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 51 of 69

2501. NeurIPS 2025Vision Transformers Don't Need Trained Registers
2502. NeurIPS 2025VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set
2503. NeurIPS 2025Volume Transmission Implements Context Factorization to Target Online Credit Assignment and Enable Compositional Generalization
2504. NeurIPS 2025WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
2505. NeurIPS 2025Watermarking Autoregressive Image Generation
2506. NeurIPS 2025What Happens During the Loss Plateau? Understanding Abrupt Learning in Transformers
2507. NeurIPS 2025What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions
2508. NeurIPS 2025What Moves the Eyes: Doubling Mechanistic Model Performance Using Deep Networks to Discover and Test Cognitive Hypotheses
2509. NeurIPS 2025What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains
2510. NeurIPS 2025What Really is a Member? Discrediting Membership Inference via Poisoning
2511. NeurIPS 2025When Do Transformers Outperform Feedforward and Recurrent Networks? A Statistical Perspective
2512. NeurIPS 2025When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration
2513. NeurIPS 2025Who You Are Matters: Bridging Interests and Social Roles via LLM-Enhanced Logic Recommendation
2514. NeurIPS 2025Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations
2515. NeurIPS 2025Why Do Some Language Models Fake Alignment While Others Don't?
2516. NeurIPS 2025Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting
2517. NeurIPS 2025WMCopier: Forging Invisible Watermarks on Arbitrary Images
2518. NeurIPS 2025World Models Should Prioritize the Unification of Physical and Social Dynamics
2519. NeurIPS 2025You Only Communicate Once: One-shot Federated Low-Rank Adaptation of MLLM
2520. NeurIPS 2025Zero-Shot Detection of LLM-Generated Text via Implicit Reward Model
2521. NeurIPS 2025Zero-shot protein stability prediction by inverse folding models: a free energy interpretation
2522. CVPR 20241-Lipschitz Layers Compared: Memory Speed and Certifiable Robustness
2523. CVPR 2024A Semi-supervised Nighttime Dehazing Baseline with Spatial-Frequency Aware and Realistic Brightness Constraint
2524. CVPR 2024A Simple and Effective Point-based Network for Event Camera 6-DOFs Pose Relocalization
2525. CVPR 2024AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation
2526. CVPR 2024Alpha Invariance: On Inverse Scaling Between Distance and Volume Density in Neural Radiance Fields
2527. CVPR 2024Amodal Ground Truth and Completion in the Wild
2528. CVPR 2024An Edit Friendly DDPM Noise Space: Inversion and Manipulations
2529. CVPR 2024Artist-Friendly Relightable and Animatable Neural Heads
2530. CVPR 2024ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe
2531. CVPR 2024Boosting Adversarial Transferability by Block Shuffle and Rotation
2532. CVPR 2024C^2RV: Cross-Regional and Cross-View Learning for Sparse-View CBCT Reconstruction
2533. CVPR 2024Consistency and Uncertainty: Identifying Unreliable Responses From Black-Box Vision-Language Models for Selective Visual Question Answering
2534. CVPR 2024Data Valuation and Detections in Federated Learning
2535. CVPR 2024Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation
2536. CVPR 2024DeCoTR: Enhancing Depth Completion with 2D and 3D Attentions
2537. CVPR 2024Denoising Point Clouds in Latent Space via Graph Convolution and Invertible Neural Network
2538. CVPR 2024DGC-GNN: Leveraging Geometry and Color Cues for Visual Descriptor-Free 2D-3D Matching
2539. CVPR 2024Digital Life Project: Autonomous 3D Characters with Social Intelligence
2540. CVPR 2024DiLiGenRT: A Photometric Stereo Dataset with Quantified Roughness and Translucency
2541. CVPR 2024Distilled Datamodel with Reverse Gradient Matching
2542. CVPR 2024DITTO: Dual and Integrated Latent Topologies for Implicit 3D Reconstruction
2543. CVPR 2024DREAM: Diffusion Rectification and Estimation-Adaptive Models
2544. CVPR 2024DreamVideo: Composing Your Dream Videos with Customized Subject and Motion
2545. CVPR 2024EASE-DETR: Easing the Competition among Object Queries
2546. CVPR 2024Eclipse: Disambiguating Illumination and Materials using Unintended Shadows
2547. CVPR 2024Efficient Meshflow and Optical Flow Estimation from Event Cameras
2548. CVPR 2024EfficientDreamer: High-Fidelity and Robust 3D Creation via Orthogonal-view Diffusion Priors
2549. CVPR 2024Entity-NeRF: Detecting and Removing Moving Entities in Urban Scenes
2550. CVPR 2024EvDiG: Event-guided Direct and Global Components Separation

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.