2025Robust Integrated Learning and Pauli Noise Mitigation for Parametrized Quantum Circuits
799. NeurIPS 2025Robust SuperAlignment: Weak-to-Strong Robustness Generalization for Vision-Language Models
800. NeurIPS 2025RUAGO: Effective and Practical Retain-Free Unlearning via Adversarial Attack and OOD Generator

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.