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 14 of 26

651. NeurIPS 2025Incentivizing Desirable Effort Profiles in Strategic Classification: The Role of Causality and Uncertainty
652. NeurIPS 2025Incentivizing Time-Aware Fairness in Data Sharing
653. NeurIPS 2025Individual Fairness In Strategic Classification
654. NeurIPS 2025Individually Fair Diversity Maximization
655. NeurIPS 2025Inference-Time Reward Hacking in Large Language Models
656. NeurIPS 2025Inner Speech as Behavior Guides: Steerable Imitation of Diverse Behaviors for Human-AI coordination
657. NeurIPS 2025Instance-Optimality for Private KL Distribution Estimation
658. NeurIPS 2025Interactive and Hybrid Imitation Learning: Provably Beating Behavior Cloning
659. NeurIPS 2025Intermediate Domain Alignment and Morphology Analogy for Patent-Product Image Retrieval
660. NeurIPS 2025Interpretable and Parameter Efficient Graph Neural Additive Models with Random Fourier Features
661. NeurIPS 2025Interpretable Next-token Prediction via the Generalized Induction Head
662. NeurIPS 2025Interpreting Arithmetic Reasoning in Large Language Models using Game-Theoretic Interactions
663. NeurIPS 2025Interpreting Emergent Features in Deep Learning-based Side-channel Analysis
664. NeurIPS 2025Interpreting vision transformers via residual replacement model
665. NeurIPS 2025InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy
666. NeurIPS 2025Jacobian-Based Interpretation of Nonlinear Neural Encoding Model
667. NeurIPS 2025Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy
668. NeurIPS 2025Knowledge Distillation Detection for Open-weights Models
669. NeurIPS 2025Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations
670. NeurIPS 2025LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs
671. NeurIPS 2025LawShift: Benchmarking Legal Judgment Prediction Under Statute Shifts
672. NeurIPS 2025Layer-Wise Modality Decomposition for Interpretable Multimodal Sensor Fusion
673. NeurIPS 2025LeapFactual: Reliable Visual Counterfactual Explanation Using Conditional Flow Matching
674. NeurIPS 2025Learning from Delayed Feedback in Games via Extra Prediction
675. NeurIPS 2025Learning Gradient Boosted Decision Trees with Algorithmic Recourse
676. NeurIPS 2025Learning in Compact Spaces with Approximately Normalized Transformer
677. NeurIPS 2025Learning to Add, Multiply, and Execute Algorithmic Instructions Exactly with Neural Networks
678. NeurIPS 2025Lie Detector: Unified Backdoor Detection via Cross-Examination Framework
679. NeurIPS 2025Lifelong Safety Alignment for Language Models
680. NeurIPS 2025LLM Generated Persona is a Promise with a Catch
681. NeurIPS 2025LLM Interpretability with Identifiable Temporal-Instantaneous Representation
682. NeurIPS 2025LLM Layers Immediately Correct Each Other
683. NeurIPS 2025LLM Strategic Reasoning: Agentic Study through Behavioral Game Theory
684. NeurIPS 2025LLM Unlearning via Neural Activation Redirection
685. NeurIPS 2025LLMs Encode Harmfulness and Refusal Separately
686. NeurIPS 2025Localizing Knowledge in Diffusion Transformers
687. NeurIPS 2025Locally Optimal Private Sampling: Beyond the Global Minimax
688. NeurIPS 2025LOMIA: Label-Only Membership Inference Attacks against Pre-trained Large Vision-Language Models
689. NeurIPS 2025Look-Ahead Reasoning on Learning Platforms
690. NeurIPS 2025LoRO: Real-Time on-Device Secure Inference for LLMs via TEE-Based Low Rank Obfuscation
691. NeurIPS 2025Low Rank Gradients and Where to Find Them
692. NeurIPS 2025Machine Unlearning in 3D Generation: A Perspective-Coherent Acceleration Framework
693. NeurIPS 2025Machine Unlearning via Task Simplex Arithmetic
694. NeurIPS 2025Manipulating Feature Visualizations with Gradient Slingshots
695. NeurIPS 2025Mask Image Watermarking
696. NeurIPS 2025Matchings Under Biased and Correlated Evaluations
697. NeurIPS 2025Measuring and Guiding Monosemanticity
698. NeurIPS 2025Mechanistic Interpretability of RNNs emulating Hidden Markov Models
699. NeurIPS 2025Median Selection with Noisy and Structural Information
700. NeurIPS 2025MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs

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.