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 13 of 26

601. NeurIPS 2025FlexAC: Towards Flexible Control of Associative Reasoning in Multimodal Large Language Models
602. NeurIPS 2025FlowMixer: A Depth-Agnostic Neural Architecture for Interpretable Spatiotemporal Forecasting
603. NeurIPS 2025FlowPrune: Accelerating Attention Flow Calculation by Pruning Flow Network
604. NeurIPS 2025FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts
605. NeurIPS 2025For Better or for Worse, Transformers Seek Patterns for Memorization
606. NeurIPS 2025Fostering the Ecosystem of AI for Social Impact Requires Expanding and Strengthening Evaluation Standards
607. NeurIPS 2025From Black-box to Causal-box: Towards Building More Interpretable Models
608. NeurIPS 2025From Counterfactuals to Trees: Competitive Analysis of Model Extraction Attacks
609. NeurIPS 2025From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit
610. NeurIPS 2025From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring
611. NeurIPS 2025From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers
612. NeurIPS 2025From Specificity to Generality: Revisiting Generalizable Artifacts in Detecting Face Deepfakes
613. NeurIPS 2025Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs
614. NeurIPS 2025Generative Model Inversion Through the Lens of the Manifold Hypothesis
615. NeurIPS 2025Generative RLHF-V: Learning Principles from Multi-modal Human Preference
616. NeurIPS 2025GeoClip: Geometry-Aware Clipping for Differentially Private SGD
617. NeurIPS 2025Geometric Imbalance in Semi-Supervised Node Classification
618. NeurIPS 2025Geometric Logit Decoupling for Energy-Based Graph Out-of-distribution Detection
619. NeurIPS 2025Geometry of Decision Making in Language Models
620. NeurIPS 2025GnnXemplar: Exemplars to Explanations - Natural Language Rules for Global GNN Interpretability
621. NeurIPS 2025GraphKeeper: Graph Domain-Incremental Learning via Knowledge Disentanglement and Preservation
622. NeurIPS 2025GraSS: Scalable Data Attribution with Gradient Sparsification and Sparse Projection
623. NeurIPS 2025Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMs
624. NeurIPS 2025GUARD: Constructing Realistic Two-Player Matrix and Security Games for Benchmarking Game-Theoretic Algorithms
625. NeurIPS 2025Guiding LLM Decision-Making with Fairness Reward Models
626. NeurIPS 2025Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferability
627. NeurIPS 2025Head Pursuit: Probing Attention Specialization in Multimodal Transformers
628. NeurIPS 2025HeavyWater and SimplexWater: Distortion-free LLM Watermarks for Low-Entropy Distributions
629. NeurIPS 2025Heterogeneous Diffusion Structure Inference for Network Cascade
630. NeurIPS 2025Hierarchical Frequency Tagging Probe (HFTP): A Unified Approach to Investigate Syntactic Structure Representations in Large Language Models and the Human Brain
631. NeurIPS 2025High-Order Flow Matching: Unified Framework and Sharp Statistical Rates
632. NeurIPS 2025Homogeneous Algorithms Can Reduce Competition in Personalized Pricing
633. NeurIPS 2025HouseLayout3D: A Benchmark and Training-free Baseline for 3D Layout Estimation in the Wild
634. NeurIPS 2025How do Transformers Learn Implicit Reasoning?
635. NeurIPS 2025How Well Can Differential Privacy Be Audited in One Run?
636. NeurIPS 2025Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection
637. NeurIPS 2025ICLScan: Detecting Backdoors in Black-Box Large Language Models via Targeted In-context Illumination
638. NeurIPS 2025Identifiability of Deep Polynomial Neural Networks
639. NeurIPS 2025IF-Guide: Influence Function-Guided Detoxification of LLMs
640. NeurIPS 2025ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression
641. NeurIPS 2025Imbalances in Neurosymbolic Learning: Characterization and Mitigating Strategies
642. NeurIPS 2025Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning
643. NeurIPS 2025Impact of Layer Norm on Memorization and Generalization in Transformers
644. NeurIPS 2025Improved Representation Steering for Language Models
645. NeurIPS 2025Improving Energy Natural Gradient Descent through Woodbury, Momentum, and Randomization
646. NeurIPS 2025Improving Model Representation and Reducing KV Cache via Skip Connections with First Value Heads
647. NeurIPS 2025Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibration
648. NeurIPS 2025Improving Task-Specific Multimodal Sentiment Analysis with General MLLMs via Prompting
649. NeurIPS 2025In-context Learning of Linear Dynamical Systems with Transformers: Approximation Bounds and Depth-separation
650. NeurIPS 2025In-Context Learning Strategies Emerge Rationally

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.