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

1,124 papers, page 16 of 23

751. ICML 2025Optimal Fair Learning Robust to Adversarial Distribution Shift
752. ICML 2025Optimizing Adaptive Attacks against Watermarks for Language Models
753. ICML 2025Optimizing Noise Distributions for Differential Privacy
754. ICML 2025Optimizing Social Network Interventions via Hypergradient-Based Recommender System Design
755. ICML 2025OR-Bench: An Over-Refusal Benchmark for Large Language Models
756. ICML 2025Partition First, Embed Later: Laplacian-Based Feature Partitioning for Refined Embedding and Visualization of High-Dimensional Data
757. ICML 2025PASS: Private Attributes Protection with Stochastic Data Substitution
758. ICML 2025Phase and Amplitude-aware Prompting for Enhancing Adversarial Robustness
759. ICML 2025Plausible Token Amplification for Improving Accuracy of Differentially Private In-Context Learning Based on Implicit Bayesian Inference
760. ICML 2025Pointwise Information Measures as Confidence Estimators in Deep Neural Networks: A Comparative Study
761. ICML 2025Policy Design for Two-sided Platforms with Participation Dynamics
762. ICML 2025POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference Optimization
763. ICML 2025Position: AI Agents Need Authenticated Delegation
764. ICML 2025Position: AI Safety should prioritize the Future of Work
765. ICML 2025Position: AI's growing due process problem
766. ICML 2025Position: Build Agent Advocates, Not Platform Agents
767. ICML 2025Position: Challenges and Future Directions of Data-Centric AI Alignment
768. ICML 2025Position: Contextual Integrity is Inadequately Applied to Language Models
769. ICML 2025Position: Evaluating Generative AI Systems Is a Social Science Measurement Challenge
770. ICML 2025Position: Explainable AI Cannot Advance Without Better User Studies
771. ICML 2025Position: Generative AI Regulation Can Learn from Social Media Regulation
772. ICML 2025Position: Human Baselines in Model Evaluations Need Rigor and Transparency (With Recommendations & Reporting Checklist)
773. ICML 2025Position: Language model developers should report train-test overlap
774. ICML 2025Position: Machine Learning Models Have a Supply Chain Problem
775. ICML 2025Position: Rethinking Explainable Machine Learning as Applied Statistics
776. ICML 2025Position: Rethinking LLM Bias Probing Using Lessons from the Social Sciences
777. ICML 2025Position: Societal Impacts Research Requires Benchmarks for Creative Composition Tasks
778. ICML 2025Position: The AI Conference Peer Review Crisis Demands Author Feedback and Reviewer Rewards
779. ICML 2025Position: The Artificial Intelligence and Machine Learning Community Should Adopt a More Transparent and Regulated Peer Review Process
780. ICML 2025Position: The Right to AI
781. ICML 2025Position: We Can’t Understand AI Using our Existing Vocabulary
782. ICML 2025Positional Attention: Expressivity and Learnability of Algorithmic Computation
783. ICML 2025Prediction via Shapley Value Regression
784. ICML 2025Prediction-Aware Learning in Multi-Agent Systems
785. ICML 2025Preference learning made easy: Everything should be understood through win rate
786. ICML 2025Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise Cancellation
787. ICML 2025Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty
788. ICML 2025Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index Models
789. ICML 2025Provably Cost-Sensitive Adversarial Defense via Randomized Smoothing
790. ICML 2025Quantifying Memory Utilization with Effective State-Size
791. ICML 2025Quantifying Prediction Consistency Under Fine-tuning Multiplicity in Tabular LLMs
792. ICML 2025QuEST: Stable Training of LLMs with 1-Bit Weights and Activations
793. ICML 2025Ranked from Within: Ranking Large Multimodal Models Without Labels
794. ICML 2025Relative Error Fair Clustering in the Weak-Strong Oracle Model
795. ICML 2025Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing
796. ICML 2025Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions
797. ICML 2025Representative Ranking for Deliberation in the Public Sphere
798. ICML 2025Rethinking Aleatoric and Epistemic Uncertainty
799. ICML 2025Rethinking the Temperature for Federated Heterogeneous Distillation
800. ICML 2025Revisiting the Predictability of Performative, Social Events

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.