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 18 of 26

851. NeurIPS 2025StyleGuard: Preventing Text-to-Image-Model-based Style Mimicry Attacks by Style Perturbations
852. NeurIPS 2025Subgraph Federated Learning via Spectral Methods
853. NeurIPS 2025Sum Estimation under Personalized Local Differential Privacy
854. NeurIPS 2025Synergistic Tensor and Pipeline Parallelism
855. NeurIPS 2025Synthesize Privacy-Preserving High-Resolution Images via Private Textual Intermediaries
856. NeurIPS 2025System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts
857. NeurIPS 2025Taming Hyperparameter Sensitivity in Data Attribution: Practical Selection Without Costly Retraining
858. NeurIPS 2025Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
859. NeurIPS 2025The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation
860. NeurIPS 2025The Boundaries of Fair AI in Medical Image Prognosis: A Causal Perspective
861. NeurIPS 2025The Complexity of Correlated Equilibria in Generalized Games
862. NeurIPS 2025The Cost of Compression: Tight Quadratic Black-Box Attacks on Sketches for $\ell_2$ Norm Estimation
863. NeurIPS 2025The emergence of sparse attention: impact of data distribution and benefits of repetition
864. NeurIPS 2025The Fluorescent Veil: A Stealthy and Effective Physical Adversarial Patch Against Traffic Sign Recognition
865. NeurIPS 2025The Future Unmarked: Watermark Removal in AI-Generated Images via Next-Frame Prediction
866. NeurIPS 2025The Hawthorne Effect in Reasoning Models: Evaluating and Steering Test Awareness
867. NeurIPS 2025The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?
868. NeurIPS 2025The Price of Opportunity Fairness in Matroid Allocation Problems
869. NeurIPS 2025The Rashomon Set Has It All: Analyzing Trustworthiness of Trees under Multiplicity
870. NeurIPS 2025The Rise of Parameter Specialization for Knowledge Storage in Large Language Models
871. NeurIPS 2025The Structure of Relation Decoding Linear Operators in Large Language Models
872. NeurIPS 2025The Temporal Graph of Bitcoin Transactions
873. NeurIPS 2025The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples
874. NeurIPS 2025The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense
875. NeurIPS 2025Tight Bounds on the Distortion of Randomized and Deterministic Distributed Voting
876. NeurIPS 2025Time-uniform and Asymptotic Confidence Sequence of Quantile under Local Differential Privacy
877. NeurIPS 2025TokenSwap: A Lightweight Method to Disrupt Memorized Sequences in LLMs
878. NeurIPS 2025Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge Retrieval
879. NeurIPS 2025TopER: Topological Embeddings in Graph Representation Learning
880. NeurIPS 2025Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement
881. NeurIPS 2025Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders
882. NeurIPS 2025Towards Interpretable and Efficient Attention: Compressing All by Contracting a Few
883. NeurIPS 2025Towards Irreversible Attack: Fooling Scene Text Recognition via Multi-Population Coevolution Search
884. NeurIPS 2025Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons
885. NeurIPS 2025ToxicTextCLIP: Text-Based Poisoning and Backdoor Attacks on CLIP Pre-training
886. NeurIPS 2025TraffiDent: A Dataset for Understanding the Interplay Between Traffic Dynamics and Incidents
887. NeurIPS 2025Train to Defend: First Defense Against Cryptanalytic Neural Network Parameter Extraction Attacks
888. NeurIPS 2025Training-free Detection of AI-generated images via Cropping Robustness
889. NeurIPS 2025Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models
890. NeurIPS 2025Transferring Linear Features Across Language Models With Model Stitching
891. NeurIPS 2025Transformer Key-Value Memories Are Nearly as Interpretable as Sparse Autoencoders
892. NeurIPS 2025Transstratal Adversarial Attack: Compromising Multi-Layered Defenses in Text-to-Image Models
893. NeurIPS 2025TRAP: Targeted Redirecting of Agentic Preferences
894. NeurIPS 2025TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets
895. NeurIPS 2025Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
896. NeurIPS 2025UMoE: Unifying Attention and FFN with Shared Experts
897. NeurIPS 2025Uncovering a Universal Abstract Algorithm for Modular Addition in Neural Networks
898. NeurIPS 2025Understanding and Improving Adversarial Robustness of Neural Probabilistic Circuits
899. NeurIPS 2025Understanding and Improving Fast Adversarial Training against $l_0$ Bounded Perturbations
900. NeurIPS 2025Understanding challenges to the interpretation of disaggregated evaluations of algorithmic fairness

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.