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

3,411 papers, page 37 of 69

1801. ICML 2025Heads up! Large Language Models Can Perform Tasks Without Your Instruction via Selective Attention Head Masking
1802. ICML 2025How Do Transformers Learn Variable Binding in Symbolic Programs?
1803. ICML 2025How to Evaluate and Mitigate IP Infringement in Visual Generative AI?
1804. ICML 2025How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias
1805. ICML 2025Identifying and Understanding Cross-Class Features in Adversarial Training
1806. ICML 2025Improving LLM Safety Alignment with Dual-Objective Optimization
1807. ICML 2025Improving Memory Efficiency for Training KANs via Meta Learning
1808. ICML 2025Improving Out-of-Distribution Detection via Dynamic Covariance Calibration
1809. ICML 2025Improving Out-of-Distribution Detection with Markov Logic Networks
1810. ICML 2025In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax Attention
1811. ICML 2025Inducing, Detecting and Characterising Neural Modules: A Pipeline for Functional Interpretability in Reinforcement Learning
1812. ICML 2025InfoCons: Identifying Interpretable Critical Concepts in Point Clouds via Information Theory
1813. ICML 2025Information Bottleneck-guided MLPs for Robust Spatial-temporal Forecasting
1814. ICML 2025Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors
1815. ICML 2025Interpreting CLIP with Hierarchical Sparse Autoencoders
1816. ICML 2025Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations
1817. ICML 2025Janus: Dual-Server Multi-Round Secure Aggregation with Verifiability for Federated Learning
1818. ICML 2025Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning
1819. ICML 2025Kandinsky Conformal Prediction: Beyond Class- and Covariate-Conditional Coverage
1820. ICML 2025Kona: An Efficient Privacy-Preservation Framework for KNN Classification by Communication Optimization
1821. ICML 2025LapSum - One Method to Differentiate Them All: Ranking, Sorting and Top-k Selection
1822. ICML 2025Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes
1823. ICML 2025Learning Classifiers That Induce Markets
1824. ICML 2025Learning Distribution-wise Control in Representation Space for Language Models
1825. ICML 2025Learning Latent Graph Structures and their Uncertainty
1826. ICML 2025Learning Multi-Level Features with Matryoshka Sparse Autoencoders
1827. ICML 2025Learning Soft Sparse Shapes for Efficient Time-Series Classification
1828. ICML 2025Learning to Route LLMs with Confidence Tokens
1829. ICML 2025LEMoN: Label Error Detection using Multimodal Neighbors
1830. ICML 2025Leveraging Model Guidance to Extract Training Data from Personalized Diffusion Models
1831. ICML 2025Leveraging Predictive Equivalence in Decision Trees
1832. ICML 2025Leveraging Randomness in Model and Data Partitioning for Privacy Amplification
1833. ICML 2025Lightweight Protocols for Distributed Private Quantile Estimation
1834. ICML 2025LIMEFLDL: A Local Interpretable Model-Agnostic Explanations Approach for Label Distribution Learning
1835. ICML 2025Linear Bandits with Partially Observable Features
1836. ICML 2025Looking Beyond the Top-1: Transformers Determine Top Tokens in Order
1837. ICML 2025Loss Functions and Operators Generated by f-Divergences
1838. ICML 2025Low-Rank Adapting Models for Sparse Autoencoders
1839. ICML 2025Machines and Mathematical Mutations: Using GNNs to Characterize Quiver Mutation Classes
1840. ICML 2025Maintaining Proportional Committees with Dynamic Candidate Sets
1841. ICML 2025Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding
1842. ICML 2025Measuring Diversity: Axioms and Challenges
1843. ICML 2025Measuring In-Context Computation Complexity via Hidden State Prediction
1844. ICML 2025Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization
1845. ICML 2025MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents
1846. ICML 2025MemFreezing: A Novel Adversarial Attack on Temporal Graph Neural Networks under Limited Future Knowledge
1847. ICML 2025MIB: A Mechanistic Interpretability Benchmark
1848. ICML 2025Mind the Gap: A Practical Attack on GGUF Quantization
1849. ICML 2025Minimalist Concept Erasure in Generative Models
1850. ICML 2025Mitigating Local Cohesion and Global Sparseness in Graph Contrastive Learning with Fuzzy Boundaries

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.