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 8 of 26

351. NeurIPS 2026The Algorithm Is Not the Behavior: Learned Priors Override Look-Ahead in a Chess-Playing Neural Network
352. NeurIPS 2026The Alignment Tax Concentrates in Output Projections
353. NeurIPS 2026The BatchNorm Illusion: Diagnosing Normalization Artifacts in Machine Unlearning Evaluation
354. NeurIPS 2026The Benefits of Temporal Correlations: SGD Efficiently Learns k-Juntas from Random Walks
355. NeurIPS 2026The Geometric Inductive Bias of Grokking: Bypassing Phase Transitions via Architectural Topology
356. NeurIPS 2026The Geometric Wall: Manifold Structure Predicts Layerwise Sparse Autoencoder Scaling Laws
357. NeurIPS 2026The Interplay of Data Structure and Imbalance in the Learning Dynamics of Diffusion Models
358. NeurIPS 2026The Kernel Reality Check: Benchmarking and Distilling Efficient Attention at Scale
359. NeurIPS 2026The Limits of AI-Driven Allocation: Optimal Screening under Aleatoric Uncertainty
360. NeurIPS 2026The Panel Complexity of Sortition: Is 12 Angry Men Enough?
361. NeurIPS 2026The parameters in weight-sparse transformers are interpretable
362. NeurIPS 2026The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment
363. NeurIPS 2026The Rate-Distortion-Polysemanticity Tradeoff in SAEs
364. NeurIPS 2026The Scaling Paradox of Tool-Calling LLM Agents Under Realistic MCP Faults
365. NeurIPS 2026The Structural Bias of $\ell_2$-Regularized Cross-Entropy Heads in Class-Incremental Learning: Characterization, Limits, and a Gauge-Anchoring Fix
366. NeurIPS 2026The SuperActivator Mechanism: Transformers Concentrate Reliable Concept Signals in the Tail
367. NeurIPS 2026Tight PAC-Bayes Generalisation Guarantees for Large Language Model Safety Monitoring
368. NeurIPS 2026Topological Periodicity Test (TopPT) via Confidence Bound of Time-Delay Embeddings
369. NeurIPS 2026Toward Optimal Regret in Robust Pricing: Decoupling Corruption and Time
370. NeurIPS 2026Towards Differentially Private Reinforcement Learning with General Function Approximation
371. NeurIPS 2026Towards Fair Graph Generation Without Sensitive Attribute
372. NeurIPS 2026Towards Understanding and Measuring Cognitive Atrophy in LLM Behaviour
373. NeurIPS 2026Tracing the Cascade: A Topology-Aware Evaluation Framework for Scientific Agent Hallucinations
374. NeurIPS 2026Training Language Models to Explain Their Own Computations
375. NeurIPS 2026Training ML Models with Predictable Failures
376. NeurIPS 2026Transfer Entropy as a Measure of Information Flow in VLMs and LLMs
377. NeurIPS 2026Transferring Visual Explainability from Self-Explaining to Prediction-Only Vision Transformers via Task Arithmetic
378. NeurIPS 2026TraXion: Rethinking Pre-training Frameworks for Mobility and Beyond
379. NeurIPS 2026TriBet: Relative E-values for Online Machine-generated Text Detection
380. NeurIPS 2026TRIDENT: Post-Selection Evidence Accountability for Token-Efficient RAG
381. NeurIPS 2026TrustMod-SM: A Multi-Axis Benchmark for Evaluating Trustworthiness of LLMs in Social Media Content Moderation
382. NeurIPS 2026Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent
383. NeurIPS 2026Uncovering Hidden Propensities in Language Models via Limited-Parameter Finetuning
384. NeurIPS 2026Uncovering the latent structure of interwoven population and temporal codes
385. NeurIPS 2026Understanding and Defending VLM Jailbreaks via Jailbreak-Related Representation Shift
386. NeurIPS 2026Understanding and Mitigating Under-Confidence in GNNs from the Final Layer
387. NeurIPS 2026Understanding Private Evolution as Learning-Augmented Clustering
388. NeurIPS 2026Uniform Diffusion Models revisited: Leave-One-Out Denoiser and Absorbing State Reformulation
389. NeurIPS 2026Uniform Spectral Growth under Factor-wise Muon Orthogonalization in Matrix Factorization and LoRA
390. NeurIPS 2026Uniform Stability and Generalization Error of GD and SGD on Fixed-Point Parameters
391. NeurIPS 2026Unifying Partner and Environment Diversity to Improve Human-AI Coordination
392. NeurIPS 2026UniVer: A Unified Perspective for Multi-step and Multi-draft Speculative Decoding
393. NeurIPS 2026Unsupervised Unlearnable Segmentation via Semantic Structure Disruption
394. NeurIPS 2026Untrusted Content Masking for Web Agents with Security Guarantees
395. NeurIPS 2026Values Are Not Single Labels: Distributional Value Profiling Across Groups and Contexts
396. NeurIPS 2026Verified-Source Authority Is Not Generic Sycophancy: Cue-Family Decomposition of LLM Compliance
397. NeurIPS 2026VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems
398. NeurIPS 2026VIGOR: Benchmarking Visual Rationale Correctness in Multimodal Large Language Models
399. NeurIPS 2026Watermarking as a Learned Intrinsic Property of Diffusion Models
400. NeurIPS 2026Watermarking Without Standards Is Not AI Governance

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.